Hugging Face's logo

g0ster
/
MNIST-practice

Model card Files Community
MNIST-practice
File size: 3,403 Bytes 
914d155
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
 
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import torchvision\n",
    "from torch import nn, optim\n",
    "from torch.autograd import Variable\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "mnist_data = torchvision.datasets.MNIST(\n",
    "    \"mnist_data\", train=True, transform=torchvision.transforms.ToTensor(), download=True\n",
    ")\n",
    "mnist_dataloader = torch.utils.data.DataLoader(mnist_data, batch_size=50)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "class Mnet(nn.Module):\n",
    "    def __init__(self):\n",
    "        super(Mnet, self).__init__()\n",
    "        self.linear1 = nn.Linear(28 * 28, 400)\n",
    "        self.linear2 = nn.Linear(400, 200)\n",
    "        self.linear3 = nn.Linear(200, 100)\n",
    "        self.linear4 = nn.Linear(100, 50)\n",
    "        self.linear5 = nn.Linear(50, 25)\n",
    "        self.final_linear = nn.Linear(25, 10)\n",
    "\n",
    "        self.relu = nn.ReLU()\n",
    "\n",
    "    def forward(self, images):\n",
    "        x = images.view(-1, 28 * 28)\n",
    "        x = self.relu(self.linear1(x))\n",
    "        x = self.relu(self.linear2(x))\n",
    "        x = self.relu(self.linear3(x))\n",
    "        x = self.relu(self.linear4(x))\n",
    "        x = self.relu(self.linear5(x))\n",
    "        x = self.final_linear(x)\n",
    "        return x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 50/50 [21:18<00:00, 25.57s/it]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "final loss: 1.1586851087486139e-06\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "from tqdm import tqdm\n",
    "model = Mnet()\n",
    "cec_loss = nn.CrossEntropyLoss()\n",
    "params = model.parameters()\n",
    "optimizer = optim.Adam(params=params, lr=0.001)\n",
    "\n",
    "n_epochs = 50\n",
    "n_iterations = 0\n",
    "\n",
    "for e in tqdm(range(n_epochs)):\n",
    "    for i, (images, labels) in enumerate(mnist_dataloader):\n",
    "        output = model(images)\n",
    "\n",
    "        model.zero_grad()\n",
    "        loss = cec_loss(output, labels)\n",
    "        loss.backward()\n",
    "\n",
    "        optimizer.step()\n",
    "        n_iterations+=1\n",
    "\n",
    "print(f'final loss: {loss.item()}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "torch.save(model, \"mnistmodel.pt\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}