Hugging Face's logo

zeromodels
/
convnext_large_fb_in22k

Image Classification
Keras
PyTorch
JAX
TensorFlow
zeromodels
convnext
backbone
Model card Files
xet
 Community
IMvision12 commited on
Commit
c84e084
·
verified ·
1 Parent(s): 0c86d29

Migrate to zeromodels (rename kf_*.json -> zm_*.json, fix refs in config + README, ensure tag + badge)

Browse files
Files changed (2) hide show
  1. README.md +36 -36
  2. kf_config.json → zm_config.json +26 -26
README.md CHANGED
@@ -2,10 +2,10 @@
2
  pipeline_tag: image-classification
3
  license: apache-2.0
4
  base_model: timm/convnext_large.fb_in22k
5
- library_name: kerasformers
6
  tags:
7
  - keras
8
- - kerasformers
9
  - image-classification
10
  - convnext
11
  - backbone
@@ -15,13 +15,13 @@ tags:
15
  - tf
16
  ---
17
 
18
- ## ***See [our collection](https://huggingface.co/collections/kerasformers/convnext-6a6bd0f2a94679977d564d48) for all versions of ConvNeXt.***
19
 
20
  # Run ConvNeXt with Keras 3: JAX, PyTorch, or TensorFlow
21
 
22
- [![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-black?logo=github)](https://github.com/IMvision12/KerasFormers) [![Docs](https://img.shields.io/badge/Docs-ConvNeXt-blue)](https://imvision12.github.io/KerasFormers/classification_backbones/) [![Collection](https://img.shields.io/badge/HF-ConvNeXt%20collection-yellow)](https://huggingface.co/collections/kerasformers/convnext-6a6bd0f2a94679977d564d48)
23
 
24
- # kerasformers/convnext_large_fb_in22k
25
 
26
  Paper: [A ConvNet for the 2020s (arXiv:2201.03545)](https://arxiv.org/abs/2201.03545) · [HF Papers](https://huggingface.co/papers/2201.03545)
27
 
@@ -29,7 +29,7 @@ ConvNeXt modernizes a ResNet-style CNN with ViT-inspired design choices. Use as
29
 
30
  For more details on the model, please go to the upstream [model card](https://huggingface.co/timm/convnext_large.fb_in22k).
31
 
32
- Pure-**Keras 3** conversion of [`timm/convnext_large.fb_in22k`](https://huggingface.co/timm/convnext_large.fb_in22k) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
33
 
34
  This is an **image-classification / backbone** checkpoint (`ConvNeXtImageClassify` / `ConvNeXtModel`).
35
 
@@ -41,11 +41,11 @@ os.environ["KERAS_BACKEND"] = "torch" # or "jax" / "tensorflow"
41
 
42
  from PIL import Image
43
  import numpy as np
44
- from kerasformers.models.convnext import ConvNeXtImageClassify, ConvNeXtModel
45
 
46
- model = ConvNeXtImageClassify.from_weights("kerasformers/convnext_large_fb_in22k")
47
  backbone = ConvNeXtModel.from_weights(
48
- "kerasformers/convnext_large_fb_in22k", as_backbone=True
49
  )
50
 
