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
162b73a
·
verified ·
1 Parent(s): 6dada05

Export model 'vit_base_patch16_clip_224.laion2b_ft_in12k', on 2025-01-20 04:35:44 UTC

Browse files
Files changed (5) hide show
  1. README.md +21 -20
  2. models.parquet +2 -2
  3. vit_base_patch16_clip_224.laion2b_ft_in12k/meta.json +3 -0
  4. vit_base_patch16_clip_224.laion2b_ft_in12k/model.onnx +3 -0
  5. vit_base_patch16_clip_224.laion2b_ft_in12k/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
- 152 models exported from TIMM in total.
118
 
119
  ## ByobNet
120
 
@@ -507,25 +507,26 @@ ONNX export version from [TIMM](https://huggingface.co/timm).
507
 
508
  ## VisionTransformer
509
 
510
- 15 models with model class `VisionTransformer`.
511
-
512
- | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
513
- |:-------------------------------------------------------------------------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:------------|:------------------|:---------------------------------|:-------------|
514
- | [vit_base_patch14_reg4_dinov2.lvd142m](https://huggingface.co/timm/vit_base_patch14_reg4_dinov2.lvd142m) | 85.5M | 117.4G | 518 | False | 768 | 768 | | VisionTransformer | vit_base_patch14_reg4_dinov2 | 2023-10-30 |
515
- | [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 |
516
- | [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 |
517
- | [vit_base_patch16_clip_384.laion2b_ft_in1k](https://huggingface.co/timm/vit_base_patch16_clip_384.laion2b_ft_in1k) | 86.4M | 49.4G | 384 | True | 768 | 1000 | imagenet-1k | VisionTransformer | vit_base_patch16_clip_384 | 2022-11-09 |
518
- | [vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k](https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k) | 64.0M | 36.8G | 384 | True | 512 | 1000 | imagenet-1k | VisionTransformer | vit_mediumd_patch16_reg4_gap_384 | 2024-08-21 |
519
- | [vit_medium_patch16_gap_384.sw_in12k_ft_in1k](https://huggingface.co/timm/vit_medium_patch16_gap_384.sw_in12k_ft_in1k) | 38.7M | 22.0G | 384 | True | 512 | 1000 | imagenet-1k | VisionTransformer | vit_medium_patch16_gap_384 | 2022-12-02 |
520
- | [vit_base_patch16_224.orig_in21k](https://huggingface.co/timm/vit_base_patch16_224.orig_in21k) | 85.6M | 16.9G | 224 | False | 768 | 768 | | VisionTransformer | vit_base_patch16_224 | 2023-11-16 |
521
- | [vit_base_patch16_rpn_224.sw_in1k](https://huggingface.co/timm/vit_base_patch16_rpn_224.sw_in1k) | 86.4M | 16.8G | 224 | True | 768 | 1000 | imagenet-1k | VisionTransformer | vit_base_patch16_rpn_224 | 2022-12-22 |
522
- | [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 |
523
- | [vit_base_patch32_clip_384.laion2b_ft_in12k_in1k](https://huggingface.co/timm/vit_base_patch32_clip_384.laion2b_ft_in12k_in1k) | 88.2M | 12.7G | 384 | True | 768 | 1000 | imagenet-1k | VisionTransformer | vit_base_patch32_clip_384 | 2022-11-05 |
524
- | [vit_small_patch16_384.augreg_in1k](https://huggingface.co/timm/vit_small_patch16_384.augreg_in1k) | 22.0M | 12.4G | 384 | True | 384 | 1000 | imagenet-1k | VisionTransformer | vit_small_patch16_384 | 2022-12-22 |
525
- | [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 |
526
- | [vit_little_patch16_reg1_gap_256.sbb_in12k_ft_in1k](https://huggingface.co/timm/vit_little_patch16_reg1_gap_256.sbb_in12k_ft_in1k) | 22.4M | 5.7G | 256 | True | 320 | 1000 | imagenet-1k | VisionTransformer | vit_little_patch16_reg1_gap_256 | 2024-05-27 |
527
- | [flexivit_small.1200ep_in1k](https://huggingface.co/timm/flexivit_small.1200ep_in1k) | 22.0M | 4.9G | 240 | True | 384 | 1000 | imagenet-1k | VisionTransformer | flexivit_small | 2022-12-22 |
528
- | [flexivit_small.600ep_in1k](https://huggingface.co/timm/flexivit_small.600ep_in1k) | 22.0M | 4.9G | 240 | True | 384 | 1000 | imagenet-1k | VisionTransformer | flexivit_small | 2022-12-22 |
 
