timm
/

Image Classification
timm
PyTorch
Safetensors
rwightman HF staff commited on
Commit
1e76a9f
1 Parent(s): ba16e85
Files changed (4) hide show
  1. README.md +252 -0
  2. config.json +37 -0
  3. model.safetensors +3 -0
  4. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,252 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - image-classification
4
+ - timm
5
+ library_tag: timm
6
+ license: cc-by-nc-4.0
7
+ datasets:
8
+ - imagenet-1k
9
+ - ig-3.6b
10
+ ---
11
+ # Model card for regnety_160.swag_ft_in1k
12
+
13
+ A RegNetY-16GF image classification model. Pretrained according to SWAG: weakly-supervised learning on ~3.6B Instagram images and associated hashtags. Fine-tuned on ImageNet-1k by paper authors.
14
+
15
+ These weights are restricted from commericial use by their CC-BY-NC-4.0 license.
16
+
17
+ The `timm` RegNet implementation includes a number of enhancements not present in other implementations, including:
18
+ * stochastic depth
19
+ * gradient checkpointing
20
+ * layer-wise LR decay
21
+ * configurable output stride (dilation)
22
+ * configurable activation and norm layers
23
+ * option for a pre-activation bottleneck block used in RegNetV variant
24
+ * only known RegNetZ model definitions with pretrained weights
25
+
26
+
27
+ ## Model Details
28
+ - **Model Type:** Image classification / feature backbone
29
+ - **Model Stats:**
30
+ - Params (M): 83.6
31
+ - GMACs: 46.9
32
+ - Activations (M): 67.7
33
+ - Image size: 384 x 384
34
+ - **Papers:**
35
+ - Revisiting Weakly Supervised Pre-Training of Visual Perception Models: https://arxiv.org/abs/2201.08371
36
+ - Designing Network Design Spaces: https://arxiv.org/abs/2003.13678
37
+ - **Original:** https://github.com/facebookresearch/SWAG
38
+ - **Dataset:** ImageNet-1k
39
+ - **Pretrain Dataset:** IG-3.6B
40
+
41
+ ## Model Usage
42
+ ### Image Classification
43
+ ```python
44
+ from urllib.request import urlopen
45
+ from PIL import Image
46
+ import timm
47
+
48
+ img = Image.open(urlopen(
49
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
50
+ ))
51
+
52
+ model = timm.create_model('regnety_160.swag_ft_in1k', pretrained=True)
53
+ model = model.eval()
54
+
55
+ # get model specific transforms (normalization, resize)
56
+ data_config = timm.data.resolve_model_data_config(model)
57
+ transforms = timm.data.create_transform(**data_config, is_training=False)
58
+
59
+ output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
60
+
61
+ top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
62
+ ```
63
+
64
+ ### Feature Map Extraction
65
+ ```python
66
+ from urllib.request import urlopen
67
+ from PIL import Image
68
+ import timm
69
+
70
+ img = Image.open(urlopen(
71
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
72
+ ))
73
+
74
+ model = timm.create_model(
75
+ 'regnety_160.swag_ft_in1k',
76
+ pretrained=True,
77
+ features_only=True,
78
+ )
79
+ model = model.eval()
80
+
81
+ # get model specific transforms (normalization, resize)
82
+ data_config = timm.data.resolve_model_data_config(model)
83
+ transforms = timm.data.create_transform(**data_config, is_training=False)
84
+
85
+ output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
86
+
87
+ for o in output:
88
+ # print shape of each feature map in output
89
+ # e.g.:
90
+ # torch.Size([1, 32, 192, 192])
91
+ # torch.Size([1, 224, 96, 96])
92
+ # torch.Size([1, 448, 48, 48])
93
+ # torch.Size([1, 1232, 24, 24])
94
+ # torch.Size([1, 3024, 12, 12])
95
+
96
+ print(o.shape)
97
+ ```
98
+
99
+ ### Image Embeddings
100
+ ```python
101
+ from urllib.request import urlopen
102
+ from PIL import Image
103
+ import timm
104
+
105
+ img = Image.open(urlopen(
106
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
107
+ ))
108
+
109
+ model = timm.create_model(
110
+ 'regnety_160.swag_ft_in1k',
111
+ pretrained=True,
112
+ num_classes=0, # remove classifier nn.Linear
113
+ )
114
+ model = model.eval()
115
+
116
+ # get model specific transforms (normalization, resize)
117
+ data_config = timm.data.resolve_model_data_config(model)
118
+ transforms = timm.data.create_transform(**data_config, is_training=False)
119
+
120
+ output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
121
+
122
+ # or equivalently (without needing to set num_classes=0)
123
+
124
+ output = model.forward_features(transforms(img).unsqueeze(0))
125
+ # output is unpooled, a (1, 3024, 12, 12) shaped tensor
126
+
127
+ output = model.forward_head(output, pre_logits=True)
128
+ # output is a (1, num_features) shaped tensor
129
+ ```
130
+
131
+ ## Model Comparison
132
+ Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
133
+
134
+ For the comparison summary below, the ra_in1k, ra3_in1k, ch_in1k, sw_*, and lion_* tagged weights are trained in `timm`.
