Add model
Browse files- README.md +138 -0
- config.json +35 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
README.md
ADDED
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- image-classification
|
4 |
+
- timm
|
5 |
+
library_name: timm
|
6 |
+
license: apache-2.0
|
7 |
+
---
|
8 |
+
# Model card for tresnet_m.miil_in21k
|
9 |
+
|
10 |
+
A TResNet image classification model. Trained on ImageNet-21K-P ("ImageNet-21K Pretraining for the Masses", a 11k subset of ImageNet-22k) by paper authors.
|
11 |
+
|
12 |
+
The weights for this model have been remapped and modified from the originals to work with standard BatchNorm instead of InplaceABN. `inplace_abn` can be problematic to build recently and ends up slower with `memory_format=channels_last`, torch.compile(), etc.
|
13 |
+
|
14 |
+
## Model Details
|
15 |
+
- **Model Type:** Image classification / feature backbone
|
16 |
+
- **Model Stats:**
|
17 |
+
- Params (M): 52.3
|
18 |
+
- GMACs: 5.8
|
19 |
+
- Activations (M): 7.3
|
20 |
+
- Image size: 224 x 224
|
21 |
+
- **Papers:**
|
22 |
+
- TResNet: High Performance GPU-Dedicated Architecture: https://arxiv.org/abs/2003.13630
|
23 |
+
- ImageNet-21K Pretraining for the Masses: https://arxiv.org/abs/2104.10972
|
24 |
+
- **Pretrain Dataset:** ImageNet-21K-P
|
25 |
+
- **Original:**
|
26 |
+
- https://github.com/Alibaba-MIIL/TResNet
|
27 |
+
- https://github.com/Alibaba-MIIL/ImageNet21K
|
28 |
+
|
29 |
+
## Model Usage
|
30 |
+
### Image Classification
|
31 |
+
```python
|
32 |
+
from urllib.request import urlopen
|
33 |
+
from PIL import Image
|
34 |
+
import timm
|
35 |
+
|
36 |
+
img = Image.open(urlopen(
|
37 |
+
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
|
38 |
+
))
|
39 |
+
|
40 |
+
model = timm.create_model('tresnet_m.miil_in21k', pretrained=True)
|
41 |
+
model = model.eval()
|
42 |
+
|
43 |
+
# get model specific transforms (normalization, resize)
|
44 |
+
data_config = timm.data.resolve_model_data_config(model)
|
45 |
+
transforms = timm.data.create_transform(**data_config, is_training=False)
|
46 |
+
|
47 |
+
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
|
48 |
+
|
49 |
+
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
|
50 |
+
```
|
51 |
+
|
52 |
+
### Feature Map Extraction
|
53 |
+
```python
|
54 |
+
from urllib.request import urlopen
|
55 |
+
from PIL import Image
|
56 |
+
import timm
|
57 |
+
|
58 |
+
img = Image.open(urlopen(
|
59 |
+
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
|
60 |
+
))
|
61 |
+
|
62 |
+
model = timm.create_model(
|
63 |
+
'tresnet_m.miil_in21k',
|
64 |
+
pretrained=True,
|
65 |
+
features_only=True,
|
66 |
+
)
|
67 |
+
model = model.eval()
|
68 |
+
|
69 |
+
# get model specific transforms (normalization, resize)
|
70 |
+
data_config = timm.data.resolve_model_data_config(model)
|
71 |
+
transforms = timm.data.create_transform(**data_config, is_training=False)
|
72 |
+
|
73 |
+
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
|
74 |
+
|
75 |
+
for o in output:
|
76 |
+
# print shape of each feature map in output
|
77 |
+
# e.g.:
|
78 |
+
# torch.Size([1, 64, 56, 56])
|