529
 
530
  ## VovNet
531
 
 
114
 
115
  # Models
116
 
117
+ 153 models exported from TIMM in total.
118
 
119
  ## ByobNet
120
 
 
507
 
508
  ## VisionTransformer
509
 
510
+ 16 models with model class `VisionTransformer`.
511
+
512
+ | Name | Params | Flops | Input Size | Can Classify | Features | Classes | Dataset | Model | Architecture | Created At |
513
+ |:-------------------------------------------------------------------------------------------------------------------------------------------------|:---------|:--------|-------------:|:---------------|-----------:|----------:|:-------------|:------------------|:---------------------------------|:-------------|
514
+ | [vit_base_patch14_reg4_dinov2.lvd142m](https://huggingface.co/timm/vit_base_patch14_reg4_dinov2.lvd142m) | 85.5M | 117.4G | 518 | False | 768 | 768 | | VisionTransformer | vit_base_patch14_reg4_dinov2 | 2023-10-30 |
515
+ | [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 |
516
+ | [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 |
517
+ | [vit_base_patch16_clip_384.laion2b_ft_in1k](https://huggingface.co/timm/vit_base_patch16_clip_384.laion2b_ft_in1k) | 86.4M | 49.4G | 384 | True | 768 | 1000 | imagenet-1k | VisionTransformer | vit_base_patch16_clip_384 | 2022-11-09 |
518
+ | [vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k](https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k) | 64.0M | 36.8G | 384 | True | 512 | 1000 | imagenet-1k | VisionTransformer | vit_mediumd_patch16_reg4_gap_384 | 2024-08-21 |
519
+ | [vit_medium_patch16_gap_384.sw_in12k_ft_in1k](https://huggingface.co/timm/vit_medium_patch16_gap_384.sw_in12k_ft_in1k) | 38.7M | 22.0G | 384 | True | 512 | 1000 | imagenet-1k | VisionTransformer | vit_medium_patch16_gap_384 | 2022-12-02 |
520
+ | [vit_base_patch16_clip_224.laion2b_ft_in12k](https://huggingface.co/timm/vit_base_patch16_clip_224.laion2b_ft_in12k) | 94.7M | 16.9G | 224 | True | 768 | 11821 | imagenet-12k | VisionTransformer | vit_base_patch16_clip_224 | 2022-11-09 |
521
+ | [vit_base_patch16_224.orig_in21k](https://huggingface.co/timm/vit_base_patch16_224.orig_in21k) | 85.6M | 16.9G | 224 | False | 768 | 768 | | VisionTransformer | vit_base_patch16_224 | 2023-11-16 |
522
+ | [vit_base_patch16_rpn_224.sw_in1k](https://huggingface.co/timm/vit_base_patch16_rpn_224.sw_in1k) | 86.4M | 16.8G | 224 | True | 768 | 1000 | imagenet-1k | VisionTransformer | vit_base_patch16_rpn_224 | 2022-12-22 |
523
+ | [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 |
524
+ | [vit_base_patch32_clip_384.laion2b_ft_in12k_in1k](https://huggingface.co/timm/vit_base_patch32_clip_384.laion2b_ft_in12k_in1k) | 88.2M | 12.7G | 384 | True | 768 | 1000 | imagenet-1k | VisionTransformer | vit_base_patch32_clip_384 | 2022-11-05 |
525
+ | [vit_small_patch16_384.augreg_in1k](https://huggingface.co/timm/vit_small_patch16_384.augreg_in1k) | 22.0M | 12.4G | 384 | True | 384 | 1000 | imagenet-1k | VisionTransformer | vit_small_patch16_384 | 2022-12-22 |
526
+ | [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 |
527
+ | [vit_little_patch16_reg1_gap_256.sbb_in12k_ft_in1k](https://huggingface.co/timm/vit_little_patch16_reg1_gap_256.sbb_in12k_ft_in1k) | 22.4M | 5.7G | 256 | True | 320 | 1000 | imagenet-1k | VisionTransformer | vit_little_patch16_reg1_gap_256 | 2024-05-27 |
528
+ | [flexivit_small.1200ep_in1k](https://huggingface.co/timm/flexivit_small.1200ep_in1k) | 22.0M | 4.9G | 240 | True | 384 | 1000 | imagenet-1k | VisionTransformer | flexivit_small | 2022-12-22 |
529
+ | [flexivit_small.600ep_in1k](https://huggingface.co/timm/flexivit_small.600ep_in1k) | 22.0M | 4.9G | 240 | True | 384 | 1000 | imagenet-1k | VisionTransformer | flexivit_small | 2022-12-22 |
530
 
531
  ## VovNet
532
 
models.parquet CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9be4322184b594d28726f93235d2f93b17870adbcceea7ead1688ee5644bb55
3
- size 18467
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a2cec1c7cd3d45cba1819fa9aba3d332180d6e80dbcf204f0fd5bbb906e076e
3
+ size 18558
vit_base_patch16_clip_224.laion2b_ft_in12k/meta.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2a65d1193a9d8f62d7e14cd89d02f1b3ccfcf3087f390c6e2bb761d0b4dd96a
3
+ size 2015430
vit_base_patch16_clip_224.laion2b_ft_in12k/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81be21728140ec150c50d7b1c043e97ceb85b4b4d49bf7bbd479713bc49aac2f
3
+ size 379732579
vit_base_patch16_clip_224.laion2b_ft_in12k/preprocess.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574b771c20861320cb80c928011fd91d4b6bda6830376ee87b045e2191b1bf4c
3
+ size 736