Hugging Face's logo

Spaces:
gauthamk
/
pytorch-resnet34-bird-classification
Sleeping

App Files Community
gauthamk commited on
Commit
97d74ab
•
1 Parent(s): 0ab32f0

Modify Model

Browse files
Files changed (4) hide show
  1. .gitignore +2 -1
  2. notebooks/onnx-testing.ipynb +9 -9
  3. notebooks/{pytorch-birds-resnet34.ipynb → pytorch-resnet34-birds-classification.ipynb} +0 -0
  4. notebooks/torch-to-onnx.ipynb +246 -205
.gitignore CHANGED
@@ -1,2 +1,3 @@
1
  *.pth
2
- data/*
 
 
1
  *.pth
2
+ data/*
3
+ __pycache__/
notebooks/onnx-testing.ipynb CHANGED
@@ -9,7 +9,7 @@
9
  },
10
  {
11
  "cell_type": "code",
12
- "execution_count": 4,
13
  "metadata": {},
14
  "outputs": [],
15
  "source": [
@@ -29,7 +29,7 @@
29
  },
30
  {
31
  "cell_type": "code",
32
- "execution_count": 51,
33
  "metadata": {},
34
  "outputs": [],
35
  "source": [
@@ -48,16 +48,16 @@
48
  },
49
  {
50
  "cell_type": "code",
51
- "execution_count": 52,
52
  "metadata": {},
53
  "outputs": [
54
  {
55
  "data": {
56
  "text/plain": [
57
- "<matplotlib.image.AxesImage at 0x7f2a86e44400>"
58
  ]
59
  },
60
- "execution_count": 52,
61
  "metadata": {},
62
  "output_type": "execute_result"
63
  },
@@ -78,7 +78,7 @@
78
  },
79
  {
80
  "cell_type": "code",
81
- "execution_count": 53,
82
  "metadata": {},
83
  "outputs": [
84
  {
@@ -91,10 +91,10 @@
91
  {
92
  "data": {
93
  "text/plain": [
94
- "<matplotlib.image.AxesImage at 0x7f2a86e93430>"
95
  ]
96
  },
97
- "execution_count": 53,
98
  "metadata": {},
99
  "output_type": "execute_result"
100
  },
@@ -133,7 +133,7 @@
133
  },
134
  {
135
  "cell_type": "code",
136
- "execution_count": 54,
137
  "metadata": {},
138
  "outputs": [
139
  {
 
9
  },
10
  {
11
  "cell_type": "code",
12
+ "execution_count": 1,
13
  "metadata": {},
14
  "outputs": [],
15
  "source": [
 
29
  },
30
  {
31
  "cell_type": "code",
32
+ "execution_count": 6,
33
  "metadata": {},
34
  "outputs": [],
35
  "source": [
 
48
  },
49
  {
50
  "cell_type": "code",
51
+ "execution_count": 7,
52
  "metadata": {},
53
  "outputs": [
54
  {
55
  "data": {
56
  "text/plain": [
57
+ "<matplotlib.image.AxesImage at 0x7f09fcc27e20>"
58
  ]
59
  },
60
+ "execution_count": 7,
61
  "metadata": {},
62
  "output_type": "execute_result"
63
  },
 
78
  },
79
  {
80
  "cell_type": "code",
81
+ "execution_count": 8,
82
  "metadata": {},
83
  "outputs": [
84
  {
 
91
  {
92
  "data": {
93
  "text/plain": [
94
+ "<matplotlib.image.AxesImage at 0x7f09fccb62c0>"
95
  ]
96
  },
97
+ "execution_count": 8,
98
  "metadata": {},
99
  "output_type": "execute_result"
100
  },
 
133
  },
134
  {
135
  "cell_type": "code",
136
+ "execution_count": 9,
137
  "metadata": {},
138
  "outputs": [
139
  {
notebooks/{pytorch-birds-resnet34.ipynb → pytorch-resnet34-birds-classification.ipynb} RENAMED
The diff for this file is too large to render. See raw diff
 
notebooks/torch-to-onnx.ipynb CHANGED
@@ -13,18 +13,19 @@
13
  "metadata": {},
14
  "outputs": [
15
  {
16
- "name": "stderr",
17
  "output_type": "stream",
18
  "text": [
19
- "/home/gautham/.local/lib/python3.10/site-packages/tqdm/auto.py:22: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
20
- " from .autonotebook import tqdm as notebook_tqdm\n"
21
  ]
22
  }
23
  ],
24
  "source": [
25
  "import torch\n",
26
  "from torch import nn\n",
27
- "from torch.nn import functional as F"
 
 
28
  ]
29
  },
30
  {
@@ -40,84 +41,76 @@
40
  "metadata": {},
41
  "outputs": [],
42
  "source": [
43
- "class DoubleConv(nn.Module):\n",
44
- " def __init__(self, in_channels, out_channels):\n",
45
- " super().__init__()\n",
46
- " self.conv = nn.Sequential(\n",
47
- " nn.Conv2d(in_channels, out_channels, 3, padding=1),\n",
48
- " nn.BatchNorm2d(out_channels),\n",
49
- " nn.ReLU(inplace=True),\n",
50
- " nn.Conv2d(out_channels, out_channels, 3, padding=1),\n",
51
- " nn.BatchNorm2d(out_channels),\n",
52
- " nn.ReLU(inplace=True)\n",
53
- " )\n",
54
- " def forward(self, x):\n",
55
- " return self.conv(x)\n",
56
  "\n",
57
- "class Down(nn.Module):\n",
58
- " def __init__(self, in_channels, out_channels):\n",
59
  " super().__init__()\n",
60
- " self.down = nn.Sequential(\n",
61
- " nn.MaxPool2d(2),\n",
62
- " DoubleConv(in_channels, out_channels)\n",
63
- " )\n",
 
 
 
 
 
 
 
 
 
64
  " def forward(self, x):\n",
65
- " return self.down(x)\n",
 
 
66
  "\n",
67
- "class Up(nn.Module):\n",
68
- " def __init__(self, in_channels, out_channels, bilinear=False):\n",
69
- " super().__init__()\n",
70
- " if bilinear:\n",
71
- " self.up = nn.Sequential(nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True),\n",
72
- " nn.Conv2d(in_channels, in_channels // 2, 1))\n",
73
- " else:\n",
74
- " self.up = nn.ConvTranspose2d(in_channels, in_channels // 2, 2, stride=2)\n",
75
- " \n",
76
- " self.conv = DoubleConv(in_channels, out_channels)\n",
77
  "\n",
78
- " def forward(self, x1, x2):\n",
79
- " x1 = self.up(x1)\n",
80
- " diffY = x2.size()[2] - x1.size()[2]\n",
81
- " diffX = x2.size()[3] - x1.size()[3]\n",
82
- " x1 = F.pad(x1, [diffX // 2, diffX - diffX // 2, diffY // 2, diffY - diffY // 2])\n",
83
- " x = torch.cat([x2, x1], dim=1)\n",
84
- " return self.conv(x)\n",
85
  "\n",
86
- "class OutConv(nn.Module):\n",
87
- " def __init__(self, in_channels, out_channels):\n",
88
- " super().__init__()\n",
89
- " self.conv = nn.Conv2d(in_channels, out_channels, 1)\n",
90
- " self.sigmoid = nn.Sigmoid()\n",
91
  "\n",
92
- " def forward(self, x):\n",
93
- " return self.sigmoid(self.conv(x))\n",
94
  "\n",
95
- "class UNet(nn.Module):\n",
96
- " def __init__(self, n_channels, n_classes):\n",
97
  " super().__init__()\n",
98
- " self.inc = DoubleConv(n_channels, 64)\n",
99
- " self.down1 = Down(64, 128)\n",
100
- " self.down2 = Down(128, 256)\n",
101
- " self.down3 = Down(256, 512)\n",
102
- " self.down4 = Down(512, 1024)\n",
103
- " self.up1 = Up(1024, 512)\n",
104
- " self.up2 = Up(512, 256)\n",
105
- " self.up3 = Up(256, 128)\n",
106
- " self.up4 = Up(128, 64)\n",
107
- " self.outc = OutConv(64, n_classes)\n",
 
 
 
 
 
 
 
 
 
 
 
108
  "\n",
109
  " def forward(self, x):\n",
110
- " x1 = self.inc(x)\n",
111
- " x2 = self.down1(x1)\n",
112
- " x3 = self.down2(x2)\n",
113
- " x4 = self.down3(x3)\n",
114
- " x5 = self.down4(x4)\n",
115
- " x = self.up1(x5, x4)\n",
116
- " x = self.up2(x4, x3)\n",
117
- " x = self.up3(x3, x2)\n",
118
- " x = self.up4(x2, x1)\n",
119
- " logits = self.outc(x)\n",
120
- " return logits"
 
