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
0c0892a
·
verified ·
1 Parent(s): 05e296a

Export model 'vit_relpos_base_patch16_clsgap_224.sw_in1k', on 2025-01-20 18:53:52 JST

Browse files
Files changed (5) hide show
  1. README.md +12 -11
  2. models.parquet +2 -2
  3. vit_relpos_base_patch16_clsgap_224.sw_in1k/meta.json +3 -0
  4. vit_relpos_base_patch16_clsgap_224.sw_in1k/model.onnx +3 -0
  5. vit_relpos_base_patch16_clsgap_224.sw_in1k/preprocess.json +3 -0
README.md CHANGED
@@ -114,7 +114,7 @@ ONNX export version from [TIMM](https://huggingface.co/timm).
114
 
115
  # Models
116
 
117
- 724 models exported from TIMM in total.
118
 
119
  ## Beit
120
 
@@ -1181,16 +1181,17 @@ ONNX export version from [TIMM](https://huggingface.co/timm).
1181
 
1182
  ## VisionTransformerRelPos
1183
 
1184
- 6 models with model class `VisionTransformerRelPos`.
1185
-
1186
- | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
1187
- |:-------------------------------------------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:------------------------|:----------------------------------|:-------------|
1188
- | [vit_relpos_base_patch16_224.sw_in1k](https://huggingface.co/timm/vit_relpos_base_patch16_224.sw_in1k) | 86.4M | 16.8G | 224 | True | 768 | 1000 | imagenet-1k | VisionTransformerRelPos | vit_relpos_base_patch16_224 | 2022-12-23 |
1189
- | [vit_relpos_medium_patch16_cls_224.sw_in1k](https://huggingface.co/timm/vit_relpos_medium_patch16_cls_224.sw_in1k) | 38.8M | 7.5G | 224 | True | 512 | 1000 | imagenet-1k | VisionTransformerRelPos | vit_relpos_medium_patch16_cls_224 | 2022-12-23 |
1190
- | [vit_relpos_medium_patch16_rpn_224.sw_in1k](https://huggingface.co/timm/vit_relpos_medium_patch16_rpn_224.sw_in1k) | 38.7M | 7.5G | 224 | True | 512 | 1000 | imagenet-1k | VisionTransformerRelPos | vit_relpos_medium_patch16_rpn_224 | 2022-12-23 |
1191
- | [vit_relpos_medium_patch16_224.sw_in1k](https://huggingface.co/timm/vit_relpos_medium_patch16_224.sw_in1k) | 38.7M | 7.5G | 224 | True | 512 | 1000 | imagenet-1k | VisionTransformerRelPos | vit_relpos_medium_patch16_224 | 2022-12-23 |
1192
- | [vit_srelpos_medium_patch16_224.sw_in1k](https://huggingface.co/timm/vit_srelpos_medium_patch16_224.sw_in1k) | 38.7M | 7.5G | 224 | True | 512 | 1000 | imagenet-1k | VisionTransformerRelPos | vit_srelpos_medium_patch16_224 | 2022-12-23 |
1193
- | [vit_srelpos_small_patch16_224.sw_in1k](https://huggingface.co/timm/vit_srelpos_small_patch16_224.sw_in1k) | 22.0M | 4.2G | 224 | True | 384 | 1000 | imagenet-1k | VisionTransformerRelPos | vit_srelpos_small_patch16_224 | 2022-12-23 |
 
1194
 
1195
  ## VovNet
1196
 
 
114
 
115
  # Models
116
 
117
+ 725 models exported from TIMM in total.
118
 
119
  ## Beit
120
 
 
1181
 
1182
  ## VisionTransformerRelPos
1183
 
1184
+ 7 models with model class `VisionTransformerRelPos`.
1185
+
1186
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
1187
+ |:---------------------------------------------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:------------------------|:-----------------------------------|:-------------|
1188
+ | [vit_relpos_base_patch16_clsgap_224.sw_in1k](https://huggingface.co/timm/vit_relpos_base_patch16_clsgap_224.sw_in1k) | 86.4M | 16.9G | 224 | True | 768 | 1000 | imagenet-1k | VisionTransformerRelPos | vit_relpos_base_patch16_clsgap_224 | 2022-12-23 |
1189
+ | [vit_relpos_base_patch16_224.sw_in1k](https://huggingface.co/timm/vit_relpos_base_patch16_224.sw_in1k) | 86.4M | 16.8G | 224 | True | 768 | 1000 | imagenet-1k | VisionTransformerRelPos | vit_relpos_base_patch16_224 | 2022-12-23 |
1190
+ | [vit_relpos_medium_patch16_cls_224.sw_in1k](https://huggingface.co/timm/vit_relpos_medium_patch16_cls_224.sw_in1k) | 38.8M | 7.5G | 224 | True | 512 | 1000 | imagenet-1k | VisionTransformerRelPos | vit_relpos_medium_patch16_cls_224 | 2022-12-23 |
1191
+ | [vit_relpos_medium_patch16_rpn_224.sw_in1k](https://huggingface.co/timm/vit_relpos_medium_patch16_rpn_224.sw_in1k) | 38.7M | 7.5G | 224 | True | 512 | 1000 | imagenet-1k | VisionTransformerRelPos | vit_relpos_medium_patch16_rpn_224 | 2022-12-23 |
1192
+ | [vit_relpos_medium_patch16_224.sw_in1k](https://huggingface.co/timm/vit_relpos_medium_patch16_224.sw_in1k) | 38.7M | 7.5G | 224 | True | 512 | 1000 | imagenet-1k | VisionTransformerRelPos | vit_relpos_medium_patch16_224 | 2022-12-23 |
1193
+ | [vit_srelpos_medium_patch16_224.sw_in1k](https://huggingface.co/timm/vit_srelpos_medium_patch16_224.sw_in1k) | 38.7M | 7.5G | 224 | True | 512 | 1000 | imagenet-1k | VisionTransformerRelPos | vit_srelpos_medium_patch16_224 | 2022-12-23 |
1194
+ | [vit_srelpos_small_patch16_224.sw_in1k](https://huggingface.co/timm/vit_srelpos_small_patch16_224.sw_in1k) | 22.0M | 4.2G | 224 | True | 384 | 1000 | imagenet-1k | VisionTransformerRelPos | vit_srelpos_small_patch16_224 | 2022-12-23 |
1195
 
1196
  ## VovNet
1197
 
models.parquet CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67e1e00734553809f6e4722ae18baa2167da98181b30b5acd22fff020bc98528
3
- size 44964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a88caf9fae217d9d0c4927bd511fbefa0039a7e5a214eb449e35b15bb8b309
3
+ size 45031
vit_relpos_base_patch16_clsgap_224.sw_in1k/meta.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf33ce478ab3cfc8960f7c4904c20b0c37137e8329abc63314352b5de905927
3
+ size 169879
vit_relpos_base_patch16_clsgap_224.sw_in1k/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75712d8af3041ac217e436b4cd43d3bc6bb2a896a185c85728a1f1ac04a5e26b
3
+ size 368190082
vit_relpos_base_patch16_clsgap_224.sw_in1k/preprocess.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c033d894bbd7f7cf6880042701e974ed810733c52b2db8b094efeebf78fed2
3
+ size 642