Hugging Face's logo

deepghs
/
timms

Image Classification
ONNX
timm
English
dghs-imgutils
image
dghs-realutils
Model card Files
xet
Community
narugo1992 commited on
Commit
76117de
·
verified ·
1 Parent(s): 338bdbd

Export model 'repvgg_b1.rvgg_in1k', on 2025-01-19 18:09:39 UTC

Browse files
Files changed (5) hide show
  1. README.md +96 -13
  2. models.parquet +2 -2
  3. repvgg_b1.rvgg_in1k/meta.json +3 -0
  4. repvgg_b1.rvgg_in1k/model.onnx +3 -0
  5. repvgg_b1.rvgg_in1k/preprocess.json +3 -0
README.md CHANGED
@@ -10,6 +10,7 @@ base_model:
10
  - timm/mobilevitv2_050.cvnets_in1k
11
  - timm/nextvit_base.bd_in1k
12
  - timm/regnetx_080.tv2_in1k
 
13
  - timm/resnetaa50.a1h_in1k
14
  - timm/vit_base_patch16_clip_384.laion2b_ft_in12k_in1k
15
  - timm/vit_base_r50_s16_384.orig_in21k_ft_in1k
@@ -28,22 +29,104 @@ ONNX export version from [TIMM](https://huggingface.co/timm).
28
 
29
  # Models
30
 
31
- 14 models exported from TIMM in total.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
 
33
  | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
34
  |:-------------------------------------------------------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:------------------|:--------------------------------|:-------------|
35
- | [vit_little_patch16_reg4_gap_256.sbb_in1k](https://huggingface.co/timm/vit_little_patch16_reg4_gap_256.sbb_in1k) | 22.4M | 5.7G | 256 | True | 320 | 1000 | imagenet-1k | VisionTransformer | vit_little_patch16_reg4_gap_256 | 2024-05-10 |
36
- | [nextvit_base.bd_in1k](https://huggingface.co/timm/nextvit_base.bd_in1k) | 44.8M | 8.3G | 224 | True | 1024 | 1000 | imagenet-1k | NextViT | nextvit_base | 2024-02-11 |
37
- | [ghostnetv2_100.in1k](https://huggingface.co/timm/ghostnetv2_100.in1k) | 4.9M | 183.8M | 224 | True | 1280 | 1000 | imagenet-1k | GhostNet | ghostnetv2_100 | 2023-08-20 |
38
- | [efficientvit_b1.r256_in1k](https://huggingface.co/timm/efficientvit_b1.r256_in1k) | 9.1M | 689.0M | 256 | True | 1600 | 1000 | imagenet-1k | EfficientVit | efficientvit_b1 | 2023-08-18 |
39
- | [convformer_m36.sail_in22k_ft_in1k](https://huggingface.co/timm/convformer_m36.sail_in22k_ft_in1k) | 57.0M | 12.8G | 224 | True | 576 | 1000 | imagenet-1k | MetaFormer | convformer_m36 | 2023-05-05 |
40
- | [mobilevitv2_050.cvnets_in1k](https://huggingface.co/timm/mobilevitv2_050.cvnets_in1k) | 1.4M | 464.6M | 256 | True | 256 | 1000 | imagenet-1k | ByobNet | mobilevitv2_050 | 2023-04-24 |
41
- | [convmixer_1024_20_ks9_p14.in1k](https://huggingface.co/timm/convmixer_1024_20_ks9_p14.in1k) | 24.4M | 6.0G | 224 | True | 1024 | 1000 | imagenet-1k | ConvMixer | convmixer_1024_20_ks9_p14 | 2023-04-24 |
42
- | [xcit_small_24_p16_224.fb_in1k](https://huggingface.co/timm/xcit_small_24_p16_224.fb_in1k) | 47.6M | 8.9G | 224 | True | 384 | 1000 | imagenet-1k | Xcit | xcit_small_24_p16_224 | 2023-04-13 |
43
- | [resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k) | 25.6M | 5.2G | 224 | True | 2048 | 1000 | imagenet-1k | ResNet | resnetaa50 | 2023-04-05 |
44
- | [regnetx_080.tv2_in1k](https://huggingface.co/timm/regnetx_080.tv2_in1k) | 39.5M | 8.0G | 224 | True | 1920 | 1000 | imagenet-1k | RegNet | regnetx_080 | 2023-03-21 |
45
- | [convnextv2_atto.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_atto.fcmae_ft_in1k) | 3.7M | 547.3M | 224 | True | 320 | 1000 | imagenet-1k | ConvNeXt | convnextv2_atto | 2023-01-05 |
46
  | [vit_base_r50_s16_384.orig_in21k_ft_in1k](https://huggingface.co/timm/vit_base_r50_s16_384.orig_in21k_ft_in1k) | 86.6M | 49.5G | 384 | True | 768 | 1000 | imagenet-1k | VisionTransformer | vit_base_r50_s16_384 | 2022-12-23 |
47
- | [mobilenetv2_100.ra_in1k](https://huggingface.co/timm/mobilenetv2_100.ra_in1k) | 3.5M | 300.8M | 224 | True | 1280 | 1000 | imagenet-1k | EfficientNet | mobilenetv2_100 | 2022-12-13 |
48
  | [vit_base_patch16_clip_384.laion2b_ft_in12k_in1k](https://huggingface.co/timm/vit_base_patch16_clip_384.laion2b_ft_in12k_in1k) | 86.4M | 49.4G | 384 | True | 768 | 1000 | imagenet-1k | VisionTransformer | vit_base_patch16_clip_384 | 2022-11-11 |
 