 
121
  ]
122
  },
123
  {
@@ -131,31 +124,12 @@
131
  "cell_type": "code",
132
  "execution_count": 3,
133
  "metadata": {},
134
- "outputs": [
135
- {
136
- "ename": "RuntimeError",
137
- "evalue": "Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.",
138
- "output_type": "error",
139
- "traceback": [
140
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
141
- "\u001b[0;31mRuntimeError\u001b[0m Traceback (most recent call last)",
142
- "Cell \u001b[0;32mIn [3], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m model \u001b[39m=\u001b[39m UNet(n_channels\u001b[39m=\u001b[39m\u001b[39m3\u001b[39m, n_classes\u001b[39m=\u001b[39m\u001b[39m1\u001b[39m)\n\u001b[0;32m----> 2\u001b[0m model\u001b[39m.\u001b[39mload_state_dict(torch\u001b[39m.\u001b[39;49mload(\u001b[39m'\u001b[39;49m\u001b[39m../weights/water_bodies_model.pth\u001b[39;49m\u001b[39m'\u001b[39;49m))\n\u001b[1;32m 3\u001b[0m model\u001b[39m.\u001b[39mto(\u001b[39m'\u001b[39m\u001b[39mcpu\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[1;32m 5\u001b[0m dummy_input \u001b[39m=\u001b[39m torch\u001b[39m.\u001b[39mrandn(\u001b[39m1\u001b[39m, \u001b[39m3\u001b[39m, \u001b[39m256\u001b[39m, \u001b[39m256\u001b[39m)\n",
143
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torch/serialization.py:789\u001b[0m, in \u001b[0;36mload\u001b[0;34m(f, map_location, pickle_module, weights_only, **pickle_load_args)\u001b[0m\n\u001b[1;32m 787\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mRuntimeError\u001b[39;00m \u001b[39mas\u001b[39;00m e:\n\u001b[1;32m 788\u001b[0m \u001b[39mraise\u001b[39;00m pickle\u001b[39m.\u001b[39mUnpicklingError(UNSAFE_MESSAGE \u001b[39m+\u001b[39m \u001b[39mstr\u001b[39m(e)) \u001b[39mfrom\u001b[39;00m \u001b[39mNone\u001b[39m\n\u001b[0;32m--> 789\u001b[0m \u001b[39mreturn\u001b[39;00m _load(opened_zipfile, map_location, pickle_module, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mpickle_load_args)\n\u001b[1;32m 790\u001b[0m \u001b[39mif\u001b[39;00m weights_only:\n\u001b[1;32m 791\u001b[0m \u001b[39mtry\u001b[39;00m:\n",
144
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torch/serialization.py:1131\u001b[0m, in \u001b[0;36m_load\u001b[0;34m(zip_file, map_location, pickle_module, pickle_file, **pickle_load_args)\u001b[0m\n\u001b[1;32m 1129\u001b[0m unpickler \u001b[39m=\u001b[39m UnpicklerWrapper(data_file, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mpickle_load_args)\n\u001b[1;32m 1130\u001b[0m unpickler\u001b[39m.\u001b[39mpersistent_load \u001b[39m=\u001b[39m persistent_load\n\u001b[0;32m-> 1131\u001b[0m result \u001b[39m=\u001b[39m unpickler\u001b[39m.\u001b[39;49mload()\n\u001b[1;32m 1133\u001b[0m torch\u001b[39m.\u001b[39m_utils\u001b[39m.\u001b[39m_validate_loaded_sparse_tensors()\n\u001b[1;32m 1135\u001b[0m \u001b[39mreturn\u001b[39;00m result\n",
145
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torch/serialization.py:1101\u001b[0m, in \u001b[0;36m_load.<locals>.persistent_load\u001b[0;34m(saved_id)\u001b[0m\n\u001b[1;32m 1099\u001b[0m \u001b[39mif\u001b[39;00m key \u001b[39mnot\u001b[39;00m \u001b[39min\u001b[39;00m loaded_storages:\n\u001b[1;32m 1100\u001b[0m nbytes \u001b[39m=\u001b[39m numel \u001b[39m*\u001b[39m torch\u001b[39m.\u001b[39m_utils\u001b[39m.\u001b[39m_element_size(dtype)\n\u001b[0;32m-> 1101\u001b[0m load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location))\n\u001b[1;32m 1103\u001b[0m \u001b[39mreturn\u001b[39;00m loaded_storages[key]\n",
146
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torch/serialization.py:1083\u001b[0m, in \u001b[0;36m_load.<locals>.load_tensor\u001b[0;34m(dtype, numel, key, location)\u001b[0m\n\u001b[1;32m 1079\u001b[0m storage \u001b[39m=\u001b[39m zip_file\u001b[39m.\u001b[39mget_storage_from_record(name, numel, torch\u001b[39m.\u001b[39mUntypedStorage)\u001b[39m.\u001b[39mstorage()\u001b[39m.\u001b[39muntyped()\n\u001b[1;32m 1080\u001b[0m \u001b[39m# TODO: Once we decide to break serialization FC, we can\u001b[39;00m\n\u001b[1;32m 1081\u001b[0m \u001b[39m# stop wrapping with TypedStorage\u001b[39;00m\n\u001b[1;32m 1082\u001b[0m loaded_storages[key] \u001b[39m=\u001b[39m torch\u001b[39m.\u001b[39mstorage\u001b[39m.\u001b[39mTypedStorage(\n\u001b[0;32m-> 1083\u001b[0m wrap_storage\u001b[39m=\u001b[39mrestore_location(storage, location),\n\u001b[1;32m 1084\u001b[0m dtype\u001b[39m=\u001b[39mdtype)\n",
147
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torch/serialization.py:215\u001b[0m, in \u001b[0;36mdefault_restore_location\u001b[0;34m(storage, location)\u001b[0m\n\u001b[1;32m 213\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mdefault_restore_location\u001b[39m(storage, location):\n\u001b[1;32m 214\u001b[0m \u001b[39mfor\u001b[39;00m _, _, fn \u001b[39min\u001b[39;00m _package_registry:\n\u001b[0;32m--> 215\u001b[0m result \u001b[39m=\u001b[39m fn(storage, location)\n\u001b[1;32m 216\u001b[0m \u001b[39mif\u001b[39;00m result \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m 217\u001b[0m \u001b[39mreturn\u001b[39;00m result\n",
148
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torch/serialization.py:182\u001b[0m, in \u001b[0;36m_cuda_deserialize\u001b[0;34m(obj, location)\u001b[0m\n\u001b[1;32m 180\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_cuda_deserialize\u001b[39m(obj, location):\n\u001b[1;32m 181\u001b[0m \u001b[39mif\u001b[39;00m location\u001b[39m.\u001b[39mstartswith(\u001b[39m'\u001b[39m\u001b[39mcuda\u001b[39m\u001b[39m'\u001b[39m):\n\u001b[0;32m--> 182\u001b[0m device \u001b[39m=\u001b[39m validate_cuda_device(location)\n\u001b[1;32m 183\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mgetattr\u001b[39m(obj, \u001b[39m\"\u001b[39m\u001b[39m_torch_load_uninitialized\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39mFalse\u001b[39;00m):\n\u001b[1;32m 184\u001b[0m \u001b[39mwith\u001b[39;00m torch\u001b[39m.\u001b[39mcuda\u001b[39m.\u001b[39mdevice(device):\n",
149
- "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torch/serialization.py:166\u001b[0m, in \u001b[0;36mvalidate_cuda_device\u001b[0;34m(location)\u001b[0m\n\u001b[1;32m 163\u001b[0m device \u001b[39m=\u001b[39m torch\u001b[39m.\u001b[39mcuda\u001b[39m.\u001b[39m_utils\u001b[39m.\u001b[39m_get_device_index(location, \u001b[39mTrue\u001b[39;00m)\n\u001b[1;32m 165\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m torch\u001b[39m.\u001b[39mcuda\u001b[39m.\u001b[39mis_available():\n\u001b[0;32m--> 166\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mRuntimeError\u001b[39;00m(\u001b[39m'\u001b[39m\u001b[39mAttempting to deserialize object on a CUDA \u001b[39m\u001b[39m'\u001b[39m\n\u001b[1;32m 167\u001b[0m \u001b[39m'\u001b[39m\u001b[39mdevice but torch.cuda.is_available() is False. \u001b[39m\u001b[39m'\u001b[39m\n\u001b[1;32m 168\u001b[0m \u001b[39m'\u001b[39m\u001b[39mIf you are running on a CPU-only machine, \u001b[39m\u001b[39m'\u001b[39m\n\u001b[1;32m 169\u001b[0m \u001b[39m'\u001b[39m\u001b[39mplease use torch.load with map_location=torch.device(\u001b[39m\u001b[39m\\'\u001b[39;00m\u001b[39mcpu\u001b[39m\u001b[39m\\'\u001b[39;00m\u001b[39m) \u001b[39m\u001b[39m'\u001b[39m\n\u001b[1;32m 170\u001b[0m \u001b[39m'\u001b[39m\u001b[39mto map your storages to the CPU.\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[1;32m 171\u001b[0m device_count \u001b[39m=\u001b[39m torch\u001b[39m.\u001b[39mcuda\u001b[39m.\u001b[39mdevice_count()\n\u001b[1;32m 172\u001b[0m \u001b[39mif\u001b[39;00m device \u001b[39m>\u001b[39m\u001b[39m=\u001b[39m device_count:\n",
150
- "\u001b[0;31mRuntimeError\u001b[0m: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU."
151
- ]
152
- }
153
- ],
154
  "source": [
155
- "model = UNet(n_channels=3, n_classes=1)\n",
156
- "model.load_state_dict(torch.load('../weights/water_bodies_model.pth'))\n",
157
  "\n",
158
- "dummy_input = torch.randn(1, 3, 256, 256)\n",
159
  "\n",
160
  "model.eval()\n",
161
  "torch_out = model(dummy_input)"
@@ -170,127 +144,194 @@
170
  },
171
  {
172
  "cell_type": "code",
173
- "execution_count": null,
174
  "metadata": {},
175
  "outputs": [
176
  {
177
  "name": "stdout",
178
  "output_type": "stream",
179
  "text": [
180
- "Exported graph: graph(%input : Float(*, 3, 256, 256, strides=[196608, 65536, 256, 1], requires_grad=0, device=cpu),\n",
181
- " %up4.up.weight : Float(128, 64, 2, 2, strides=[256, 4, 2, 1], requires_grad=1, device=cpu),\n",
182
- " %up4.up.bias : Float(64, strides=[1], requires_grad=1, device=cpu),\n",
183
- " %outc.conv.weight : Float(1, 64, 1, 1, strides=[64, 1, 1, 1], requires_grad=1, device=cpu),\n",
184
- " %outc.conv.bias : Float(1, strides=[1], requires_grad=1, device=cpu),\n",
185
- " %onnx::Conv_226 : Float(64, 3, 3, 3, strides=[27, 9, 3, 1], requires_grad=0, device=cpu),\n",
186
- " %onnx::Conv_227 : Float(64, strides=[1], requires_grad=0, device=cpu),\n",
187
- " %onnx::Conv_229 : Float(64, 64, 3, 3, strides=[576, 9, 3, 1], requires_grad=0, device=cpu),\n",
188
- " %onnx::Conv_230 : Float(64, strides=[1], requires_grad=0, device=cpu),\n",
189
- " %onnx::Conv_232 : Float(128, 64, 3, 3, strides=[576, 9, 3, 1], requires_grad=0, device=cpu),\n",
190
- " %onnx::Conv_233 : Float(128, strides=[1], requires_grad=0, device=cpu),\n",
191
- " %onnx::Conv_235 : Float(128, 128, 3, 3, strides=[1152, 9, 3, 1], requires_grad=0, device=cpu),\n",
192
- " %onnx::Conv_236 : Float(128, strides=[1], requires_grad=0, device=cpu),\n",
193
- " %onnx::Conv_238 : Float(64, 128, 3, 3, strides=[1152, 9, 3, 1], requires_grad=0, device=cpu),\n",
194
- " %onnx::Conv_239 : Float(64, strides=[1], requires_grad=0, device=cpu),\n",
195
- " %onnx::Conv_241 : Float(64, 64, 3, 3, strides=[576, 9, 3, 1], requires_grad=0, device=cpu),\n",
196
- " %onnx::Conv_242 : Float(64, strides=[1], requires_grad=0, device=cpu)):\n",
197
- " %/inc/conv/conv.0/Conv_output_0 : Float(*, 64, 256, 256, strides=[4194304, 65536, 256, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/inc/conv/conv.0/Conv\"](%input, %onnx::Conv_226, %onnx::Conv_227), scope: __main__.UNet::/__main__.DoubleConv::inc/torch.nn.modules.container.Sequential::conv/torch.nn.modules.conv.Conv2d::conv.0 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
198
