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
c54f572
·
verified ·
1 Parent(s): c4d7899

Export model 'vit_betwixt_patch16_reg1_gap_256.sbb_in1k', on 2025-01-19 18:18:48 UTC

Browse files
Files changed (5) hide show
  1. README.md +9 -7
  2. models.parquet +2 -2
  3. vit_betwixt_patch16_reg1_gap_256.sbb_in1k/meta.json +3 -0
  4. vit_betwixt_patch16_reg1_gap_256.sbb_in1k/model.onnx +3 -0
  5. vit_betwixt_patch16_reg1_gap_256.sbb_in1k/preprocess.json +3 -0
README.md CHANGED
@@ -33,6 +33,7 @@ base_model:
33
  - timm/swin_base_patch4_window7_224.ms_in1k
34
  - timm/vit_base_patch16_clip_384.laion2b_ft_in12k_in1k
35
  - timm/vit_base_r50_s16_384.orig_in21k_ft_in1k
 
36
  - timm/vit_little_patch16_reg4_gap_256.sbb_in1k
37
  - timm/xcit_small_24_p16_224.fb_in1k
38
  language:
@@ -48,7 +49,7 @@ ONNX export version from [TIMM](https://huggingface.co/timm).
48
 
49
  # Models
50
 
51
- 34 models exported from TIMM in total.
52
 
53
  ## ByobNet
54
 
@@ -208,13 +209,14 @@ ONNX export version from [TIMM](https://huggingface.co/timm).
208
 
209
  ## VisionTransformer
210
 
211
- 3 models with model class `VisionTransformer`.
212
 
213
- | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
214
- |:-------------------------------------------------------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:------------------|:--------------------------------|:-------------|
215
- | [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 |
216
- | [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 |
217
- | [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 |
 
218
 
219
  ## Xcit
220
 
 
33
  - timm/swin_base_patch4_window7_224.ms_in1k
34
  - timm/vit_base_patch16_clip_384.laion2b_ft_in12k_in1k
35
  - timm/vit_base_r50_s16_384.orig_in21k_ft_in1k
36
+ - timm/vit_betwixt_patch16_reg1_gap_256.sbb_in1k
37
  - timm/vit_little_patch16_reg4_gap_256.sbb_in1k
38
  - timm/xcit_small_24_p16_224.fb_in1k
39
  language:
 
49
 
50
  # Models
51
 
52
+ 35 models exported from TIMM in total.
53
 
54
  ## ByobNet
55
 
 
209
 
210
  ## VisionTransformer
211
 
212
+ 4 models with model class `VisionTransformer`.
213
 
214
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
215
+ |:-------------------------------------------------------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:------------------|:---------------------------------|:-------------|
216
+ | [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 |
217
+ | [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 |
218
+ | [vit_betwixt_patch16_reg1_gap_256.sbb_in1k](https://huggingface.co/timm/vit_betwixt_patch16_reg1_gap_256.sbb_in1k) | 60.2M | 15.3G | 256 | True | 640 | 1000 | imagenet-1k | VisionTransformer | vit_betwixt_patch16_reg1_gap_256 | 2024-05-10 |
219
+ | [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 |
220
 
221
  ## Xcit
222
 
models.parquet CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5a63a9abebca224e180d01c20aa37d7651d4571a59f58528981d15ad4496134
3
- size 11008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e47009cff6811b7021528c4db57473dbb88ab5e25f559eb4f4f7eca45928b151
3
+ size 11079
vit_betwixt_patch16_reg1_gap_256.sbb_in1k/meta.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37031121afc0192d1b80c9c786f8b1e94e94f00aea659d99bc6cd901fb3afaf8
3
+ size 169869
vit_betwixt_patch16_reg1_gap_256.sbb_in1k/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1767f01ad12f3f449a330b4e06f2a7de1521549bd9580fe4d91b5d82c41e2681
3
+ size 241817422
vit_betwixt_patch16_reg1_gap_256.sbb_in1k/preprocess.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c3ceed99ae49aa023c8c7cbc224be5ba023f409004ac0091862f1e398d784e
3
+ size 642