Hugging Face's logo

timm
/
regnetz_c16_evos.ch_in1k

Image Classification
timm
PyTorch
Safetensors
Transformers
Model card Files Community
rwightman HF staff commited on
Commit
744296d
·
1 Parent(s): 5e3dba5

Add model

Browse files
Files changed (4) hide show
  1. README.md +265 -0
  2. config.json +40 -0
  3. model.safetensors +3 -0
  4. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - image-classification
4
+ - timm
5
+ library_tag: timm
6
+ license: apache-2.0
7
+ datasets:
8
+ - imagenet-1k
9
+ ---
10
+ # Model card for regnetz_c16_evos.ch_in1k
11
+
12
+ A RegNetZ image classification model. Trained on ImageNet-1k by Ross Wightman in `timm`.
13
+
14
+ These RegNetZ B / C / D models explore different group size and layer configurations and did not follow any paper descriptions. Like EfficientNets, this architecture uses linear (non activated) block outputs and an inverted-bottleneck (mid block expansion).
15
+ * B16 : ~1.5GF @ 256x256 with a group-width of 16. Single layer stem.
16
+ * C16 : ~2.5GF @ 256x256 with a group-width of 16. Single layer stem.
17
+ * D32 : ~6GF @ 256x256 with a group-width of 32. Tiered 3-layer stem, no pooling.
18
+ * D8 : ~4GF @ 256x256 with a group-width of 8. Tiered 3-layer stem, no pooling.
19
+ * E8 : ~10GF @ 256x256 with a group-width of 8. Tiered 3-layer stem, no pooling.
20
+
21
+ This model uses customized EvoNorm-S0 normalization-activation layers instead of BatchNorm with SiLU activations.
22
+
23
+ This model architecture is implemented using `timm`'s flexible [BYOBNet (Bring-Your-Own-Blocks Network)](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/byobnet.py).
24
+
25
+ BYOBNet allows configuration of:
26
+ * block / stage layout
27
+ * stem layout
28
+ * output stride (dilation)
29
+ * activation and norm layers
30
+ * channel and spatial / self-attention layers
31
+
32
+ ...and also includes `timm` features common to many other architectures, including:
33
+ * stochastic depth
34
+ * gradient checkpointing
35
+ * layer-wise LR decay
36
+ * per-stage feature extraction
37
+
38
+
39
+ ## Model Details
40
+ - **Model Type:** Image classification / feature backbone
41
+ - **Model Stats:**
42
+ - Params (M): 13.5
43
+ - GMACs: 2.5
44
+ - Activations (M): 16.6
45
+ - Image size: train = 256 x 256, test = 320 x 320
46
+ - **Papers:**
47
+ - Fast and Accurate Model Scaling: https://arxiv.org/abs/2103.06877
48
+ - Evolving Normalization-Activation Layers: https://arxiv.org/abs/2004.02967
49
+ - **Dataset:** ImageNet-1k
50
+ - **Original:** https://github.com/huggingface/pytorch-image-models
51
+
52
+ ## Model Usage
53
+ ### Image Classification
54
+ ```python
55
+ from urllib.request import urlopen
56
+ from PIL import Image
57
+ import timm
58
+
59
+ img = Image.open(urlopen(
60
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
61
+ ))
62
+
63
+ model = timm.create_model('regnetz_c16_evos.ch_in1k', pretrained=True)
64
+ model = model.eval()
65
+
66
+ # get model specific transforms (normalization, resize)
67
+ data_config = timm.data.resolve_model_data_config(model)
68
+ transforms = timm.data.create_transform(**data_config, is_training=False)
69
+
70
+ output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
71
+
72
+ top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
73