- " %/inc/conv/conv.2/Relu_output_0 : Float(*, 64, 256, 256, strides=[4194304, 65536, 256, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/inc/conv/conv.2/Relu\"](%/inc/conv/conv.0/Conv_output_0), scope: __main__.UNet::/__main__.DoubleConv::inc/torch.nn.modules.container.Sequential::conv/torch.nn.modules.activation.ReLU::conv.2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
199
- " %/inc/conv/conv.3/Conv_output_0 : Float(*, 64, 256, 256, strides=[4194304, 65536, 256, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/inc/conv/conv.3/Conv\"](%/inc/conv/conv.2/Relu_output_0, %onnx::Conv_229, %onnx::Conv_230), scope: __main__.UNet::/__main__.DoubleConv::inc/torch.nn.modules.container.Sequential::conv/torch.nn.modules.conv.Conv2d::conv.3 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
200
- " %/inc/conv/conv.5/Relu_output_0 : Float(*, 64, 256, 256, strides=[4194304, 65536, 256, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/inc/conv/conv.5/Relu\"](%/inc/conv/conv.3/Conv_output_0), scope: __main__.UNet::/__main__.DoubleConv::inc/torch.nn.modules.container.Sequential::conv/torch.nn.modules.activation.ReLU::conv.5 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
201
- " %/down1/down/down.0/MaxPool_output_0 : Float(*, 64, 128, 128, strides=[1048576, 16384, 128, 1], requires_grad=1, device=cpu) = onnx::MaxPool[ceil_mode=0, kernel_shape=[2, 2], pads=[0, 0, 0, 0], strides=[2, 2], onnx_name=\"/down1/down/down.0/MaxPool\"](%/inc/conv/conv.5/Relu_output_0), scope: __main__.UNet::/__main__.Down::down1/torch.nn.modules.container.Sequential::down/torch.nn.modules.pooling.MaxPool2d::down.0 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:780:0\n",
202
- " %/down1/down/down.1/conv/conv.0/Conv_output_0 : Float(*, 128, 128, 128, strides=[2097152, 16384, 128, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/down1/down/down.1/conv/conv.0/Conv\"](%/down1/down/down.0/MaxPool_output_0, %onnx::Conv_232, %onnx::Conv_233), scope: __main__.UNet::/__main__.Down::down1/torch.nn.modules.container.Sequential::down/__main__.DoubleConv::down.1/torch.nn.modules.container.Sequential::conv/torch.nn.modules.conv.Conv2d::conv.0 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
203
- " %/down1/down/down.1/conv/conv.2/Relu_output_0 : Float(*, 128, 128, 128, strides=[2097152, 16384, 128, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/down1/down/down.1/conv/conv.2/Relu\"](%/down1/down/down.1/conv/conv.0/Conv_output_0), scope: __main__.UNet::/__main__.Down::down1/torch.nn.modules.container.Sequential::down/__main__.DoubleConv::down.1/torch.nn.modules.container.Sequential::conv/torch.nn.modules.activation.ReLU::conv.2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
204
- " %/down1/down/down.1/conv/conv.3/Conv_output_0 : Float(*, 128, 128, 128, strides=[2097152, 16384, 128, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/down1/down/down.1/conv/conv.3/Conv\"](%/down1/down/down.1/conv/conv.2/Relu_output_0, %onnx::Conv_235, %onnx::Conv_236), scope: __main__.UNet::/__main__.Down::down1/torch.nn.modules.container.Sequential::down/__main__.DoubleConv::down.1/torch.nn.modules.container.Sequential::conv/torch.nn.modules.conv.Conv2d::conv.3 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
205
- " %/down1/down/down.1/conv/conv.5/Relu_output_0 : Float(*, 128, 128, 128, strides=[2097152, 16384, 128, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/down1/down/down.1/conv/conv.5/Relu\"](%/down1/down/down.1/conv/conv.3/Conv_output_0), scope: __main__.UNet::/__main__.Down::down1/torch.nn.modules.container.Sequential::down/__main__.DoubleConv::down.1/torch.nn.modules.container.Sequential::conv/torch.nn.modules.activation.ReLU::conv.5 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
206
- " %/up4/up/ConvTranspose_output_0 : Float(*, 64, 256, 256, strides=[4194304, 65536, 256, 1], requires_grad=0, device=cpu) = onnx::ConvTranspose[dilations=[1, 1], group=1, kernel_shape=[2, 2], pads=[0, 0, 0, 0], strides=[2, 2], onnx_name=\"/up4/up/ConvTranspose\"](%/down1/down/down.1/conv/conv.5/Relu_output_0, %up4.up.weight, %up4.up.bias), scope: __main__.UNet::/__main__.Up::up4/torch.nn.modules.conv.ConvTranspose2d::up # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:953:0\n",
207
- " %/up4/Shape_output_0 : Long(4, strides=[1], device=cpu) = onnx::Shape[onnx_name=\"/up4/Shape\"](%/inc/conv/conv.5/Relu_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:37:0\n",
208
- " %/up4/Constant_output_0 : Long(device=cpu) = onnx::Constant[value={2}, onnx_name=\"/up4/Constant\"](), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:37:0\n",
209
- " %/up4/Gather_output_0 : Long(device=cpu) = onnx::Gather[axis=0, onnx_name=\"/up4/Gather\"](%/up4/Shape_output_0, %/up4/Constant_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:37:0\n",
210
- " %/up4/Shape_1_output_0 : Long(4, strides=[1], device=cpu) = onnx::Shape[onnx_name=\"/up4/Shape_1\"](%/up4/up/ConvTranspose_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:38:0\n",
211
- " %/up4/Constant_1_output_0 : Long(device=cpu) = onnx::Constant[value={2}, onnx_name=\"/up4/Constant_1\"](), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:38:0\n",
212
- " %/up4/Gather_1_output_0 : Long(device=cpu) = onnx::Gather[axis=0, onnx_name=\"/up4/Gather_1\"](%/up4/Shape_1_output_0, %/up4/Constant_1_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:38:0\n",
213
- " %/up4/Sub_output_0 : Long(requires_grad=0, device=cpu) = onnx::Sub[onnx_name=\"/up4/Sub\"](%/up4/Gather_output_0, %/up4/Gather_1_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:38:0\n",
214
- " %/up4/Shape_2_output_0 : Long(4, strides=[1], device=cpu) = onnx::Shape[onnx_name=\"/up4/Shape_2\"](%/inc/conv/conv.5/Relu_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:38:0\n",
215
- " %/up4/Constant_2_output_0 : Long(device=cpu) = onnx::Constant[value={3}, onnx_name=\"/up4/Constant_2\"](), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:38:0\n",
216
- " %/up4/Gather_2_output_0 : Long(device=cpu) = onnx::Gather[axis=0, onnx_name=\"/up4/Gather_2\"](%/up4/Shape_2_output_0, %/up4/Constant_2_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:38:0\n",
217
- " %/up4/Shape_3_output_0 : Long(4, strides=[1], device=cpu) = onnx::Shape[onnx_name=\"/up4/Shape_3\"](%/up4/up/ConvTranspose_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:38:0\n",
218
- " %/up4/Constant_3_output_0 : Long(device=cpu) = onnx::Constant[value={3}, onnx_name=\"/up4/Constant_3\"](), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:38:0\n",
219
- " %/up4/Gather_3_output_0 : Long(device=cpu) = onnx::Gather[axis=0, onnx_name=\"/up4/Gather_3\"](%/up4/Shape_3_output_0, %/up4/Constant_3_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:38:0\n",
220
- " %/up4/Sub_1_output_0 : Long(requires_grad=0, device=cpu) = onnx::Sub[onnx_name=\"/up4/Sub_1\"](%/up4/Gather_2_output_0, %/up4/Gather_3_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:38:0\n",
221
- " %/up4/Constant_4_output_0 : Long(requires_grad=0, device=cpu) = onnx::Constant[value={2}, onnx_name=\"/up4/Constant_4\"](), scope: __main__.UNet::/__main__.Up::up4 # /home/gautham/.local/lib/python3.10/site-packages/torch/_tensor.py:867:0\n",
222
- " %/up4/Div_output_0 : Long(device=cpu) = onnx::Div[onnx_name=\"/up4/Div\"](%/up4/Sub_1_output_0, %/up4/Constant_4_output_0), scope: __main__.UNet::/__main__.Up::up4 # /home/gautham/.local/lib/python3.10/site-packages/torch/_tensor.py:867:0\n",
223
- " %/up4/Cast_output_0 : Long(device=cpu) = onnx::Cast[to=7, onnx_name=\"/up4/Cast\"](%/up4/Div_output_0), scope: __main__.UNet::/__main__.Up::up4 # /home/gautham/.local/lib/python3.10/site-packages/torch/_tensor.py:867:0\n",
224
- " %/up4/Cast_1_output_0 : Long(requires_grad=0, device=cpu) = onnx::Cast[to=7, onnx_name=\"/up4/Cast_1\"](%/up4/Cast_output_0), scope: __main__.UNet::/__main__.Up::up4 # /home/gautham/.local/lib/python3.10/site-packages/torch/_tensor.py:867:0\n",
225
- " %/up4/Sub_2_output_0 : Long(requires_grad=0, device=cpu) = onnx::Sub[onnx_name=\"/up4/Sub_2\"](%/up4/Sub_1_output_0, %/up4/Cast_1_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
226
- " %/up4/Constant_5_output_0 : Long(requires_grad=0, device=cpu) = onnx::Constant[value={2}, onnx_name=\"/up4/Constant_5\"](), scope: __main__.UNet::/__main__.Up::up4 # /home/gautham/.local/lib/python3.10/site-packages/torch/_tensor.py:867:0\n",
227
- " %/up4/Div_1_output_0 : Long(device=cpu) = onnx::Div[onnx_name=\"/up4/Div_1\"](%/up4/Sub_output_0, %/up4/Constant_5_output_0), scope: __main__.UNet::/__main__.Up::up4 # /home/gautham/.local/lib/python3.10/site-packages/torch/_tensor.py:867:0\n",
228
- " %/up4/Cast_2_output_0 : Long(device=cpu) = onnx::Cast[to=7, onnx_name=\"/up4/Cast_2\"](%/up4/Div_1_output_0), scope: __main__.UNet::/__main__.Up::up4 # /home/gautham/.local/lib/python3.10/site-packages/torch/_tensor.py:867:0\n",
229
- " %/up4/Cast_3_output_0 : Long(requires_grad=0, device=cpu) = onnx::Cast[to=7, onnx_name=\"/up4/Cast_3\"](%/up4/Cast_2_output_0), scope: __main__.UNet::/__main__.Up::up4 # /home/gautham/.local/lib/python3.10/site-packages/torch/_tensor.py:867:0\n",
230
- " %/up4/Sub_3_output_0 : Long(requires_grad=0, device=cpu) = onnx::Sub[onnx_name=\"/up4/Sub_3\"](%/up4/Sub_output_0, %/up4/Cast_3_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
231
- " %onnx::Unsqueeze_175 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={0}]()\n",
232
- " %/up4/Unsqueeze_output_0 : Long(1, strides=[1], device=cpu) = onnx::Unsqueeze[onnx_name=\"/up4/Unsqueeze\"](%/up4/Cast_1_output_0, %onnx::Unsqueeze_175), scope: __main__.UNet::/__main__.Up::up4\n",
233
- " %onnx::Unsqueeze_177 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={0}]()\n",
234
- " %/up4/Unsqueeze_1_output_0 : Long(1, strides=[1], device=cpu) = onnx::Unsqueeze[onnx_name=\"/up4/Unsqueeze_1\"](%/up4/Sub_2_output_0, %onnx::Unsqueeze_177), scope: __main__.UNet::/__main__.Up::up4\n",
235
- " %onnx::Unsqueeze_179 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={0}]()\n",
236
- " %/up4/Unsqueeze_2_output_0 : Long(1, strides=[1], device=cpu) = onnx::Unsqueeze[onnx_name=\"/up4/Unsqueeze_2\"](%/up4/Cast_3_output_0, %onnx::Unsqueeze_179), scope: __main__.UNet::/__main__.Up::up4\n",
237
- " %onnx::Unsqueeze_181 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={0}]()\n",
238
- " %/up4/Unsqueeze_3_output_0 : Long(1, strides=[1], device=cpu) = onnx::Unsqueeze[onnx_name=\"/up4/Unsqueeze_3\"](%/up4/Sub_3_output_0, %onnx::Unsqueeze_181), scope: __main__.UNet::/__main__.Up::up4\n",