51
  image = Image.open("your_image.jpg").convert("RGB")
@@ -56,40 +56,40 @@ feats = backbone(x)
56
  print(len(feats), [tuple(f.shape) for f in feats])
57
  ```
58
 
59
- Load any ConvNeXt variant the same way with `from_weights("kerasformers/<variant>")`:
60
 
61
  | Variant | Hub |
62
  |---|---|
63
- | `convnext_atto_d2_in1k` | [`kerasformers/convnext_atto_d2_in1k`](https://huggingface.co/kerasformers/convnext_atto_d2_in1k) |
64
- | `convnext_base_fb_in1k` | [`kerasformers/convnext_base_fb_in1k`](https://huggingface.co/kerasformers/convnext_base_fb_in1k) |
65
- | `convnext_base_fb_in22k` | [`kerasformers/convnext_base_fb_in22k`](https://huggingface.co/kerasformers/convnext_base_fb_in22k) |
66
- | `convnext_base_fb_in22k_ft_in1k` | [`kerasformers/convnext_base_fb_in22k_ft_in1k`](https://huggingface.co/kerasformers/convnext_base_fb_in22k_ft_in1k) |
67
- | `convnext_base_fb_in22k_ft_in1k_384` | [`kerasformers/convnext_base_fb_in22k_ft_in1k_384`](https://huggingface.co/kerasformers/convnext_base_fb_in22k_ft_in1k_384) |
68
- | `convnext_femto_d1_in1k` | [`kerasformers/convnext_femto_d1_in1k`](https://huggingface.co/kerasformers/convnext_femto_d1_in1k) |
69
- | `convnext_large_fb_in1k` | [`kerasformers/convnext_large_fb_in1k`](https://huggingface.co/kerasformers/convnext_large_fb_in1k) |
70
- | `convnext_large_fb_in22k` | [`kerasformers/convnext_large_fb_in22k`](https://huggingface.co/kerasformers/convnext_large_fb_in22k) |
71
- | `convnext_large_fb_in22k_ft_in1k` | [`kerasformers/convnext_large_fb_in22k_ft_in1k`](https://huggingface.co/kerasformers/convnext_large_fb_in22k_ft_in1k) |
72
- | `convnext_large_fb_in22k_ft_in1k_384` | [`kerasformers/convnext_large_fb_in22k_ft_in1k_384`](https://huggingface.co/kerasformers/convnext_large_fb_in22k_ft_in1k_384) |
73
- | `convnext_nano_d1h_in1k` | [`kerasformers/convnext_nano_d1h_in1k`](https://huggingface.co/kerasformers/convnext_nano_d1h_in1k) |
74
- | `convnext_nano_in12k_ft_in1k` | [`kerasformers/convnext_nano_in12k_ft_in1k`](https://huggingface.co/kerasformers/convnext_nano_in12k_ft_in1k) |
75
- | `convnext_pico_d1_in1k` | [`kerasformers/convnext_pico_d1_in1k`](https://huggingface.co/kerasformers/convnext_pico_d1_in1k) |
76
- | `convnext_small_fb_in1k` | [`kerasformers/convnext_small_fb_in1k`](https://huggingface.co/kerasformers/convnext_small_fb_in1k) |
77
- | `convnext_small_fb_in22k` | [`kerasformers/convnext_small_fb_in22k`](https://huggingface.co/kerasformers/convnext_small_fb_in22k) |
78
- | `convnext_small_fb_in22k_ft_in1k` | [`kerasformers/convnext_small_fb_in22k_ft_in1k`](https://huggingface.co/kerasformers/convnext_small_fb_in22k_ft_in1k) |
79
- | `convnext_small_fb_in22k_ft_in1k_384` | [`kerasformers/convnext_small_fb_in22k_ft_in1k_384`](https://huggingface.co/kerasformers/convnext_small_fb_in22k_ft_in1k_384) |
80
- | `convnext_tiny_fb_in1k` | [`kerasformers/convnext_tiny_fb_in1k`](https://huggingface.co/kerasformers/convnext_tiny_fb_in1k) |
81
- | `convnext_tiny_fb_in22k` | [`kerasformers/convnext_tiny_fb_in22k`](https://huggingface.co/kerasformers/convnext_tiny_fb_in22k) |
82
- | `convnext_tiny_fb_in22k_ft_in1k` | [`kerasformers/convnext_tiny_fb_in22k_ft_in1k`](https://huggingface.co/kerasformers/convnext_tiny_fb_in22k_ft_in1k) |
83
- | `convnext_tiny_fb_in22k_ft_in1k_384` | [`kerasformers/convnext_tiny_fb_in22k_ft_in1k_384`](https://huggingface.co/kerasformers/convnext_tiny_fb_in22k_ft_in1k_384) |
84
- | `convnext_xlarge_fb_in22k` | [`kerasformers/convnext_xlarge_fb_in22k`](https://huggingface.co/kerasformers/convnext_xlarge_fb_in22k) |
85
- | `convnext_xlarge_fb_in22k_ft_in1k` | [`kerasformers/convnext_xlarge_fb_in22k_ft_in1k`](https://huggingface.co/kerasformers/convnext_xlarge_fb_in22k_ft_in1k) |
86
- | `convnext_xlarge_fb_in22k_ft_in1k_384` | [`kerasformers/convnext_xlarge_fb_in22k_ft_in1k_384`](https://huggingface.co/kerasformers/convnext_xlarge_fb_in22k_ft_in1k_384) |
87
 
88
  ## Tips
89
 
90
- - Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
91
  - `ConvNeXtImageClassify` returns class logits; `ConvNeXtModel` returns features (`as_backbone=True` for multi-scale stages).
92
- - See [docs](https://imvision12.github.io/KerasFormers/classification_backbones/) and [Loading Weights](https://imvision12.github.io/KerasFormers/loading_weights/).
93
  - Upstream / timm checkpoints: `ConvNeXtImageClassify.from_weights("hf:timm/convnext_large.fb_in22k")`.
94
 
95
  ## Special Thanks
 
2
  pipeline_tag: image-classification
3
  license: apache-2.0
4
  base_model: timm/convnext_large.fb_in22k
5
+ library_name: zeromodels
6
  tags:
7
  - keras
8
+ - zeromodels
9
  - image-classification
10
  - convnext
11
  - backbone
 
15
  - tf
16
  ---
17
 
18
+ ## ***See [our collection](https://huggingface.co/collections/zeromodels/convnext-6a6bd0f2a94679977d564d48) for all versions of ConvNeXt.***
19
 
20
  # Run ConvNeXt with Keras 3: JAX, PyTorch, or TensorFlow
21
 
22
+ [![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-black?logo=github)](https://github.com/IMvision12/ZeroModels) [![Docs](https://img.shields.io/badge/Docs-ConvNeXt-blue)](https://imvision12.github.io/ZeroModels/classification_backbones/) [![Collection](https://img.shields.io/badge/HF-ConvNeXt%20collection-yellow)](https://huggingface.co/collections/zeromodels/convnext-6a6bd0f2a94679977d564d48)
23
 
24
+ # zeromodels/convnext_large_fb_in22k
25
 
26
  Paper: [A ConvNet for the 2020s (arXiv:2201.03545)](https://arxiv.org/abs/2201.03545) · [HF Papers](https://huggingface.co/papers/2201.03545)
27
 
 
29
 
30
  For more details on the model, please go to the upstream [model card](https://huggingface.co/timm/convnext_large.fb_in22k).
31
 
32
+ Pure-**Keras 3** conversion of [`timm/convnext_large.fb_in22k`](https://huggingface.co/timm/convnext_large.fb_in22k) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
33
 
34
  This is an **image-classification / backbone** checkpoint (`ConvNeXtImageClassify` / `ConvNeXtModel`).
35
 
 
41
 
42
  from PIL import Image
43
  import numpy as np
44
+ from zeromodels.models.convnext import ConvNeXtImageClassify, ConvNeXtModel
45
 
46
+ model = ConvNeXtImageClassify.from_weights("zeromodels/convnext_large_fb_in22k")
47
  backbone = ConvNeXtModel.from_weights(
48
+ "zeromodels/convnext_large_fb_in22k", as_backbone=True
49
  )
50
 
51
  image = Image.open("your_image.jpg").convert("RGB")
 
56
  print(len(feats), [tuple(f.shape) for f in feats])
57
  ```
58
 