 
 
 
 
 
 
 
 
49
 
 
10
  - timm/mobilevitv2_050.cvnets_in1k
11
  - timm/nextvit_base.bd_in1k
12
  - timm/regnetx_080.tv2_in1k
13
+ - timm/repvgg_b1.rvgg_in1k
14
  - timm/resnetaa50.a1h_in1k
15
  - timm/vit_base_patch16_clip_384.laion2b_ft_in12k_in1k
16
  - timm/vit_base_r50_s16_384.orig_in21k_ft_in1k
 
29
 
30
  # Models
31
 
32
+ 15 models exported from TIMM in total.
33
+
34
+ ByobNet
35
+
36
+ 2 models with model class `ByobNet`.
37
+
38
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
39
+ |:---------------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:--------|:----------------|:-------------|
40
+ | [repvgg_b1.rvgg_in1k](https://huggingface.co/timm/repvgg_b1.rvgg_in1k) | 57.3M | 13.1G | 224 | True | 2048 | 1000 | imagenet-1k | ByobNet | repvgg_b1 | 2023-03-22 |
41
+ | [mobilevitv2_050.cvnets_in1k](https://huggingface.co/timm/mobilevitv2_050.cvnets_in1k) | 1.4M | 464.6M | 256 | True | 256 | 1000 | imagenet-1k | ByobNet | mobilevitv2_050 | 2023-04-24 |
42
+
43
+ ConvMixer
44
+
45
+ 1 model with model class `ConvMixer`.
46
+
47
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
48
+ |:---------------------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:----------|:--------------------------|:-------------|
49
+ | [convmixer_1024_20_ks9_p14.in1k](https://huggingface.co/timm/convmixer_1024_20_ks9_p14.in1k) | 24.4M | 6.0G | 224 | True | 1024 | 1000 | imagenet-1k | ConvMixer | convmixer_1024_20_ks9_p14 | 2023-04-24 |
50
+
51
+ ConvNeXt
52
+
53
+ 1 model with model class `ConvNeXt`.
54
+
55
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
56
+ |:-------------------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:---------|:----------------|:-------------|
57
+ | [convnextv2_atto.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_atto.fcmae_ft_in1k) | 3.7M | 547.3M | 224 | True | 320 | 1000 | imagenet-1k | ConvNeXt | convnextv2_atto | 2023-01-05 |
58
+
59
+ EfficientNet
60
+
61
+ 1 model with model class `EfficientNet`.
62
+
63
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
64
+ |:-------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:-------------|:----------------|:-------------|
65
+ | [mobilenetv2_100.ra_in1k](https://huggingface.co/timm/mobilenetv2_100.ra_in1k) | 3.5M | 300.8M | 224 | True | 1280 | 1000 | imagenet-1k | EfficientNet | mobilenetv2_100 | 2022-12-13 |
66
+
67
+ EfficientVit
68
+
69
+ 1 model with model class `EfficientVit`.
70
+
71
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
72
+ |:-----------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:-------------|:----------------|:-------------|
73
+ | [efficientvit_b1.r256_in1k](https://huggingface.co/timm/efficientvit_b1.r256_in1k) | 9.1M | 689.0M | 256 | True | 1600 | 1000 | imagenet-1k | EfficientVit | efficientvit_b1 | 2023-08-18 |
74
+
75
+ GhostNet
76
+
77
+ 1 model with model class `GhostNet`.
78
+
79
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
80
+ |:-----------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:---------|:---------------|:-------------|
81
+ | [ghostnetv2_100.in1k](https://huggingface.co/timm/ghostnetv2_100.in1k) | 4.9M | 183.8M | 224 | True | 1280 | 1000 | imagenet-1k | GhostNet | ghostnetv2_100 | 2023-08-20 |
82
+
83
+ MetaFormer
84
+
85
+ 1 model with model class `MetaFormer`.
86
+
87
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
88
+ |:---------------------------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:-----------|:---------------|:-------------|
89
+ | [convformer_m36.sail_in22k_ft_in1k](https://huggingface.co/timm/convformer_m36.sail_in22k_ft_in1k) | 57.0M | 12.8G | 224 | True | 576 | 1000 | imagenet-1k | MetaFormer | convformer_m36 | 2023-05-05 |
90
+
91
+ NextViT
92
+
93
+ 1 model with model class `NextViT`.
94
+
95
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
96
+ |:-------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:--------|:---------------|:-------------|
97
+ | [nextvit_base.bd_in1k](https://huggingface.co/timm/nextvit_base.bd_in1k) | 44.8M | 8.3G | 224 | True | 1024 | 1000 | imagenet-1k | NextViT | nextvit_base | 2024-02-11 |
98
+
99
+ RegNet
100
+
101
+ 1 model with model class `RegNet`.
102
+
103
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
104
+ |:-------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:--------|:---------------|:-------------|
105
+ | [regnetx_080.tv2_in1k](https://huggingface.co/timm/regnetx_080.tv2_in1k) | 39.5M | 8.0G | 224 | True | 1920 | 1000 | imagenet-1k | RegNet | regnetx_080 | 2023-03-21 |
106
+
107
+ ResNet
108
+
109
+ 1 model with model class `ResNet`.
110
+
111
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
112
+ |:-----------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:--------|:---------------|:-------------|
113
+ | [resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k) | 25.6M | 5.2G | 224 | True | 2048 | 1000 | imagenet-1k | ResNet | resnetaa50 | 2023-04-05 |
114
+
115
+ VisionTransformer
116
+
117
+ 3 models with model class `VisionTransformer`.
118
 