135
+
136
+ |model |img_size|top1 |top5 |param_count|gmacs|macts |
137
+ |-------------------------|--------|------|------|-----------|-----|------|
138
+ |[regnety_1280.swag_ft_in1k](https://huggingface.co/timm/regnety_1280.swag_ft_in1k)|384 |88.228|98.684|644.81 |374.99|210.2 |
139
+ |[regnety_320.swag_ft_in1k](https://huggingface.co/timm/regnety_320.swag_ft_in1k)|384 |86.84 |98.364|145.05 |95.0 |88.87 |
140
+ |[regnety_160.swag_ft_in1k](https://huggingface.co/timm/regnety_160.swag_ft_in1k)|384 |86.024|98.05 |83.59 |46.87|67.67 |
141
+ |[regnety_160.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.sw_in12k_ft_in1k)|288 |86.004|97.83 |83.59 |26.37|38.07 |
142
+ |[regnety_1280.swag_lc_in1k](https://huggingface.co/timm/regnety_1280.swag_lc_in1k)|224 |85.996|97.848|644.81 |127.66|71.58 |
143
+ |[regnety_160.lion_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.lion_in12k_ft_in1k)|288 |85.982|97.844|83.59 |26.37|38.07 |
144
+ |[regnety_160.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.sw_in12k_ft_in1k)|224 |85.574|97.666|83.59 |15.96|23.04 |
145
+ |[regnety_160.lion_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.lion_in12k_ft_in1k)|224 |85.564|97.674|83.59 |15.96|23.04 |
146
+ |[regnety_120.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_120.sw_in12k_ft_in1k)|288 |85.398|97.584|51.82 |20.06|35.34 |
147
+ |[regnety_2560.seer_ft_in1k](https://huggingface.co/timm/regnety_2560.seer_ft_in1k)|384 |85.15 |97.436|1282.6 |747.83|296.49|
148
+ |[regnetz_e8.ra3_in1k](https://huggingface.co/timm/regnetz_e8.ra3_in1k)|320 |85.036|97.268|57.7 |15.46|63.94 |
149
+ |[regnety_120.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_120.sw_in12k_ft_in1k)|224 |84.976|97.416|51.82 |12.14|21.38 |
150
+ |[regnety_320.swag_lc_in1k](https://huggingface.co/timm/regnety_320.swag_lc_in1k)|224 |84.56 |97.446|145.05 |32.34|30.26 |
151
+ |[regnetz_040_h.ra3_in1k](https://huggingface.co/timm/regnetz_040_h.ra3_in1k)|320 |84.496|97.004|28.94 |6.43 |37.94 |
152
+ |[regnetz_e8.ra3_in1k](https://huggingface.co/timm/regnetz_e8.ra3_in1k)|256 |84.436|97.02 |57.7 |9.91 |40.94 |
153
+ |[regnety_1280.seer_ft_in1k](https://huggingface.co/timm/regnety_1280.seer_ft_in1k)|384 |84.432|97.092|644.81 |374.99|210.2 |
154
+ |[regnetz_040.ra3_in1k](https://huggingface.co/timm/regnetz_040.ra3_in1k)|320 |84.246|96.93 |27.12 |6.35 |37.78 |
155
+ |[regnetz_d8.ra3_in1k](https://huggingface.co/timm/regnetz_d8.ra3_in1k)|320 |84.054|96.992|23.37 |6.19 |37.08 |
156
+ |[regnetz_d8_evos.ch_in1k](https://huggingface.co/timm/regnetz_d8_evos.ch_in1k)|320 |84.038|96.992|23.46 |7.03 |38.92 |