239
- " %/up4/Concat_output_0 : Long(4, strides=[1], device=cpu) = onnx::Concat[axis=0, onnx_name=\"/up4/Concat\"](%/up4/Unsqueeze_output_0, %/up4/Unsqueeze_1_output_0, %/up4/Unsqueeze_2_output_0, %/up4/Unsqueeze_3_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
240
- " %onnx::Unsqueeze_184 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={0}]()\n",
241
- " %/up4/Unsqueeze_4_output_0 : Long(1, strides=[1], device=cpu) = onnx::Unsqueeze[onnx_name=\"/up4/Unsqueeze_4\"](%/up4/Cast_1_output_0, %onnx::Unsqueeze_184), scope: __main__.UNet::/__main__.Up::up4\n",
242
- " %onnx::Unsqueeze_186 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={0}]()\n",
243
- " %/up4/Unsqueeze_5_output_0 : Long(1, strides=[1], device=cpu) = onnx::Unsqueeze[onnx_name=\"/up4/Unsqueeze_5\"](%/up4/Sub_2_output_0, %onnx::Unsqueeze_186), scope: __main__.UNet::/__main__.Up::up4\n",
244
- " %onnx::Unsqueeze_188 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={0}]()\n",
245
- " %/up4/Unsqueeze_6_output_0 : Long(1, strides=[1], device=cpu) = onnx::Unsqueeze[onnx_name=\"/up4/Unsqueeze_6\"](%/up4/Cast_3_output_0, %onnx::Unsqueeze_188), scope: __main__.UNet::/__main__.Up::up4\n",
246
- " %onnx::Unsqueeze_190 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={0}]()\n",
247
- " %/up4/Unsqueeze_7_output_0 : Long(1, strides=[1], device=cpu) = onnx::Unsqueeze[onnx_name=\"/up4/Unsqueeze_7\"](%/up4/Sub_3_output_0, %onnx::Unsqueeze_190), scope: __main__.UNet::/__main__.Up::up4\n",
248
- " %/up4/Concat_1_output_0 : Long(4, strides=[1], device=cpu) = onnx::Concat[axis=0, onnx_name=\"/up4/Concat_1\"](%/up4/Unsqueeze_4_output_0, %/up4/Unsqueeze_5_output_0, %/up4/Unsqueeze_6_output_0, %/up4/Unsqueeze_7_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
249
- " %onnx::Pad_193 : NoneType = prim::Constant(), scope: __main__.UNet::/__main__.Up::up4\n",
250
- " %/up4/Constant_6_output_0 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={0}, onnx_name=\"/up4/Constant_6\"](), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
251
- " %/up4/Shape_4_output_0 : Long(1, strides=[1], device=cpu) = onnx::Shape[onnx_name=\"/up4/Shape_4\"](%/up4/Concat_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
252
- " %/up4/Gather_4_output_0 : Long(1, strides=[1], device=cpu) = onnx::Gather[axis=0, onnx_name=\"/up4/Gather_4\"](%/up4/Shape_4_output_0, %/up4/Constant_6_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
253
- " %/up4/Constant_7_output_0 : Long(requires_grad=0, device=cpu) = onnx::Constant[value={8}, onnx_name=\"/up4/Constant_7\"](), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
254
- " %/up4/Sub_4_output_0 : Long(1, strides=[1], device=cpu) = onnx::Sub[onnx_name=\"/up4/Sub_4\"](%/up4/Constant_7_output_0, %/up4/Gather_4_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
255
- " %/up4/Cast_4_output_0 : Long(4, strides=[1], device=cpu) = onnx::Cast[to=7, onnx_name=\"/up4/Cast_4\"](%/up4/Concat_1_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
256
- " %/up4/ConstantOfShape_output_0 : Long(4, strides=[1], device=cpu) = onnx::ConstantOfShape[value={0}, onnx_name=\"/up4/ConstantOfShape\"](%/up4/Sub_4_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
257
- " %/up4/Concat_2_output_0 : Long(8, strides=[1], device=cpu) = onnx::Concat[axis=0, onnx_name=\"/up4/Concat_2\"](%/up4/Cast_4_output_0, %/up4/ConstantOfShape_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
258
- " %/up4/Constant_8_output_0 : Long(2, strides=[1], device=cpu) = onnx::Constant[value=-1 2 [ CPULongType{2} ], onnx_name=\"/up4/Constant_8\"](), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
259
- " %/up4/Reshape_output_0 : Long(4, 2, strides=[2, 1], device=cpu) = onnx::Reshape[allowzero=0, onnx_name=\"/up4/Reshape\"](%/up4/Concat_2_output_0, %/up4/Constant_8_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
260
- " %/up4/Constant_9_output_0 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={0}, onnx_name=\"/up4/Constant_9\"](), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
261
- " %/up4/Constant_10_output_0 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={-1}, onnx_name=\"/up4/Constant_10\"](), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
262
- " %/up4/Constant_11_output_0 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={-9223372036854775807}, onnx_name=\"/up4/Constant_11\"](), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
263
- " %/up4/Constant_12_output_0 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={-1}, onnx_name=\"/up4/Constant_12\"](), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
264
- " %/up4/Slice_output_0 : Long(4, 2, strides=[2, 1], device=cpu) = onnx::Slice[onnx_name=\"/up4/Slice\"](%/up4/Reshape_output_0, %/up4/Constant_10_output_0, %/up4/Constant_11_output_0, %/up4/Constant_9_output_0, %/up4/Constant_12_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
265
- " %/up4/Transpose_output_0 : Long(2, 4, strides=[4, 1], device=cpu) = onnx::Transpose[perm=[1, 0], onnx_name=\"/up4/Transpose\"](%/up4/Slice_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
266
- " %/up4/Constant_13_output_0 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={-1}, onnx_name=\"/up4/Constant_13\"](), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
267
- " %/up4/Reshape_1_output_0 : Long(8, strides=[1], device=cpu) = onnx::Reshape[allowzero=0, onnx_name=\"/up4/Reshape_1\"](%/up4/Transpose_output_0, %/up4/Constant_13_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
268
- " %/up4/Cast_5_output_0 : Long(8, strides=[1], device=cpu) = onnx::Cast[to=7, onnx_name=\"/up4/Cast_5\"](%/up4/Reshape_1_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
269
- " %/up4/Pad_output_0 : Float(*, *, *, *, strides=[4194304, 65536, 256, 1], requires_grad=1, device=cpu) = onnx::Pad[mode=\"constant\", onnx_name=\"/up4/Pad\"](%/up4/up/ConvTranspose_output_0, %/up4/Cast_5_output_0, %onnx::Pad_193), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:39:0\n",
270
- " %/up4/Concat_3_output_0 : Float(*, *, 256, 256, strides=[8388608, 65536, 256, 1], requires_grad=1, device=cpu) = onnx::Concat[axis=1, onnx_name=\"/up4/Concat_3\"](%/inc/conv/conv.5/Relu_output_0, %/up4/Pad_output_0), scope: __main__.UNet::/__main__.Up::up4 # /tmp/ipykernel_19565/1651252862.py:40:0\n",
271
- " %/up4/conv/conv/conv.0/Conv_output_0 : Float(*, 64, 256, 256, strides=[4194304, 65536, 256, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/up4/conv/conv/conv.0/Conv\"](%/up4/Concat_3_output_0, %onnx::Conv_238, %onnx::Conv_239), scope: __main__.UNet::/__main__.Up::up4/__main__.DoubleConv::conv/torch.nn.modules.container.Sequential::conv/torch.nn.modules.conv.Conv2d::conv.0 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
272
- " %/up4/conv/conv/conv.2/Relu_output_0 : Float(*, 64, 256, 256, strides=[4194304, 65536, 256, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/up4/conv/conv/conv.2/Relu\"](%/up4/conv/conv/conv.0/Conv_output_0), scope: __main__.UNet::/__main__.Up::up4/__main__.DoubleConv::conv/torch.nn.modules.container.Sequential::conv/torch.nn.modules.activation.ReLU::conv.2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
273
- " %/up4/conv/conv/conv.3/Conv_output_0 : Float(*, 64, 256, 256, strides=[4194304, 65536, 256, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/up4/conv/conv/conv.3/Conv\"](%/up4/conv/conv/conv.2/Relu_output_0, %onnx::Conv_241, %onnx::Conv_242), scope: __main__.UNet::/__main__.Up::up4/__main__.DoubleConv::conv/torch.nn.modules.container.Sequential::conv/torch.nn.modules.conv.Conv2d::conv.3 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
274
- " %/up4/conv/conv/conv.5/Relu_output_0 : Float(*, 64, 256, 256, strides=[4194304, 65536, 256, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/up4/conv/conv/conv.5/Relu\"](%/up4/conv/conv/conv.3/Conv_output_0), scope: __main__.UNet::/__main__.Up::up4/__main__.DoubleConv::conv/torch.nn.modules.container.Sequential::conv/torch.nn.modules.activation.ReLU::conv.5 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
275
- " %/outc/conv/Conv_output_0 : Float(*, 1, 256, 256, strides=[65536, 65536, 256, 1], requires_grad=0, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[1, 1], pads=[0, 0, 0, 0], strides=[1, 1], onnx_name=\"/outc/conv/Conv\"](%/up4/conv/conv/conv.5/Relu_output_0, %outc.conv.weight, %outc.conv.bias), scope: __main__.UNet::/__main__.OutConv::outc/torch.nn.modules.conv.Conv2d::conv # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
276
- " %output : Float(*, 1, 256, 256, strides=[65536, 65536, 256, 1], requires_grad=1, device=cpu) = onnx::Sigmoid[onnx_name=\"/outc/sigmoid/Sigmoid\"](%/outc/conv/Conv_output_0), scope: __main__.UNet::/__main__.OutConv::outc/torch.nn.modules.activation.Sigmoid::sigmoid # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/activation.py:294:0\n",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
277
  " return (%output)\n",
278
  "\n"
279
  ]
280
- },
281
- {
282
- "name": "stderr",
283
- "output_type": "stream",
284
- "text": [
285
- "/home/gautham/.local/lib/python3.10/site-packages/torch/onnx/utils.py:687: UserWarning: The shape inference of prim::Constant type is missing, so it may result in wrong shape inference for the exported graph. Please consider adding it in symbolic function. (Triggered internally at ../torch/csrc/jit/passes/onnx/shape_type_inference.cpp:1884.)\n",
286
- " _C._jit_pass_onnx_graph_shape_type_inference(\n",
287
- "/home/gautham/.local/lib/python3.10/site-packages/torch/onnx/utils.py:1178: UserWarning: The shape inference of prim::Constant type is missing, so it may result in wrong shape inference for the exported graph. Please consider adding it in symbolic function. (Triggered internally at ../torch/csrc/jit/passes/onnx/shape_type_inference.cpp:1884.)\n",
288
- " _C._jit_pass_onnx_graph_shape_type_inference(\n"
289
- ]
290
  }
291
  ],
292
  "source": [
293
- "onnx_path = '../weights/model.onnx'\n",
294
  "\n",
295
  "torch.onnx.export(model,\n",
296
  " dummy_input,\n",
@@ -311,7 +352,7 @@
311
  },
312
  {
313
  "cell_type": "code",
314
- "execution_count": null,
315
  "metadata": {},
316
  "outputs": [],
317
  "source": [
@@ -330,7 +371,7 @@
330
  },
331
  {
332
  "cell_type": "code",
333
- "execution_count": null,
334
  "metadata": {},
335
  "outputs": [
336
  {
 