59
+ Load any ConvNeXt variant the same way with `from_weights("zeromodels/<variant>")`:
60
 
61
  | Variant | Hub |
62
  |---|---|
63
+ | `convnext_atto_d2_in1k` | [`zeromodels/convnext_atto_d2_in1k`](https://huggingface.co/zeromodels/convnext_atto_d2_in1k) |
64
+ | `convnext_base_fb_in1k` | [`zeromodels/convnext_base_fb_in1k`](https://huggingface.co/zeromodels/convnext_base_fb_in1k) |
65
+ | `convnext_base_fb_in22k` | [`zeromodels/convnext_base_fb_in22k`](https://huggingface.co/zeromodels/convnext_base_fb_in22k) |
66
+ | `convnext_base_fb_in22k_ft_in1k` | [`zeromodels/convnext_base_fb_in22k_ft_in1k`](https://huggingface.co/zeromodels/convnext_base_fb_in22k_ft_in1k) |
67
+ | `convnext_base_fb_in22k_ft_in1k_384` | [`zeromodels/convnext_base_fb_in22k_ft_in1k_384`](https://huggingface.co/zeromodels/convnext_base_fb_in22k_ft_in1k_384) |
68
+ | `convnext_femto_d1_in1k` | [`zeromodels/convnext_femto_d1_in1k`](https://huggingface.co/zeromodels/convnext_femto_d1_in1k) |
69
+ | `convnext_large_fb_in1k` | [`zeromodels/convnext_large_fb_in1k`](https://huggingface.co/zeromodels/convnext_large_fb_in1k) |
70
+ | `convnext_large_fb_in22k` | [`zeromodels/convnext_large_fb_in22k`](https://huggingface.co/zeromodels/convnext_large_fb_in22k) |
71
+ | `convnext_large_fb_in22k_ft_in1k` | [`zeromodels/convnext_large_fb_in22k_ft_in1k`](https://huggingface.co/zeromodels/convnext_large_fb_in22k_ft_in1k) |
72
+ | `convnext_large_fb_in22k_ft_in1k_384` | [`zeromodels/convnext_large_fb_in22k_ft_in1k_384`](https://huggingface.co/zeromodels/convnext_large_fb_in22k_ft_in1k_384) |
73
+ | `convnext_nano_d1h_in1k` | [`zeromodels/convnext_nano_d1h_in1k`](https://huggingface.co/zeromodels/convnext_nano_d1h_in1k) |
74
+ | `convnext_nano_in12k_ft_in1k` | [`zeromodels/convnext_nano_in12k_ft_in1k`](https://huggingface.co/zeromodels/convnext_nano_in12k_ft_in1k) |
75
+ | `convnext_pico_d1_in1k` | [`zeromodels/convnext_pico_d1_in1k`](https://huggingface.co/zeromodels/convnext_pico_d1_in1k) |
76
+ | `convnext_small_fb_in1k` | [`zeromodels/convnext_small_fb_in1k`](https://huggingface.co/zeromodels/convnext_small_fb_in1k) |
77
+ | `convnext_small_fb_in22k` | [`zeromodels/convnext_small_fb_in22k`](https://huggingface.co/zeromodels/convnext_small_fb_in22k) |
78
+ | `convnext_small_fb_in22k_ft_in1k` | [`zeromodels/convnext_small_fb_in22k_ft_in1k`](https://huggingface.co/zeromodels/convnext_small_fb_in22k_ft_in1k) |
79
+ | `convnext_small_fb_in22k_ft_in1k_384` | [`zeromodels/convnext_small_fb_in22k_ft_in1k_384`](https://huggingface.co/zeromodels/convnext_small_fb_in22k_ft_in1k_384) |
80
+ | `convnext_tiny_fb_in1k` | [`zeromodels/convnext_tiny_fb_in1k`](https://huggingface.co/zeromodels/convnext_tiny_fb_in1k) |
81
+ | `convnext_tiny_fb_in22k` | [`zeromodels/convnext_tiny_fb_in22k`](https://huggingface.co/zeromodels/convnext_tiny_fb_in22k) |
82
+ | `convnext_tiny_fb_in22k_ft_in1k` | [`zeromodels/convnext_tiny_fb_in22k_ft_in1k`](https://huggingface.co/zeromodels/convnext_tiny_fb_in22k_ft_in1k) |
83
+ | `convnext_tiny_fb_in22k_ft_in1k_384` | [`zeromodels/convnext_tiny_fb_in22k_ft_in1k_384`](https://huggingface.co/zeromodels/convnext_tiny_fb_in22k_ft_in1k_384) |
84
+ | `convnext_xlarge_fb_in22k` | [`zeromodels/convnext_xlarge_fb_in22k`](https://huggingface.co/zeromodels/convnext_xlarge_fb_in22k) |
85
+ | `convnext_xlarge_fb_in22k_ft_in1k` | [`zeromodels/convnext_xlarge_fb_in22k_ft_in1k`](https://huggingface.co/zeromodels/convnext_xlarge_fb_in22k_ft_in1k) |
86
+ | `convnext_xlarge_fb_in22k_ft_in1k_384` | [`zeromodels/convnext_xlarge_fb_in22k_ft_in1k_384`](https://huggingface.co/zeromodels/convnext_xlarge_fb_in22k_ft_in1k_384) |
87
 