157
+ |[regnetz_d32.ra3_in1k](https://huggingface.co/timm/regnetz_d32.ra3_in1k)|320 |84.022|96.866|27.58 |9.33 |37.08 |
158
+ |[regnety_080.ra3_in1k](https://huggingface.co/timm/regnety_080.ra3_in1k)|288 |83.932|96.888|39.18 |13.22|29.69 |
159
+ |[regnety_640.seer_ft_in1k](https://huggingface.co/timm/regnety_640.seer_ft_in1k)|384 |83.912|96.924|281.38 |188.47|124.83|
160
+ |[regnety_160.swag_lc_in1k](https://huggingface.co/timm/regnety_160.swag_lc_in1k)|224 |83.778|97.286|83.59 |15.96|23.04 |
161
+ |[regnetz_040_h.ra3_in1k](https://huggingface.co/timm/regnetz_040_h.ra3_in1k)|256 |83.776|96.704|28.94 |4.12 |24.29 |
162
+ |[regnetv_064.ra3_in1k](https://huggingface.co/timm/regnetv_064.ra3_in1k)|288 |83.72 |96.75 |30.58 |10.55|27.11 |
163
+ |[regnety_064.ra3_in1k](https://huggingface.co/timm/regnety_064.ra3_in1k)|288 |83.718|96.724|30.58 |10.56|27.11 |
164
+ |[regnety_160.deit_in1k](https://huggingface.co/timm/regnety_160.deit_in1k)|288 |83.69 |96.778|83.59 |26.37|38.07 |
165
+ |[regnetz_040.ra3_in1k](https://huggingface.co/timm/regnetz_040.ra3_in1k)|256 |83.62 |96.704|27.12 |4.06 |24.19 |
166
+ |[regnetz_d8.ra3_in1k](https://huggingface.co/timm/regnetz_d8.ra3_in1k)|256 |83.438|96.776|23.37 |3.97 |23.74 |
167
+ |[regnetz_d32.ra3_in1k](https://huggingface.co/timm/regnetz_d32.ra3_in1k)|256 |83.424|96.632|27.58 |5.98 |23.74 |
168
+ |[regnetz_d8_evos.ch_in1k](https://huggingface.co/timm/regnetz_d8_evos.ch_in1k)|256 |83.36 |96.636|23.46 |4.5 |24.92 |
169
+ |[regnety_320.seer_ft_in1k](https://huggingface.co/timm/regnety_320.seer_ft_in1k)|384 |83.35 |96.71 |145.05 |95.0 |88.87 |
170
+ |[regnetv_040.ra3_in1k](https://huggingface.co/timm/regnetv_040.ra3_in1k)|288 |83.204|96.66 |20.64 |6.6 |20.3 |
171
+ |[regnety_320.tv2_in1k](https://huggingface.co/timm/regnety_320.tv2_in1k)|224 |83.162|96.42 |145.05 |32.34|30.26 |
172
+ |[regnety_080.ra3_in1k](https://huggingface.co/timm/regnety_080.ra3_in1k)|224 |83.16 |96.486|39.18 |8.0 |17.97 |
173
+ |[regnetv_064.ra3_in1k](https://huggingface.co/timm/regnetv_064.ra3_in1k)|224 |83.108|96.458|30.58 |6.39 |16.41 |
174
+ |[regnety_040.ra3_in1k](https://huggingface.co/timm/regnety_040.ra3_in1k)|288 |83.044|96.5 |20.65 |6.61 |20.3 |
175
+ |[regnety_064.ra3_in1k](https://huggingface.co/timm/regnety_064.ra3_in1k)|224 |83.02 |96.292|30.58 |6.39 |16.41 |
176
+ |[regnety_160.deit_in1k](https://huggingface.co/timm/regnety_160.deit_in1k)|224 |82.974|96.502|83.59 |15.96|23.04 |
177
+ |[regnetx_320.tv2_in1k](https://huggingface.co/timm/regnetx_320.tv2_in1k)|224 |82.816|96.208|107.81 |31.81|36.3 |