+ ```
74
+
75
+ ### Feature Map Extraction
76
+ ```python
77
+ from urllib.request import urlopen
78
+ from PIL import Image
79
+ import timm
80
+
81
+ img = Image.open(urlopen(
82
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
83
+ ))
84
+
85
+ model = timm.create_model(
86
+ 'regnetz_c16_evos.ch_in1k',
87
+ pretrained=True,
88
+ features_only=True,
89
+ )
90
+ model = model.eval()
91
+
92
+ # get model specific transforms (normalization, resize)
93
+ data_config = timm.data.resolve_model_data_config(model)
94
+ transforms = timm.data.create_transform(**data_config, is_training=False)
95
+
96
+ output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
97
+
98
+ for o in output:
99
+ # print shape of each feature map in output
100
+ # e.g.:
101
+ # torch.Size([1, 32, 128, 128])
102
+ # torch.Size([1, 48, 64, 64])
103
+ # torch.Size([1, 96, 32, 32])
104
+ # torch.Size([1, 192, 16, 16])
105
+ # torch.Size([1, 1536, 8, 8])
106
+
107
+ print(o.shape)
108
+ ```
109
+
110
+ ### Image Embeddings
111
+ ```python
112
+ from urllib.request import urlopen
113
+ from PIL import Image
114
+ import timm
115
+
116
+ img = Image.open(urlopen(
117
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
118
+ ))
119
+
120
+ model = timm.create_model(
121
+ 'regnetz_c16_evos.ch_in1k',
122
+ pretrained=True,
123
+ num_classes=0, # remove classifier nn.Linear
124
+ )
125
+ model = model.eval()
126
+
127
+ # get model specific transforms (normalization, resize)
128
+ data_config = timm.data.resolve_model_data_config(model)
129
+ transforms = timm.data.create_transform(**data_config, is_training=False)
130
+
131
+ output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
132
+
133
+ # or equivalently (without needing to set num_classes=0)
134
+
135
+ output = model.forward_features(transforms(img).unsqueeze(0))
136
+ # output is unpooled, a (1, 1536, 8, 8) shaped tensor
137
+
138
+ output = model.forward_head(output, pre_logits=True)
139
+ # output is a (1, num_features) shaped tensor
140
+ ```
141
+
142
+ ## Model Comparison
143
+ Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
144
+
145
+ For the comparison summary below, the ra_in1k, ra3_in1k, ch_in1k, sw_*, and lion_* tagged weights are trained in `timm`.
146
+
147
+ |model |img_size|top1 |top5 |param_count|gmacs|macts |
148
+ |-------------------------|--------|------|------|-----------|-----|------|
149
+ |[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 |
150
+ |[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 |
151
+ |[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 |
152
+ |[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 |
153
+ |[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 |
154
+ |[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 |
155
+ |[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 |
156
+ |[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 |
157
+ |[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 |
158
+ |[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|
159
+ |[regnetz_e8.ra3_in1k](https://huggingface.co/timm/regnetz_e8.ra3_in1k)|320 |85.036|97.268|57.7 |15.46|63.94 |
160
+ |[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 |
161
+ |[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 |
162