79 |
+
# torch.Size([1, 128, 28, 28])
|
80 |
+
# torch.Size([1, 1024, 14, 14])
|
81 |
+
# torch.Size([1, 2048, 7, 7])
|
82 |
+
|
83 |
+
print(o.shape)
|
84 |
+
```
|
85 |
+
|
86 |
+
### Image Embeddings
|
87 |
+
```python
|
88 |
+
from urllib.request import urlopen
|
89 |
+
from PIL import Image
|
90 |
+
import timm
|
91 |
+
|
92 |
+
img = Image.open(urlopen(
|
93 |
+
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
|
94 |
+
))
|
95 |
+
|
96 |
+
model = timm.create_model(
|
97 |
+
'tresnet_m.miil_in21k',
|
98 |
+
pretrained=True,
|
99 |
+
num_classes=0, # remove classifier nn.Linear
|
100 |
+
)
|
101 |
+
model = model.eval()
|
102 |
+
|
103 |
+
# get model specific transforms (normalization, resize)
|
104 |
+
data_config = timm.data.resolve_model_data_config(model)
|
105 |
+
transforms = timm.data.create_transform(**data_config, is_training=False)
|
106 |
+
|
107 |
+
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
|
108 |
+
|
109 |
+
# or equivalently (without needing to set num_classes=0)
|
110 |
+
|
111 |
+
output = model.forward_features(transforms(img).unsqueeze(0))
|
112 |
+
# output is unpooled, a (1, 2048, 7, 7) shaped tensor
|
113 |
+
|
114 |
+
output = model.forward_head(output, pre_logits=True)
|
115 |
+
# output is a (1, num_features) shaped tensor
|
116 |
+
```
|
117 |
+
|
118 |
+
## Citation
|
119 |
+
```bibtex
|
120 |
+
@misc{ridnik2020tresnet,
|
121 |
+
title={TResNet: High Performance GPU-Dedicated Architecture},
|
122 |
+
author={Tal Ridnik and Hussam Lawen and Asaf Noy and Itamar Friedman},
|
123 |
+
year={2020},
|
124 |
+
eprint={2003.13630},
|
125 |
+
archivePrefix={arXiv},
|
126 |
+
primaryClass={cs.CV}
|
127 |
+
}
|
128 |
+
```
|
129 |
+
```bibtex
|
130 |
+
@misc{ridnik2021imagenet21k,
|
131 |
+
title={ImageNet-21K Pretraining for the Masses},
|
132 |
+
author={Tal Ridnik and Emanuel Ben-Baruch and Asaf Noy and Lihi Zelnik-Manor},
|
133 |
+
year={2021},
|
134 |
+
eprint={2104.10972},
|
135 |
+
archivePrefix={arXiv},
|
136 |
+
primaryClass={cs.CV}
|
137 |
+
}
|
138 |
+
```
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architecture": "tresnet_m",
|
3 |
+
"num_classes": 11221,
|
4 |
+
"num_features": 2048,
|
5 |
+
"pretrained_cfg": {
|
6 |
+
"tag": "miil_in21k",
|
7 |
+
"custom_load": false,
|
8 |
+
"input_size": [
|
9 |
+
3,
|
10 |
+
224,
|
11 |
+
224
|
12 |
+
],
|
13 |
+
"fixed_input_size": false,
|
14 |
+
"interpolation": "bilinear",
|
15 |
+
"crop_pct": 0.875,
|
16 |
+
"crop_mode": "center",
|
17 |
+
"mean": [
|
18 |
+
0.0,
|
19 |
+
0.0,
|
20 |
+
0.0
|
21 |
+
],
|
22 |
+
"std": [
|
23 |
+
1.0,
|
24 |
+
1.0,
|
25 |
+
1.0
|
26 |
+
],
|
27 |
+
"num_classes": 11221,
|
28 |
+
"pool_size": [
|
29 |
+
7,
|
30 |
+
7
|
31 |
+
],
|
32 |
+
"first_conv": "body.conv1.conv",
|
33 |
+
"classifier": "head.fc"
|
34 |
+
}
|
35 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0c4dba14875e71f2fbd03f463ad475f0c708a9810be3ec0cc8ec5cfb1e35f24
|
3 |
+
size 209617236
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77e985a1dfb1e646a905df65ff43eaa2be5237ca0a1367cec7013b1f1c19e782
|
3 |
+
size 209731669
|