178
+ |[regnety_032.ra_in1k](https://huggingface.co/timm/regnety_032.ra_in1k)|288 |82.742|96.418|19.44 |5.29 |18.61 |
179
+ |[regnety_160.tv2_in1k](https://huggingface.co/timm/regnety_160.tv2_in1k)|224 |82.634|96.22 |83.59 |15.96|23.04 |
180
+ |[regnetz_c16_evos.ch_in1k](https://huggingface.co/timm/regnetz_c16_evos.ch_in1k)|320 |82.634|96.472|13.49 |3.86 |25.88 |
181
+ |[regnety_080_tv.tv2_in1k](https://huggingface.co/timm/regnety_080_tv.tv2_in1k)|224 |82.592|96.246|39.38 |8.51 |19.73 |
182
+ |[regnetx_160.tv2_in1k](https://huggingface.co/timm/regnetx_160.tv2_in1k)|224 |82.564|96.052|54.28 |15.99|25.52 |
183
+ |[regnetz_c16.ra3_in1k](https://huggingface.co/timm/regnetz_c16.ra3_in1k)|320 |82.51 |96.358|13.46 |3.92 |25.88 |
184
+ |[regnetv_040.ra3_in1k](https://huggingface.co/timm/regnetv_040.ra3_in1k)|224 |82.44 |96.198|20.64 |4.0 |12.29 |
185
+ |[regnety_040.ra3_in1k](https://huggingface.co/timm/regnety_040.ra3_in1k)|224 |82.304|96.078|20.65 |4.0 |12.29 |
186
+ |[regnetz_c16.ra3_in1k](https://huggingface.co/timm/regnetz_c16.ra3_in1k)|256 |82.16 |96.048|13.46 |2.51 |16.57 |
187
+ |[regnetz_c16_evos.ch_in1k](https://huggingface.co/timm/regnetz_c16_evos.ch_in1k)|256 |81.936|96.15 |13.49 |2.48 |16.57 |
188
+ |[regnety_032.ra_in1k](https://huggingface.co/timm/regnety_032.ra_in1k)|224 |81.924|95.988|19.44 |3.2 |11.26 |
189
+ |[regnety_032.tv2_in1k](https://huggingface.co/timm/regnety_032.tv2_in1k)|224 |81.77 |95.842|19.44 |3.2 |11.26 |
190
+ |[regnetx_080.tv2_in1k](https://huggingface.co/timm/regnetx_080.tv2_in1k)|224 |81.552|95.544|39.57 |8.02 |14.06 |
191
+ |[regnetx_032.tv2_in1k](https://huggingface.co/timm/regnetx_032.tv2_in1k)|224 |80.924|95.27 |15.3 |3.2 |11.37 |
192
+ |[regnety_320.pycls_in1k](https://huggingface.co/timm/regnety_320.pycls_in1k)|224 |80.804|95.246|145.05 |32.34|30.26 |
193
+ |[regnetz_b16.ra3_in1k](https://huggingface.co/timm/regnetz_b16.ra3_in1k)|288 |80.712|95.47 |9.72 |2.39 |16.43 |
194
+ |[regnety_016.tv2_in1k](https://huggingface.co/timm/regnety_016.tv2_in1k)|224 |80.66 |95.334|11.2 |1.63 |8.04 |
195
+ |[regnety_120.pycls_in1k](https://huggingface.co/timm/regnety_120.pycls_in1k)|224 |80.37 |95.12 |51.82 |12.14|21.38 |
196
+ |[regnety_160.pycls_in1k](https://huggingface.co/timm/regnety_160.pycls_in1k)|224 |80.288|94.964|83.59 |15.96|23.04 |
197
+ |[regnetx_320.pycls_in1k](https://huggingface.co/timm/regnetx_320.pycls_in1k)|224 |80.246|95.01 |107.81 |31.81|36.3 |
198
+ |[regnety_080.pycls_in1k](https://huggingface.co/timm/regnety_080.pycls_in1k)|224 |79.882|94.834|39.18 |8.0 |17.97 |