88
  ## Tips
89
 
90
+ - Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
91
  - `ConvNeXtImageClassify` returns class logits; `ConvNeXtModel` returns features (`as_backbone=True` for multi-scale stages).
92
+ - See [docs](https://imvision12.github.io/ZeroModels/classification_backbones/) and [Loading Weights](https://imvision12.github.io/ZeroModels/loading_weights/).
93
  - Upstream / timm checkpoints: `ConvNeXtImageClassify.from_weights("hf:timm/convnext_large.fb_in22k")`.
94
 
95
  ## Special Thanks
kf_config.json → zm_config.json RENAMED
@@ -1,27 +1,27 @@
1
- {
2
- "library_name": "kerasformers",
3
- "kerasformers_version": "1.2.1",
4
- "model_module": "kerasformers.models.convnext",
5
- "model_class": "ConvNeXtImageClassify",
6
- "variant": "convnext_large_fb_in22k",
7
- "weights": "model.weights.h5",
8
- "schema_version": 2,
9
- "weight_dtype": "float32",
10
- "model_type": "convnext",
11
- "vision_config": {
12
- "depths": [
13
- 3,
14
- 3,
15
- 27,
16
- 3
17
- ],
18
- "projection_dim": [
19
- 192,
20
- 384,
21
- 768,
22
- 1536
23
- ],
24
- "image_size": 224,
25
- "num_classes": 21841
26
- }
27
  }
 
1
+ {
2
+ "library_name": "zeromodels",
3
+ "zeromodels_version": "1.2.1",
4
+ "model_module": "zeromodels.models.convnext",
5
+ "model_class": "ConvNeXtImageClassify",
6
+ "variant": "convnext_large_fb_in22k",
7
+ "weights": "model.weights.h5",
8
+ "schema_version": 2,
9
+ "weight_dtype": "float32",
10
+ "model_type": "convnext",
11
+ "vision_config": {
12
+ "depths": [
13
+ 3,
14
+ 3,
15
+ 27,
16
+ 3
17
+ ],
18
+ "projection_dim": [
19
+ 192,
20
+ 384,
21
+ 768,
22
+ 1536
23
+ ],
24
+ "image_size": 224,
25
+ "num_classes": 21841
26
+ }
27
  }