119
  | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
120
  |:-------------------------------------------------------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:------------------|:--------------------------------|:-------------|
 
 
 
 
 
 
 
 
 
 
 
121
  | [vit_base_r50_s16_384.orig_in21k_ft_in1k](https://huggingface.co/timm/vit_base_r50_s16_384.orig_in21k_ft_in1k) | 86.6M | 49.5G | 384 | True | 768 | 1000 | imagenet-1k | VisionTransformer | vit_base_r50_s16_384 | 2022-12-23 |
 
122
  | [vit_base_patch16_clip_384.laion2b_ft_in12k_in1k](https://huggingface.co/timm/vit_base_patch16_clip_384.laion2b_ft_in12k_in1k) | 86.4M | 49.4G | 384 | True | 768 | 1000 | imagenet-1k | VisionTransformer | vit_base_patch16_clip_384 | 2022-11-11 |
123
+ | [vit_little_patch16_reg4_gap_256.sbb_in1k](https://huggingface.co/timm/vit_little_patch16_reg4_gap_256.sbb_in1k) | 22.4M | 5.7G | 256 | True | 320 | 1000 | imagenet-1k | VisionTransformer | vit_little_patch16_reg4_gap_256 | 2024-05-10 |
124
+
125
+ Xcit
126
+
127
+ 1 model with model class `Xcit`.
128
+
129
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
130
+ |:-------------------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:--------|:----------------------|:-------------|
131
+ | [xcit_small_24_p16_224.fb_in1k](https://huggingface.co/timm/xcit_small_24_p16_224.fb_in1k) | 47.6M | 8.9G | 224 | True | 384 | 1000 | imagenet-1k | Xcit | xcit_small_24_p16_224 | 2023-04-13 |
132
 
models.parquet CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2c2e4e4a46e94ffbe86b2b67e0f709d9994c18f0255268f22ade77081a75954
3
- size 9338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4209625aee68a55dbaa321f480e484f48a2a9331ea02dbfdb98a884d6e1734f2
3
+ size 9397
repvgg_b1.rvgg_in1k/meta.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19f3e397cd44e7054056057c87da68dda5bb8745583e06ae3c5967a8f67e3303
3
+ size 169793
repvgg_b1.rvgg_in1k/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:494f0ea4fd11d5454a1ee8c253c2c9cb7f13059919dfe799514cee58d4fce14d
3
+ size 229707260
repvgg_b1.rvgg_in1k/preprocess.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6abb43a6abcd1556f46dcb1b8605bb3c121fb3d91a10e384e0f737a9d92bd254
3
+ size 735