199
+ |[regnetz_b16.ra3_in1k](https://huggingface.co/timm/regnetz_b16.ra3_in1k)|224 |79.872|94.974|9.72 |1.45 |9.95 |
200
+ |[regnetx_160.pycls_in1k](https://huggingface.co/timm/regnetx_160.pycls_in1k)|224 |79.862|94.828|54.28 |15.99|25.52 |
201
+ |[regnety_064.pycls_in1k](https://huggingface.co/timm/regnety_064.pycls_in1k)|224 |79.716|94.772|30.58 |6.39 |16.41 |
202
+ |[regnetx_120.pycls_in1k](https://huggingface.co/timm/regnetx_120.pycls_in1k)|224 |79.592|94.738|46.11 |12.13|21.37 |
203
+ |[regnetx_016.tv2_in1k](https://huggingface.co/timm/regnetx_016.tv2_in1k)|224 |79.44 |94.772|9.19 |1.62 |7.93 |
204
+ |[regnety_040.pycls_in1k](https://huggingface.co/timm/regnety_040.pycls_in1k)|224 |79.23 |94.654|20.65 |4.0 |12.29 |
205
+ |[regnetx_080.pycls_in1k](https://huggingface.co/timm/regnetx_080.pycls_in1k)|224 |79.198|94.55 |39.57 |8.02 |14.06 |
206
+ |[regnetx_064.pycls_in1k](https://huggingface.co/timm/regnetx_064.pycls_in1k)|224 |79.064|94.454|26.21 |6.49 |16.37 |
207
+ |[regnety_032.pycls_in1k](https://huggingface.co/timm/regnety_032.pycls_in1k)|224 |78.884|94.412|19.44 |3.2 |11.26 |
208
+ |[regnety_008_tv.tv2_in1k](https://huggingface.co/timm/regnety_008_tv.tv2_in1k)|224 |78.654|94.388|6.43 |0.84 |5.42 |
209
+ |[regnetx_040.pycls_in1k](https://huggingface.co/timm/regnetx_040.pycls_in1k)|224 |78.482|94.24 |22.12 |3.99 |12.2 |
210
+ |[regnetx_032.pycls_in1k](https://huggingface.co/timm/regnetx_032.pycls_in1k)|224 |78.178|94.08 |15.3 |3.2 |11.37 |
211
+ |[regnety_016.pycls_in1k](https://huggingface.co/timm/regnety_016.pycls_in1k)|224 |77.862|93.73 |11.2 |1.63 |8.04 |
212
+ |[regnetx_008.tv2_in1k](https://huggingface.co/timm/regnetx_008.tv2_in1k)|224 |77.302|93.672|7.26 |0.81 |5.15 |
213
+ |[regnetx_016.pycls_in1k](https://huggingface.co/timm/regnetx_016.pycls_in1k)|224 |76.908|93.418|9.19 |1.62 |7.93 |
214
+ |[regnety_008.pycls_in1k](https://huggingface.co/timm/regnety_008.pycls_in1k)|224 |76.296|93.05 |6.26 |0.81 |5.25 |
215
+ |[regnety_004.tv2_in1k](https://huggingface.co/timm/regnety_004.tv2_in1k)|224 |75.592|92.712|4.34 |0.41 |3.89 |
216
+ |[regnety_006.pycls_in1k](https://huggingface.co/timm/regnety_006.pycls_in1k)|224 |75.244|92.518|6.06 |0.61 |4.33 |
217
+ |[regnetx_008.pycls_in1k](https://huggingface.co/timm/regnetx_008.pycls_in1k)|224 |75.042|92.342|7.26 |0.81 |5.15 |
218
+ |[regnetx_004_tv.tv2_in1k](https://huggingface.co/timm/regnetx_004_tv.tv2_in1k)|224 |74.57 |92.184|5.5 |0.42 |3.17 |
219
+ |[regnety_004.pycls_in1k](https://huggingface.co/timm/regnety_004.pycls_in1k)|224 |74.018|91.764|4.34 |0.41 |3.89 |