13
  "metadata": {},
14
  "outputs": [
15
  {
16
+ "name": "stdout",
17
  "output_type": "stream",
18
  "text": [
19
+ "True\n"
 
20
  ]
21
  }
22
  ],
23
  "source": [
24
  "import torch\n",
25
  "from torch import nn\n",
26
+ "from torch.nn import functional as F\n",
27
+ "\n",
28
+ "print(torch.cuda.is_available())"
29
  ]
30
  },
31
  {
 
41
  "metadata": {},
42
  "outputs": [],
43
  "source": [
44
+ "class BasicBlock(nn.Module):\n",
 
 
 
 
 
 
 
 
 
 
 
 
45
  "\n",
46
+ " def __init__(self, in_channels, out_channels, stride= 1):\n",
 
47
  " super().__init__()\n",
48
+ " self.conv1 = nn.Conv2d(in_channels, out_channels, 3, stride= stride, padding= 1)\n",
49
+ " self.conv2 = nn.Conv2d(out_channels, out_channels, 3, stride= 1, padding= 1)\n",
50
+ " self.bn1 = nn.BatchNorm2d(out_channels)\n",
51
+ " self.bn2 = nn.BatchNorm2d(out_channels)\n",
52
+ " self.relu = nn.ReLU(inplace= True)\n",
53
+ "\n",
54
+ " self.downsample = nn.Sequential()\n",
55
+ " \n",
56
+ " if stride != 1:\n",
57
+ " self.downsample = nn.Sequential(\n",
58
+ " nn.Conv2d(in_channels, out_channels, 1, stride),\n",
59
+ " nn.BatchNorm2d(out_channels))\n",
60
+ "\n",
61
  " def forward(self, x):\n",
62
+ " out = self.conv1(x)\n",
63
+ " out = self.bn1(out)\n",
64
+ " out = self.relu(out)\n",
65
  "\n",
66
+ " out = self.conv2(out)\n",
67
+ " out = self.bn2(out)\n",
 
 
 
 
 
 
 
 
68
  "\n",
69
+ " out += self.downsample(x)\n",
 
 
 
 
 
 
70
  "\n",
71
+ " out = self.relu(out)\n",
 
 
 
 
72
  "\n",
73
+ " return out\n",
 
74
  "\n",
75
+ "class ResNet34(nn.Module):\n",
76
+ " def __init__(self, num_classes) -> None:\n",
77
  " super().__init__()\n",
78
+ "\n",
79
+ " self.conv1 = nn.Sequential(nn.Conv2d(3, 64, 7, stride= 2, padding= 3),\n",
80
+ " nn.BatchNorm2d(64), nn.MaxPool2d(3, stride= 2, padding= 1), nn.ReLU(inplace= True))\n",
81
+ "\n",
82
+ " self.layer0 = self._make_layer(64, 64, 3, 1)\n",
83
+ " self.layer1 = self._make_layer(64, 128, 4, 2)\n",
84
+ " self.layer2 = self._make_layer(128, 256, 6, 2)\n",
85
+ " self.layer3 = self._make_layer(256, 512, 3, 2)\n",
86
+ "\n",
87
+ " self.avg_pool = nn.AvgPool2d(7)\n",
88
+ " self.fc = nn.Linear(512, num_classes)\n",
89
+ "\n",
90
+ " def _make_layer(self, in_channels, out_channels, num_blocks, stride):\n",
91
+ " \n",
92
+ " layers = []\n",
93
+ " layers.append(BasicBlock(in_channels, out_channels, stride))\n",
94
+ "\n",
95
+ " for i in range(num_blocks - 1):\n",
96
+ " layers.append(BasicBlock(out_channels, out_channels, 1))\n",
97
+ "\n",
98
+ " return nn.Sequential(*layers)\n",
99
  "\n",
100
  " def forward(self, x):\n",
101
+ " out = self.conv1(x)\n",
102
+ " \n",
103
+ " out = self.layer0(out)\n",
104
+ " out = self.layer1(out)\n",
105
+ " out = self.layer2(out)\n",
106
+ " out = self.layer3(out)\n",
107
+ "\n",
108
+ " out = self.avg_pool(out)\n",
109
+ " out = out.view(out.size(0), -1)\n",
110
+ " out = self.fc(out)\n",
111
+ "\n",
112
+ " out = F.log_softmax(out, dim= 1)\n",
113
+ " return out"
114
  ]
115
  },
116
  {
 
124
  "cell_type": "code",
125
  "execution_count": 3,
126
  "metadata": {},
127
+ "outputs": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
128
  "source": [
129
+ "model = ResNet34(450)\n",
130
+ "model.load_state_dict(torch.load('../model/birds_resnet34_model.pth'))\n",
131
  "\n",
132
+ "dummy_input = torch.randn(1, 3, 224, 224)\n",
133
  "\n",
134
  "model.eval()\n",
135
  "torch_out = model(dummy_input)"
 