+ |[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 |
163
+ |[regnetz_e8.ra3_in1k](https://huggingface.co/timm/regnetz_e8.ra3_in1k)|256 |84.436|97.02 |57.7 |9.91 |40.94 |
164
+ |[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 |
165
+ |[regnetz_040.ra3_in1k](https://huggingface.co/timm/regnetz_040.ra3_in1k)|320 |84.246|96.93 |27.12 |6.35 |37.78 |
166
+ |[regnetz_d8.ra3_in1k](https://huggingface.co/timm/regnetz_d8.ra3_in1k)|320 |84.054|96.992|23.37 |6.19 |37.08 |
167
+ |[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 |
168
+ |[regnetz_d32.ra3_in1k](https://huggingface.co/timm/regnetz_d32.ra3_in1k)|320 |84.022|96.866|27.58 |9.33 |37.08 |
169
+ |[regnety_080.ra3_in1k](https://huggingface.co/timm/regnety_080.ra3_in1k)|288 |83.932|96.888|39.18 |13.22|29.69 |
170
+ |[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|
171
+ |[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 |
172
+ |[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 |
173
+ |[regnetv_064.ra3_in1k](https://huggingface.co/timm/regnetv_064.ra3_in1k)|288 |83.72 |96.75 |30.58 |10.55|27.11 |
174
+ |[regnety_064.ra3_in1k](https://huggingface.co/timm/regnety_064.ra3_in1k)|288 |83.718|96.724|30.58 |10.56|27.11 |
175
+ |[regnety_160.deit_in1k](https://huggingface.co/timm/regnety_160.deit_in1k)|288 |83.69 |96.778|83.59 |26.37|38.07 |
176
+ |[regnetz_040.ra3_in1k](https://huggingface.co/timm/regnetz_040.ra3_in1k)|256 |83.62 |96.704|27.12 |4.06 |24.19 |
177
+ |[regnetz_d8.ra3_in1k](https://huggingface.co/timm/regnetz_d8.ra3_in1k)|256 |83.438|96.776|23.37 |3.97 |23.74 |
178
+ |[regnetz_d32.ra3_in1k](https://huggingface.co/timm/regnetz_d32.ra3_in1k)|256 |83.424|96.632|27.58 |5.98 |23.74 |
179
+ |[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 |
180
+ |[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 |
181
+ |[regnetv_040.ra3_in1k](https://huggingface.co/timm/regnetv_040.ra3_in1k)|288 |83.204|96.66 |20.64 |6.6 |20.3 |
182
+ |[regnety_320.tv2_in1k](https://huggingface.co/timm/regnety_320.tv2_in1k)|224 |83.162|96.42 |145.05 |32.34|30.26 |
183
+ |[regnety_080.ra3_in1k](https://huggingface.co/timm/regnety_080.ra3_in1k)|224 |83.16 |96.486|39.18 |8.0 |17.97 |
184
+ |[regnetv_064.ra3_in1k](https://huggingface.co/timm/regnetv_064.ra3_in1k)|224 |83.108|96.458|30.58 |6.39 |16.41 |
185
+ |[regnety_040.ra3_in1k](https://huggingface.co/timm/regnety_040.ra3_in1k)|288 |83.044|96.5 |20.65 |6.61 |20.3 |
186
+ |[regnety_064.ra3_in1k](https://huggingface.co/timm/regnety_064.ra3_in1k)|224 |83.02 |96.292|30.58 |6.39 |16.41 |
187
+ |[regnety_160.deit_in1k](https://huggingface.co/timm/regnety_160.deit_in1k)|224 |82.974|96.502|83.59 |15.96|23.04 |
188
+ |[regnetx_320.tv2_in1k](https://huggingface.co/timm/regnetx_320.tv2_in1k)|224 |82.816|96.208|107.81 |31.81|36.3 |
189
+ |[regnety_032.ra_in1k](https://huggingface.co/timm/regnety_032.ra_in1k)|288 |82.742|96.418|19.44 |5.29 |18.61 |
190
+ |[regnety_160.tv2_in1k](https://huggingface.co/timm/regnety_160.tv2_in1k)|224 |82.634|96.22 |83.59 |15.96|23.04 |
191
+ |[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 |
192
+ |[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 |
193
+ |[regnetx_160.tv2_in1k](https://huggingface.co/timm/regnetx_160.tv2_in1k)|224 |82.564|96.052|54.28 |15.99|25.52 |
194