220
+ |[regnetx_006.pycls_in1k](https://huggingface.co/timm/regnetx_006.pycls_in1k)|224 |73.862|91.67 |6.2 |0.61 |3.98 |
221
+ |[regnetx_004.pycls_in1k](https://huggingface.co/timm/regnetx_004.pycls_in1k)|224 |72.38 |90.832|5.16 |0.4 |3.14 |
222
+ |[regnety_002.pycls_in1k](https://huggingface.co/timm/regnety_002.pycls_in1k)|224 |70.282|89.534|3.16 |0.2 |2.17 |
223
+ |[regnetx_002.pycls_in1k](https://huggingface.co/timm/regnetx_002.pycls_in1k)|224 |68.752|88.556|2.68 |0.2 |2.16 |
224
+
225
+ ## Citation
226
+ ```bibtex
227
+ @inproceedings{singh2022revisiting,
228
+ title={{Revisiting Weakly Supervised Pre-Training of Visual Perception Models}},
229
+ author={Singh, Mannat and Gustafson, Laura and Adcock, Aaron and Reis, Vinicius de Freitas and Gedik, Bugra and Kosaraju, Raj Prateek and Mahajan, Dhruv and Girshick, Ross and Doll{'a}r, Piotr and van der Maaten, Laurens},
230
+ booktitle={CVPR},
231
+ year={2022}
232
+ }
233
+ ```
234
+ ```bibtex
235
+ @InProceedings{Radosavovic2020,
236
+ title = {Designing Network Design Spaces},
237
+ author = {Ilija Radosavovic and Raj Prateek Kosaraju and Ross Girshick and Kaiming He and Piotr Doll{'a}r},
238
+ booktitle = {CVPR},
239
+ year = {2020}
240
+ }
241
+ ```
242
+ ```bibtex
243
+ @misc{rw2019timm,
244
+ author = {Ross Wightman},
245
+ title = {PyTorch Image Models},
246
+ year = {2019},
247
+ publisher = {GitHub},
248
+ journal = {GitHub repository},
249
+ doi = {10.5281/zenodo.4414861},
250
+ howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
251
+ }
252
+ ```
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "regnety_160",
3
+ "num_classes": 1000,
4
+ "num_features": 3024,
5
+ "pretrained_cfg": {
6
+ "tag": "swag_ft_in1k",
7
+ "custom_load": false,
8
+ "input_size": [
9
+ 3,
10
+ 384,
11
+ 384
12
+ ],
13
+ "fixed_input_size": false,
14
+ "interpolation": "bicubic",
15
+ "crop_pct": 1.0,
16
+ "crop_mode": "center",
17
+ "mean": [
18
+ 0.485,
19
+ 0.456,
20
+ 0.406
21
+ ],
22
+ "std": [
23
+ 0.229,
24
+ 0.224,
25
+ 0.225
26
+ ],
27
+ "num_classes": 1000,
28
+ "pool_size": [
29
+ 12,
30
+ 12
31
+ ],
32
+ "first_conv": "stem.conv",
33
+ "classifier": "head.fc",
34
+ "license": "cc-by-nc-4.0",
35
+ "origin_url": "https://github.com/pytorch/vision"
36
+ }
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7555d0c6287e25622697725f42a841fd65bb1e53150f039ce2b9a37b63fe8784
3
+ size 334892224
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f22e16f4ce922e532d910f832949e76a680593c3feacb4372c0e3f334c3a45f7
3
+ size 335000317