144
  },
145
  {
146
  "cell_type": "code",
147
+ "execution_count": 4,
148
  "metadata": {},
149
  "outputs": [
150
  {
151
  "name": "stdout",
152
  "output_type": "stream",
153
  "text": [
154
+ "Exported graph: graph(%input : Float(*, 3, 224, 224, strides=[150528, 50176, 224, 1], requires_grad=0, device=cpu),\n",
155
+ " %fc.weight : Float(450, 512, strides=[512, 1], requires_grad=1, device=cpu),\n",
156
+ " %fc.bias : Float(450, strides=[1], requires_grad=1, device=cpu),\n",
157
+ " %onnx::Conv_393 : Float(64, 3, 7, 7, strides=[147, 49, 7, 1], requires_grad=0, device=cpu),\n",
158
+ " %onnx::Conv_394 : Float(64, strides=[1], requires_grad=0, device=cpu),\n",
159
+ " %onnx::Conv_396 : Float(64, 64, 3, 3, strides=[576, 9, 3, 1], requires_grad=0, device=cpu),\n",
160
+ " %onnx::Conv_397 : Float(64, strides=[1], requires_grad=0, device=cpu),\n",
161
+ " %onnx::Conv_399 : Float(64, 64, 3, 3, strides=[576, 9, 3, 1], requires_grad=0, device=cpu),\n",
162
+ " %onnx::Conv_400 : Float(64, strides=[1], requires_grad=0, device=cpu),\n",
163
+ " %onnx::Conv_402 : Float(64, 64, 3, 3, strides=[576, 9, 3, 1], requires_grad=0, device=cpu),\n",
164
+ " %onnx::Conv_403 : Float(64, strides=[1], requires_grad=0, device=cpu),\n",
165
+ " %onnx::Conv_405 : Float(64, 64, 3, 3, strides=[576, 9, 3, 1], requires_grad=0, device=cpu),\n",
166
+ " %onnx::Conv_406 : Float(64, strides=[1], requires_grad=0, device=cpu),\n",
167
+ " %onnx::Conv_408 : Float(64, 64, 3, 3, strides=[576, 9, 3, 1], requires_grad=0, device=cpu),\n",
168
+ " %onnx::Conv_409 : Float(64, strides=[1], requires_grad=0, device=cpu),\n",
169
+ " %onnx::Conv_411 : Float(64, 64, 3, 3, strides=[576, 9, 3, 1], requires_grad=0, device=cpu),\n",
170
+ " %onnx::Conv_412 : Float(64, strides=[1], requires_grad=0, device=cpu),\n",
171
+ " %onnx::Conv_414 : Float(128, 64, 3, 3, strides=[576, 9, 3, 1], requires_grad=0, device=cpu),\n",
172
+ " %onnx::Conv_415 : Float(128, strides=[1], requires_grad=0, device=cpu),\n",
173
+ " %onnx::Conv_417 : Float(128, 128, 3, 3, strides=[1152, 9, 3, 1], requires_grad=0, device=cpu),\n",
174
+ " %onnx::Conv_418 : Float(128, strides=[1], requires_grad=0, device=cpu),\n",
175
+ " %onnx::Conv_420 : Float(128, 64, 1, 1, strides=[64, 1, 1, 1], requires_grad=0, device=cpu),\n",
176
+ " %onnx::Conv_421 : Float(128, strides=[1], requires_grad=0, device=cpu),\n",
177
+ " %onnx::Conv_423 : Float(128, 128, 3, 3, strides=[1152, 9, 3, 1], requires_grad=0, device=cpu),\n",
178
+ " %onnx::Conv_424 : Float(128, strides=[1], requires_grad=0, device=cpu),\n",
179
+ " %onnx::Conv_426 : Float(128, 128, 3, 3, strides=[1152, 9, 3, 1], requires_grad=0, device=cpu),\n",
180
+ " %onnx::Conv_427 : Float(128, strides=[1], requires_grad=0, device=cpu),\n",
181
+ " %onnx::Conv_429 : Float(128, 128, 3, 3, strides=[1152, 9, 3, 1], requires_grad=0, device=cpu),\n",
182
+ " %onnx::Conv_430 : Float(128, strides=[1], requires_grad=0, device=cpu),\n",
183
+ " %onnx::Conv_432 : Float(128, 128, 3, 3, strides=[1152, 9, 3, 1], requires_grad=0, device=cpu),\n",
184
+ " %onnx::Conv_433 : Float(128, strides=[1], requires_grad=0, device=cpu),\n",
185
+ " %onnx::Conv_435 : Float(128, 128, 3, 3, strides=[1152, 9, 3, 1], requires_grad=0, device=cpu),\n",
186
+ " %onnx::Conv_436 : Float(128, strides=[1], requires_grad=0, device=cpu),\n",
187
+ " %onnx::Conv_438 : Float(128, 128, 3, 3, strides=[1152, 9, 3, 1], requires_grad=0, device=cpu),\n",
188
+ " %onnx::Conv_439 : Float(128, strides=[1], requires_grad=0, device=cpu),\n",
189
+ " %onnx::Conv_441 : Float(256, 128, 3, 3, strides=[1152, 9, 3, 1], requires_grad=0, device=cpu),\n",
190
+ " %onnx::Conv_442 : Float(256, strides=[1], requires_grad=0, device=cpu),\n",
191
+ " %onnx::Conv_444 : Float(256, 256, 3, 3, strides=[2304, 9, 3, 1], requires_grad=0, device=cpu),\n",
192
+ " %onnx::Conv_445 : Float(256, strides=[1], requires_grad=0, device=cpu),\n",
193
+ " %onnx::Conv_447 : Float(256, 128, 1, 1, strides=[128, 1, 1, 1], requires_grad=0, device=cpu),\n",
194
+ " %onnx::Conv_448 : Float(256, strides=[1], requires_grad=0, device=cpu),\n",
195
+ " %onnx::Conv_450 : Float(256, 256, 3, 3, strides=[2304, 9, 3, 1], requires_grad=0, device=cpu),\n",
196
+ " %onnx::Conv_451 : Float(256, strides=[1], requires_grad=0, device=cpu),\n",
197
+ " %onnx::Conv_453 : Float(256, 256, 3, 3, strides=[2304, 9, 3, 1], requires_grad=0, device=cpu),\n",
198
+ " %onnx::Conv_454 : Float(256, strides=[1], requires_grad=0, device=cpu),\n",
199
+ " %onnx::Conv_456 : Float(256, 256, 3, 3, strides=[2304, 9, 3, 1], requires_grad=0, device=cpu),\n",
200
+ " %onnx::Conv_457 : Float(256, strides=[1], requires_grad=0, device=cpu),\n",
201
+ " %onnx::Conv_459 : Float(256, 256, 3, 3, strides=[2304, 9, 3, 1], requires_grad=0, device=cpu),\n",
202
+ " %onnx::Conv_460 : Float(256, strides=[1], requires_grad=0, device=cpu),\n",
203
+ " %onnx::Conv_462 : Float(256, 256, 3, 3, strides=[2304, 9, 3, 1], requires_grad=0, device=cpu),\n",
204
+ " %onnx::Conv_463 : Float(256, strides=[1], requires_grad=0, device=cpu),\n",
205
+ " %onnx::Conv_465 : Float(256, 256, 3, 3, strides=[2304, 9, 3, 1], requires_grad=0, device=cpu),\n",
206
+ " %onnx::Conv_466 : Float(256, strides=[1], requires_grad=0, device=cpu),\n",
207
+ " %onnx::Conv_468 : Float(256, 256, 3, 3, strides=[2304, 9, 3, 1], requires_grad=0, device=cpu),\n",
208
+ " %onnx::Conv_469 : Float(256, strides=[1], requires_grad=0, device=cpu),\n",
209
+ " %onnx::Conv_471 : Float(256, 256, 3, 3, strides=[2304, 9, 3, 1], requires_grad=0, device=cpu),\n",
210
+ " %onnx::Conv_472 : Float(256, strides=[1], requires_grad=0, device=cpu),\n",
211
+ " %onnx::Conv_474 : Float(256, 256, 3, 3, strides=[2304, 9, 3, 1], requires_grad=0, device=cpu),\n",
212
+ " %onnx::Conv_475 : Float(256, strides=[1], requires_grad=0, device=cpu),\n",
213
+ " %onnx::Conv_477 : Float(256, 256, 3, 3, strides=[2304, 9, 3, 1], requires_grad=0, device=cpu),\n",
214
+ " %onnx::Conv_478 : Float(256, strides=[1], requires_grad=0, device=cpu),\n",
215
+ " %onnx::Conv_480 : Float(512, 256, 3, 3, strides=[2304, 9, 3, 1], requires_grad=0, device=cpu),\n",
216
+ " %onnx::Conv_481 : Float(512, strides=[1], requires_grad=0, device=cpu),\n",
217
+ " %onnx::Conv_483 : Float(512, 512, 3, 3, strides=[4608, 9, 3, 1], requires_grad=0, device=cpu),\n",
218
+ " %onnx::Conv_484 : Float(512, strides=[1], requires_grad=0, device=cpu),\n",
219
+ " %onnx::Conv_486 : Float(512, 256, 1, 1, strides=[256, 1, 1, 1], requires_grad=0, device=cpu),\n",
220
+ " %onnx::Conv_487 : Float(512, strides=[1], requires_grad=0, device=cpu),\n",
221
+ " %onnx::Conv_489 : Float(512, 512, 3, 3, strides=[4608, 9, 3, 1], requires_grad=0, device=cpu),\n",
222
+ " %onnx::Conv_490 : Float(512, strides=[1], requires_grad=0, device=cpu),\n",
223
+ " %onnx::Conv_492 : Float(512, 512, 3, 3, strides=[4608, 9, 3, 1], requires_grad=0, device=cpu),\n",
224
+ " %onnx::Conv_493 : Float(512, strides=[1], requires_grad=0, device=cpu),\n",
225
+ " %onnx::Conv_495 : Float(512, 512, 3, 3, strides=[4608, 9, 3, 1], requires_grad=0, device=cpu),\n",
226
+ " %onnx::Conv_496 : Float(512, strides=[1], requires_grad=0, device=cpu),\n",
227
+ " %onnx::Conv_498 : Float(512, 512, 3, 3, strides=[4608, 9, 3, 1], requires_grad=0, device=cpu),\n",
228
+ " %onnx::Conv_499 : Float(512, strides=[1], requires_grad=0, device=cpu)):\n",
229
+ " %/conv1/conv1.0/Conv_output_0 : Float(*, 64, 112, 112, strides=[802816, 12544, 112, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[7, 7], pads=[3, 3, 3, 3], strides=[2, 2], onnx_name=\"/conv1/conv1.0/Conv\"](%input, %onnx::Conv_393, %onnx::Conv_394), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::conv1/torch.nn.modules.conv.Conv2d::conv1.0 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
230
+ " %/conv1/conv1.2/MaxPool_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::MaxPool[ceil_mode=0, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[2, 2], onnx_name=\"/conv1/conv1.2/MaxPool\"](%/conv1/conv1.0/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::conv1/torch.nn.modules.pooling.MaxPool2d::conv1.2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:780:0\n",
231
+ " %/conv1/conv1.3/Relu_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/conv1/conv1.3/Relu\"](%/conv1/conv1.2/MaxPool_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::conv1/torch.nn.modules.activation.ReLU::conv1.3 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
232
+ " %/layer0/layer0.0/conv1/Conv_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer0/layer0.0/conv1/Conv\"](%/conv1/conv1.3/Relu_output_0, %onnx::Conv_396, %onnx::Conv_397), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.0/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
233
+ " %/layer0/layer0.0/relu/Relu_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer0/layer0.0/relu/Relu\"](%/layer0/layer0.0/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.0/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
234
+ " %/layer0/layer0.0/conv2/Conv_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer0/layer0.0/conv2/Conv\"](%/layer0/layer0.0/relu/Relu_output_0, %onnx::Conv_399, %onnx::Conv_400), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.0/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
235
+ " %/layer0/layer0.0/Add_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer0/layer0.0/Add\"](%/layer0/layer0.0/conv2/Conv_output_0, %/conv1/conv1.3/Relu_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.0 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
236
+ " %/layer0/layer0.0/relu_1/Relu_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer0/layer0.0/relu_1/Relu\"](%/layer0/layer0.0/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.0/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
237
+ " %/layer0/layer0.1/conv1/Conv_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer0/layer0.1/conv1/Conv\"](%/layer0/layer0.0/relu_1/Relu_output_0, %onnx::Conv_402, %onnx::Conv_403), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.1/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
238
+ " %/layer0/layer0.1/relu/Relu_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer0/layer0.1/relu/Relu\"](%/layer0/layer0.1/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.1/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
239
+ " %/layer0/layer0.1/conv2/Conv_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer0/layer0.1/conv2/Conv\"](%/layer0/layer0.1/relu/Relu_output_0, %onnx::Conv_405, %onnx::Conv_406), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.1/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
240
+ " %/layer0/layer0.1/Add_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer0/layer0.1/Add\"](%/layer0/layer0.1/conv2/Conv_output_0, %/layer0/layer0.0/relu_1/Relu_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.1 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
241
+ " %/layer0/layer0.1/relu_1/Relu_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer0/layer0.1/relu_1/Relu\"](%/layer0/layer0.1/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.1/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
242
+ " %/layer0/layer0.2/conv1/Conv_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer0/layer0.2/conv1/Conv\"](%/layer0/layer0.1/relu_1/Relu_output_0, %onnx::Conv_408, %onnx::Conv_409), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.2/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
243
+ " %/layer0/layer0.2/relu/Relu_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer0/layer0.2/relu/Relu\"](%/layer0/layer0.2/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.2/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
244
+ " %/layer0/layer0.2/conv2/Conv_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer0/layer0.2/conv2/Conv\"](%/layer0/layer0.2/relu/Relu_output_0, %onnx::Conv_411, %onnx::Conv_412), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.2/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
245