+ |[regnetz_c16.ra3_in1k](https://huggingface.co/timm/regnetz_c16.ra3_in1k)|320 |82.51 |96.358|13.46 |3.92 |25.88 |
195
+ |[regnetv_040.ra3_in1k](https://huggingface.co/timm/regnetv_040.ra3_in1k)|224 |82.44 |96.198|20.64 |4.0 |12.29 |
196
+ |[regnety_040.ra3_in1k](https://huggingface.co/timm/regnety_040.ra3_in1k)|224 |82.304|96.078|20.65 |4.0 |12.29 |
197
+ |[regnetz_c16.ra3_in1k](https://huggingface.co/timm/regnetz_c16.ra3_in1k)|256 |82.16 |96.048|13.46 |2.51 |16.57 |
198
+ |[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 |
199
+ |[regnety_032.ra_in1k](https://huggingface.co/timm/regnety_032.ra_in1k)|224 |81.924|95.988|19.44 |3.2 |11.26 |
200
+ |[regnety_032.tv2_in1k](https://huggingface.co/timm/regnety_032.tv2_in1k)|224 |81.77 |95.842|19.44 |3.2 |11.26 |
201
+ |[regnetx_080.tv2_in1k](https://huggingface.co/timm/regnetx_080.tv2_in1k)|224 |81.552|95.544|39.57 |8.02 |14.06 |
202
+ |[regnetx_032.tv2_in1k](https://huggingface.co/timm/regnetx_032.tv2_in1k)|224 |80.924|95.27 |15.3 |3.2 |11.37 |
203
+ |[regnety_320.pycls_in1k](https://huggingface.co/timm/regnety_320.pycls_in1k)|224 |80.804|95.246|145.05 |32.34|30.26 |
204
+ |[regnetz_b16.ra3_in1k](https://huggingface.co/timm/regnetz_b16.ra3_in1k)|288 |80.712|95.47 |9.72 |2.39 |16.43 |
205
+ |[regnety_016.tv2_in1k](https://huggingface.co/timm/regnety_016.tv2_in1k)|224 |80.66 |95.334|11.2 |1.63 |8.04 |
206
+ |[regnety_120.pycls_in1k](https://huggingface.co/timm/regnety_120.pycls_in1k)|224 |80.37 |95.12 |51.82 |12.14|21.38 |
207
+ |[regnety_160.pycls_in1k](https://huggingface.co/timm/regnety_160.pycls_in1k)|224 |80.288|94.964|83.59 |15.96|23.04 |
208
+ |[regnetx_320.pycls_in1k](https://huggingface.co/timm/regnetx_320.pycls_in1k)|224 |80.246|95.01 |107.81 |31.81|36.3 |
209
+ |[regnety_080.pycls_in1k](https://huggingface.co/timm/regnety_080.pycls_in1k)|224 |79.882|94.834|39.18 |8.0 |17.97 |
210
+ |[regnetz_b16.ra3_in1k](https://huggingface.co/timm/regnetz_b16.ra3_in1k)|224 |79.872|94.974|9.72 |1.45 |9.95 |
211
+ |[regnetx_160.pycls_in1k](https://huggingface.co/timm/regnetx_160.pycls_in1k)|224 |79.862|94.828|54.28 |15.99|25.52 |
212
+ |[regnety_064.pycls_in1k](https://huggingface.co/timm/regnety_064.pycls_in1k)|224 |79.716|94.772|30.58 |6.39 |16.41 |
213
+ |[regnetx_120.pycls_in1k](https://huggingface.co/timm/regnetx_120.pycls_in1k)|224 |79.592|94.738|46.11 |12.13|21.37 |
214
+ |[regnetx_016.tv2_in1k](https://huggingface.co/timm/regnetx_016.tv2_in1k)|224 |79.44 |94.772|9.19 |1.62 |7.93 |
215
+ |[regnety_040.pycls_in1k](https://huggingface.co/timm/regnety_040.pycls_in1k)|224 |79.23 |94.654|20.65 |4.0 |12.29 |
216
+ |[regnetx_080.pycls_in1k](https://huggingface.co/timm/regnetx_080.pycls_in1k)|224 |79.198|94.55 |39.57 |8.02 |14.06 |
217
+ |[regnetx_064.pycls_in1k](https://huggingface.co/timm/regnetx_064.pycls_in1k)|224 |79.064|94.454|26.21 |6.49 |16.37 |
218
+ |[regnety_032.pycls_in1k](https://huggingface.co/timm/regnety_032.pycls_in1k)|224 |78.884|94.412|19.44 |3.2 |11.26 |
219
+ |[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 |
220
+ |[regnetx_040.pycls_in1k](https://huggingface.co/timm/regnetx_040.pycls_in1k)|224 |78.482|94.24 |22.12 |3.99 |12.2 |
221
+ |[regnetx_032.pycls_in1k](https://huggingface.co/timm/regnetx_032.pycls_in1k)|224 |78.178|94.08 |15.3 |3.2 |11.37 |
222