+ " %/layer0/layer0.2/Add_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer0/layer0.2/Add\"](%/layer0/layer0.2/conv2/Conv_output_0, %/layer0/layer0.1/relu_1/Relu_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.2 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
246
+ " %/layer0/layer0.2/relu_1/Relu_output_0 : Float(*, 64, 56, 56, strides=[200704, 3136, 56, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer0/layer0.2/relu_1/Relu\"](%/layer0/layer0.2/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer0/__main__.BasicBlock::layer0.2/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
247
+ " %/layer1/layer1.0/conv1/Conv_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[2, 2], onnx_name=\"/layer1/layer1.0/conv1/Conv\"](%/layer0/layer0.2/relu_1/Relu_output_0, %onnx::Conv_414, %onnx::Conv_415), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.0/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
248
+ " %/layer1/layer1.0/relu/Relu_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer1/layer1.0/relu/Relu\"](%/layer1/layer1.0/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.0/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
249
+ " %/layer1/layer1.0/conv2/Conv_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer1/layer1.0/conv2/Conv\"](%/layer1/layer1.0/relu/Relu_output_0, %onnx::Conv_417, %onnx::Conv_418), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.0/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
250
+ " %/layer1/layer1.0/downsample/downsample.0/Conv_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[1, 1], pads=[0, 0, 0, 0], strides=[2, 2], onnx_name=\"/layer1/layer1.0/downsample/downsample.0/Conv\"](%/layer0/layer0.2/relu_1/Relu_output_0, %onnx::Conv_420, %onnx::Conv_421), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.0/torch.nn.modules.container.Sequential::downsample/torch.nn.modules.conv.Conv2d::downsample.0 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
251
+ " %/layer1/layer1.0/Add_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer1/layer1.0/Add\"](%/layer1/layer1.0/conv2/Conv_output_0, %/layer1/layer1.0/downsample/downsample.0/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.0 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
252
+ " %/layer1/layer1.0/relu_1/Relu_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer1/layer1.0/relu_1/Relu\"](%/layer1/layer1.0/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.0/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
253
+ " %/layer1/layer1.1/conv1/Conv_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer1/layer1.1/conv1/Conv\"](%/layer1/layer1.0/relu_1/Relu_output_0, %onnx::Conv_423, %onnx::Conv_424), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.1/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
254
+ " %/layer1/layer1.1/relu/Relu_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer1/layer1.1/relu/Relu\"](%/layer1/layer1.1/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.1/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
255
+ " %/layer1/layer1.1/conv2/Conv_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer1/layer1.1/conv2/Conv\"](%/layer1/layer1.1/relu/Relu_output_0, %onnx::Conv_426, %onnx::Conv_427), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.1/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
256
+ " %/layer1/layer1.1/Add_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer1/layer1.1/Add\"](%/layer1/layer1.1/conv2/Conv_output_0, %/layer1/layer1.0/relu_1/Relu_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.1 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
257
+ " %/layer1/layer1.1/relu_1/Relu_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer1/layer1.1/relu_1/Relu\"](%/layer1/layer1.1/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.1/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
258
+ " %/layer1/layer1.2/conv1/Conv_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer1/layer1.2/conv1/Conv\"](%/layer1/layer1.1/relu_1/Relu_output_0, %onnx::Conv_429, %onnx::Conv_430), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.2/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
259
+ " %/layer1/layer1.2/relu/Relu_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer1/layer1.2/relu/Relu\"](%/layer1/layer1.2/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.2/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
260
+ " %/layer1/layer1.2/conv2/Conv_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer1/layer1.2/conv2/Conv\"](%/layer1/layer1.2/relu/Relu_output_0, %onnx::Conv_432, %onnx::Conv_433), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.2/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
261
+ " %/layer1/layer1.2/Add_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer1/layer1.2/Add\"](%/layer1/layer1.2/conv2/Conv_output_0, %/layer1/layer1.1/relu_1/Relu_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.2 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
262
+ " %/layer1/layer1.2/relu_1/Relu_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer1/layer1.2/relu_1/Relu\"](%/layer1/layer1.2/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.2/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
263
+ " %/layer1/layer1.3/conv1/Conv_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer1/layer1.3/conv1/Conv\"](%/layer1/layer1.2/relu_1/Relu_output_0, %onnx::Conv_435, %onnx::Conv_436), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.3/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
264
+ " %/layer1/layer1.3/relu/Relu_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer1/layer1.3/relu/Relu\"](%/layer1/layer1.3/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.3/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
265
+ " %/layer1/layer1.3/conv2/Conv_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer1/layer1.3/conv2/Conv\"](%/layer1/layer1.3/relu/Relu_output_0, %onnx::Conv_438, %onnx::Conv_439), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.3/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
266
+ " %/layer1/layer1.3/Add_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer1/layer1.3/Add\"](%/layer1/layer1.3/conv2/Conv_output_0, %/layer1/layer1.2/relu_1/Relu_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.3 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
267
+ " %/layer1/layer1.3/relu_1/Relu_output_0 : Float(*, 128, 28, 28, strides=[100352, 784, 28, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer1/layer1.3/relu_1/Relu\"](%/layer1/layer1.3/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer1/__main__.BasicBlock::layer1.3/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
268
+ " %/layer2/layer2.0/conv1/Conv_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[2, 2], onnx_name=\"/layer2/layer2.0/conv1/Conv\"](%/layer1/layer1.3/relu_1/Relu_output_0, %onnx::Conv_441, %onnx::Conv_442), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.0/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
269
+ " %/layer2/layer2.0/relu/Relu_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer2/layer2.0/relu/Relu\"](%/layer2/layer2.0/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.0/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
270
+ " %/layer2/layer2.0/conv2/Conv_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer2/layer2.0/conv2/Conv\"](%/layer2/layer2.0/relu/Relu_output_0, %onnx::Conv_444, %onnx::Conv_445), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.0/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
271
+ " %/layer2/layer2.0/downsample/downsample.0/Conv_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[1, 1], pads=[0, 0, 0, 0], strides=[2, 2], onnx_name=\"/layer2/layer2.0/downsample/downsample.0/Conv\"](%/layer1/layer1.3/relu_1/Relu_output_0, %onnx::Conv_447, %onnx::Conv_448), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.0/torch.nn.modules.container.Sequential::downsample/torch.nn.modules.conv.Conv2d::downsample.0 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
272
+ " %/layer2/layer2.0/Add_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer2/layer2.0/Add\"](%/layer2/layer2.0/conv2/Conv_output_0, %/layer2/layer2.0/downsample/downsample.0/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.0 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
273
+ " %/layer2/layer2.0/relu_1/Relu_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer2/layer2.0/relu_1/Relu\"](%/layer2/layer2.0/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.0/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
274
+ " %/layer2/layer2.1/conv1/Conv_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer2/layer2.1/conv1/Conv\"](%/layer2/layer2.0/relu_1/Relu_output_0, %onnx::Conv_450, %onnx::Conv_451), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.1/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
275
+ " %/layer2/layer2.1/relu/Relu_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer2/layer2.1/relu/Relu\"](%/layer2/layer2.1/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.1/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
276
+ " %/layer2/layer2.1/conv2/Conv_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer2/layer2.1/conv2/Conv\"](%/layer2/layer2.1/relu/Relu_output_0, %onnx::Conv_453, %onnx::Conv_454), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.1/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
277
+ " %/layer2/layer2.1/Add_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer2/layer2.1/Add\"](%/layer2/layer2.1/conv2/Conv_output_0, %/layer2/layer2.0/relu_1/Relu_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.1 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
278
+ " %/layer2/layer2.1/relu_1/Relu_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer2/layer2.1/relu_1/Relu\"](%/layer2/layer2.1/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.1/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
279
+ " %/layer2/layer2.2/conv1/Conv_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer2/layer2.2/conv1/Conv\"](%/layer2/layer2.1/relu_1/Relu_output_0, %onnx::Conv_456, %onnx::Conv_457), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.2/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
280
+ " %/layer2/layer2.2/relu/Relu_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer2/layer2.2/relu/Relu\"](%/layer2/layer2.2/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.2/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
281
+ " %/layer2/layer2.2/conv2/Conv_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer2/layer2.2/conv2/Conv\"](%/layer2/layer2.2/relu/Relu_output_0, %onnx::Conv_459, %onnx::Conv_460), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.2/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
282
+ " %/layer2/layer2.2/Add_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer2/layer2.2/Add\"](%/layer2/layer2.2/conv2/Conv_output_0, %/layer2/layer2.1/relu_1/Relu_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.2 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
283
+ " %/layer2/layer2.2/relu_1/Relu_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer2/layer2.2/relu_1/Relu\"](%/layer2/layer2.2/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.2/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
284
+ " %/layer2/layer2.3/conv1/Conv_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer2/layer2.3/conv1/Conv\"](%/layer2/layer2.2/relu_1/Relu_output_0, %onnx::Conv_462, %onnx::Conv_463), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.3/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
285
+ " %/layer2/layer2.3/relu/Relu_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer2/layer2.3/relu/Relu\"](%/layer2/layer2.3/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.3/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
286
+ " %/layer2/layer2.3/conv2/Conv_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer2/layer2.3/conv2/Conv\"](%/layer2/layer2.3/relu/Relu_output_0, %onnx::Conv_465, %onnx::Conv_466), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.3/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
287
+ " %/layer2/layer2.3/Add_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer2/layer2.3/Add\"](%/layer2/layer2.3/conv2/Conv_output_0, %/layer2/layer2.2/relu_1/Relu_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.3 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
288
+ " %/layer2/layer2.3/relu_1/Relu_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer2/layer2.3/relu_1/Relu\"](%/layer2/layer2.3/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.3/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
289
+ " %/layer2/layer2.4/conv1/Conv_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer2/layer2.4/conv1/Conv\"](%/layer2/layer2.3/relu_1/Relu_output_0, %onnx::Conv_468, %onnx::Conv_469), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.4/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
290
+ " %/layer2/layer2.4/relu/Relu_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer2/layer2.4/relu/Relu\"](%/layer2/layer2.4/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.4/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
291
+ " %/layer2/layer2.4/conv2/Conv_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer2/layer2.4/conv2/Conv\"](%/layer2/layer2.4/relu/Relu_output_0, %onnx::Conv_471, %onnx::Conv_472), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.4/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
292
+ " %/layer2/layer2.4/Add_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer2/layer2.4/Add\"](%/layer2/layer2.4/conv2/Conv_output_0, %/layer2/layer2.3/relu_1/Relu_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.4 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
293
+ " %/layer2/layer2.4/relu_1/Relu_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer2/layer2.4/relu_1/Relu\"](%/layer2/layer2.4/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.4/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
294
+ " %/layer2/layer2.5/conv1/Conv_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer2/layer2.5/conv1/Conv\"](%/layer2/layer2.4/relu_1/Relu_output_0, %onnx::Conv_474, %onnx::Conv_475), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.5/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
295
+ " %/layer2/layer2.5/relu/Relu_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer2/layer2.5/relu/Relu\"](%/layer2/layer2.5/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.5/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
296
+ " %/layer2/layer2.5/conv2/Conv_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer2/layer2.5/conv2/Conv\"](%/layer2/layer2.5/relu/Relu_output_0, %onnx::Conv_477, %onnx::Conv_478), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.5/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
297
+ " %/layer2/layer2.5/Add_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer2/layer2.5/Add\"](%/layer2/layer2.5/conv2/Conv_output_0, %/layer2/layer2.4/relu_1/Relu_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.5 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
298
+ " %/layer2/layer2.5/relu_1/Relu_output_0 : Float(*, 256, 14, 14, strides=[50176, 196, 14, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer2/layer2.5/relu_1/Relu\"](%/layer2/layer2.5/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer2/__main__.BasicBlock::layer2.5/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
299
+ " %/layer3/layer3.0/conv1/Conv_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[2, 2], onnx_name=\"/layer3/layer3.0/conv1/Conv\"](%/layer2/layer2.5/relu_1/Relu_output_0, %onnx::Conv_480, %onnx::Conv_481), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.0/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
300
+ " %/layer3/layer3.0/relu/Relu_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer3/layer3.0/relu/Relu\"](%/layer3/layer3.0/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.0/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
301
+ " %/layer3/layer3.0/conv2/Conv_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer3/layer3.0/conv2/Conv\"](%/layer3/layer3.0/relu/Relu_output_0, %onnx::Conv_483, %onnx::Conv_484), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.0/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
302
+ " %/layer3/layer3.0/downsample/downsample.0/Conv_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[1, 1], pads=[0, 0, 0, 0], strides=[2, 2], onnx_name=\"/layer3/layer3.0/downsample/downsample.0/Conv\"](%/layer2/layer2.5/relu_1/Relu_output_0, %onnx::Conv_486, %onnx::Conv_487), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.0/torch.nn.modules.container.Sequential::downsample/torch.nn.modules.conv.Conv2d::downsample.0 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
303
+ " %/layer3/layer3.0/Add_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer3/layer3.0/Add\"](%/layer3/layer3.0/conv2/Conv_output_0, %/layer3/layer3.0/downsample/downsample.0/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.0 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
304
+ " %/layer3/layer3.0/relu_1/Relu_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer3/layer3.0/relu_1/Relu\"](%/layer3/layer3.0/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.0/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
305
+ " %/layer3/layer3.1/conv1/Conv_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer3/layer3.1/conv1/Conv\"](%/layer3/layer3.0/relu_1/Relu_output_0, %onnx::Conv_489, %onnx::Conv_490), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.1/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
306
+ " %/layer3/layer3.1/relu/Relu_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer3/layer3.1/relu/Relu\"](%/layer3/layer3.1/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.1/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
307
+ " %/layer3/layer3.1/conv2/Conv_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer3/layer3.1/conv2/Conv\"](%/layer3/layer3.1/relu/Relu_output_0, %onnx::Conv_492, %onnx::Conv_493), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.1/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
308
+ " %/layer3/layer3.1/Add_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer3/layer3.1/Add\"](%/layer3/layer3.1/conv2/Conv_output_0, %/layer3/layer3.0/relu_1/Relu_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.1 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
309
+ " %/layer3/layer3.1/relu_1/Relu_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer3/layer3.1/relu_1/Relu\"](%/layer3/layer3.1/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.1/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
310
+ " %/layer3/layer3.2/conv1/Conv_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer3/layer3.2/conv1/Conv\"](%/layer3/layer3.1/relu_1/Relu_output_0, %onnx::Conv_495, %onnx::Conv_496), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.2/torch.nn.modules.conv.Conv2d::conv1 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
311
+ " %/layer3/layer3.2/relu/Relu_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer3/layer3.2/relu/Relu\"](%/layer3/layer3.2/conv1/Conv_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.2/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
312
+ " %/layer3/layer3.2/conv2/Conv_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Conv[dilations=[1, 1], group=1, kernel_shape=[3, 3], pads=[1, 1, 1, 1], strides=[1, 1], onnx_name=\"/layer3/layer3.2/conv2/Conv\"](%/layer3/layer3.2/relu/Relu_output_0, %onnx::Conv_498, %onnx::Conv_499), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.2/torch.nn.modules.conv.Conv2d::conv2 # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:458:0\n",
313
+ " %/layer3/layer3.2/Add_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Add[onnx_name=\"/layer3/layer3.2/Add\"](%/layer3/layer3.2/conv2/Conv_output_0, %/layer3/layer3.1/relu_1/Relu_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.2 # /tmp/ipykernel_3991/1263192908.py:23:0\n",
314
+ " %/layer3/layer3.2/relu_1/Relu_output_0 : Float(*, 512, 7, 7, strides=[25088, 49, 7, 1], requires_grad=1, device=cpu) = onnx::Relu[onnx_name=\"/layer3/layer3.2/relu_1/Relu\"](%/layer3/layer3.2/Add_output_0), scope: __main__.ResNet34::/torch.nn.modules.container.Sequential::layer3/__main__.BasicBlock::layer3.2/torch.nn.modules.activation.ReLU::relu # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1453:0\n",
315
+ " %/avg_pool/Constant_output_0 : Long(8, strides=[1], device=cpu) = onnx::Constant[value= 0 0 0 0 0 0 0 0 [ CPULongType{8} ], onnx_name=\"/avg_pool/Constant\"](), scope: __main__.ResNet34::/torch.nn.modules.pooling.AvgPool2d::avg_pool # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/pooling.py:628:0\n",
316
+ " %/avg_pool/Pad_output_0 : Float(*, 512, 7, 7, device=cpu) = onnx::Pad[mode=\"constant\", onnx_name=\"/avg_pool/Pad\"](%/layer3/layer3.2/relu_1/Relu_output_0, %/avg_pool/Constant_output_0), scope: __main__.ResNet34::/torch.nn.modules.pooling.AvgPool2d::avg_pool # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/pooling.py:628:0\n",
317
+ " %/avg_pool/AveragePool_output_0 : Float(*, 512, 1, 1, strides=[512, 1, 1, 1], requires_grad=1, device=cpu) = onnx::AveragePool[ceil_mode=0, kernel_shape=[7, 7], pads=[0, 0, 0, 0], strides=[7, 7], onnx_name=\"/avg_pool/AveragePool\"](%/avg_pool/Pad_output_0), scope: __main__.ResNet34::/torch.nn.modules.pooling.AvgPool2d::avg_pool # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/pooling.py:628:0\n",
318
+ " %/Shape_output_0 : Long(4, strides=[1], device=cpu) = onnx::Shape[onnx_name=\"/Shape\"](%/avg_pool/AveragePool_output_0), scope: __main__.ResNet34:: # /tmp/ipykernel_3991/1263192908.py:62:0\n",
319
+ " %/Constant_output_0 : Long(device=cpu) = onnx::Constant[value={0}, onnx_name=\"/Constant\"](), scope: __main__.ResNet34:: # /tmp/ipykernel_3991/1263192908.py:62:0\n",
320
+ " %/Gather_output_0 : Long(device=cpu) = onnx::Gather[axis=0, onnx_name=\"/Gather\"](%/Shape_output_0, %/Constant_output_0), scope: __main__.ResNet34:: # /tmp/ipykernel_3991/1263192908.py:62:0\n",
321
+ " %onnx::Unsqueeze_384 : Long(1, strides=[1], device=cpu) = onnx::Constant[value={0}]()\n",
322
+ " %/Unsqueeze_output_0 : Long(1, strides=[1], device=cpu) = onnx::Unsqueeze[onnx_name=\"/Unsqueeze\"](%/Gather_output_0, %onnx::Unsqueeze_384), scope: __main__.ResNet34::\n",
323
+ " %/Constant_1_output_0 : Long(1, strides=[1], requires_grad=0, device=cpu) = onnx::Constant[value={-1}, onnx_name=\"/Constant_1\"](), scope: __main__.ResNet34::\n",
324
+ " %/Concat_output_0 : Long(2, strides=[1], device=cpu) = onnx::Concat[axis=0, onnx_name=\"/Concat\"](%/Unsqueeze_output_0, %/Constant_1_output_0), scope: __main__.ResNet34:: # /tmp/ipykernel_3991/1263192908.py:62:0\n",
325
+ " %/Reshape_output_0 : Float(*, 512, strides=[512, 1], requires_grad=1, device=cpu) = onnx::Reshape[allowzero=0, onnx_name=\"/Reshape\"](%/avg_pool/AveragePool_output_0, %/Concat_output_0), scope: __main__.ResNet34:: # /tmp/ipykernel_3991/1263192908.py:62:0\n",
326
+ " %/fc/Gemm_output_0 : Float(*, 450, strides=[450, 1], requires_grad=1, device=cpu) = onnx::Gemm[alpha=1., beta=1., transB=1, onnx_name=\"/fc/Gemm\"](%/Reshape_output_0, %fc.weight, %fc.bias), scope: __main__.ResNet34::/torch.nn.modules.linear.Linear::fc # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/modules/linear.py:114:0\n",
327
+ " %output : Float(*, 450, strides=[450, 1], requires_grad=1, device=cpu) = onnx::LogSoftmax[axis=1, onnx_name=\"/LogSoftmax\"](%/fc/Gemm_output_0), scope: __main__.ResNet34:: # /home/gautham/.local/lib/python3.10/site-packages/torch/nn/functional.py:1927:0\n",
328
  " return (%output)\n",
329
  "\n"
330
  ]
 
 
 
 
 
 
 
 
 
 
331
  }
332
  ],
333
  "source": [
334
+ "onnx_path = '../model/model.onnx'\n",
335
  "\n",
336
  "torch.onnx.export(model,\n",
337
  " dummy_input,\n",
 
352
  },
353
  {
354
  "cell_type": "code",
355
+ "execution_count": 5,
356
  "metadata": {},
357
  "outputs": [],
358
  "source": [
 
371
  },
372
  {
373
  "cell_type": "code",
374
+ "execution_count": 6,
375
  "metadata": {},
376
  "outputs": [
377
  {