+ |[regnety_016.pycls_in1k](https://huggingface.co/timm/regnety_016.pycls_in1k)|224 |77.862|93.73 |11.2 |1.63 |8.04 |
223
+ |[regnetx_008.tv2_in1k](https://huggingface.co/timm/regnetx_008.tv2_in1k)|224 |77.302|93.672|7.26 |0.81 |5.15 |
224
+ |[regnetx_016.pycls_in1k](https://huggingface.co/timm/regnetx_016.pycls_in1k)|224 |76.908|93.418|9.19 |1.62 |7.93 |
225
+ |[regnety_008.pycls_in1k](https://huggingface.co/timm/regnety_008.pycls_in1k)|224 |76.296|93.05 |6.26 |0.81 |5.25 |
226
+ |[regnety_004.tv2_in1k](https://huggingface.co/timm/regnety_004.tv2_in1k)|224 |75.592|92.712|4.34 |0.41 |3.89 |
227
+ |[regnety_006.pycls_in1k](https://huggingface.co/timm/regnety_006.pycls_in1k)|224 |75.244|92.518|6.06 |0.61 |4.33 |
228
+ |[regnetx_008.pycls_in1k](https://huggingface.co/timm/regnetx_008.pycls_in1k)|224 |75.042|92.342|7.26 |0.81 |5.15 |
229
+ |[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 |
230
+ |[regnety_004.pycls_in1k](https://huggingface.co/timm/regnety_004.pycls_in1k)|224 |74.018|91.764|4.34 |0.41 |3.89 |
231
+ |[regnetx_006.pycls_in1k](https://huggingface.co/timm/regnetx_006.pycls_in1k)|224 |73.862|91.67 |6.2 |0.61 |3.98 |
232
+ |[regnetx_004.pycls_in1k](https://huggingface.co/timm/regnetx_004.pycls_in1k)|224 |72.38 |90.832|5.16 |0.4 |3.14 |
233
+ |[regnety_002.pycls_in1k](https://huggingface.co/timm/regnety_002.pycls_in1k)|224 |70.282|89.534|3.16 |0.2 |2.17 |
234
+ |[regnetx_002.pycls_in1k](https://huggingface.co/timm/regnetx_002.pycls_in1k)|224 |68.752|88.556|2.68 |0.2 |2.16 |
235
+
236
+ ## Citation
237
+ ```bibtex
238
+ @misc{rw2019timm,
239
+ author = {Ross Wightman},
240
+ title = {PyTorch Image Models},
241
+ year = {2019},
242
+ publisher = {GitHub},
243
+ journal = {GitHub repository},
244
+ doi = {10.5281/zenodo.4414861},
245
+ howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
246
+ }
247
+ ```
248
+ ```bibtex
249
+ @InProceedings{Dollar2021,
250
+ title = {Fast and Accurate Model Scaling},
251
+ author = {Piotr Doll{'a}r and Mannat Singh and Ross Girshick},
252
+ booktitle = {CVPR},
253
+ year = {2021}
254
+ }
255
+ ```
256
+ ```bibtex
257
+ @article{liu2020evolving,
258
+ title={Evolving normalization-activation layers},
259
+ author={Liu, Hanxiao and Brock, Andy and Simonyan, Karen and Le, Quoc},
260
+ journal={Advances in Neural Information Processing Systems},
261
+ volume={33},
262
+ pages={13539--13550},
263
+ year={2020}
264
+ }
265
+ ```
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "regnetz_c16_evos",
3
+ "num_classes": 1000,
4
+ "num_features": 1536,
5
+ "pretrained_cfg": {
6
+ "tag": "ch_in1k",
7
+ "custom_load": false,
8
+ "input_size": [
9
+ 3,
10
+ 256,
11
+ 256
12
+ ],
13
+ "test_input_size": [
14
+ 3,
15
+ 320,
16
+ 320
17
+ ],
18
+ "fixed_input_size": false,
19
+ "interpolation": "bicubic",
20
+ "crop_pct": 0.95,
21
+ "crop_mode": "center",
22
+ "mean": [
23
+ 0.5,
24
+ 0.5,
25
+ 0.5
26
+ ],
27
+ "std": [
28
+ 0.5,
29
+ 0.5,
30
+ 0.5
31
+ ],
32
+ "num_classes": 1000,
33
+ "pool_size": [
34
+ 8,
35
+ 8
36
+ ],
37
+ "first_conv": "stem.conv",
38
+ "classifier": "head.fc"
39
+ }
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c48d8f4b036d9cce364d06494fcd728a2a07d1231a51b0e321fd45af79e75ca
3
+ size 53984478
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6e639538eb16419527e653475815eaaa1482cf9eb2a4ab3a19f7f324c47d910
3
+ size 54077853