nielsr HF staff commited on
Commit
d72d44e
1 Parent(s): 1c8390b

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +82 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - vision
5
+ - image-classification
6
+ datasets:
7
+ - imagenet-21k
8
+ widget:
9
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
10
+ example_title: Tiger
11
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
12
+ example_title: Teapot
13
+ - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
14
+ example_title: Palace
15
+ ---
16
+
17
+ # ConvNeXT (base-sized model)
18
+
19
+ ConvNeXT model trained on ImageNet-22k at resolution 224x224. It was introduced in the paper [A ConvNet for the 2020s](https://arxiv.org/abs/2201.03545) by Liu et al. and first released in [this repository](https://github.com/facebookresearch/ConvNeXt).
20
+
21
+ Disclaimer: The team releasing ConvNeXT did not write a model card for this model so this model card has been written by the Hugging Face team.
22
+
23
+ ## Model description
24
+
25
+ ConvNeXT is a pure convolutional model (ConvNet), inspired by the design of Vision Transformers, that claims to outperform them. The authors started from a ResNet and "modernized" its design by taking the Swin Transformer as inspiration.
26
+
27
+ ![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/convnext_architecture.png)
28
+
29
+ ## Intended uses & limitations
30
+
31
+ You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=convnext) to look for
32
+ fine-tuned versions on a task that interests you.
33
+
34
+ ### How to use
35
+
36
+ Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
37
+
38
+ ```python
39
+ from transformers import ConvNextFeatureExtractor, ConvNextForImageClassification
40
+ import torch
41
+ from datasets import load_dataset
42
+
43
+ dataset = load_dataset("huggingface/cats-image")
44
+ image = dataset["test"]["image"][0]
45
+
46
+ feature_extractor = ConvNextFeatureExtractor.from_pretrained("facebook/convnext-base-224-22k")
47
+ model = ConvNextForImageClassification.from_pretrained("facebook/convnext-base-224-22k")
48
+
49
+ inputs = feature_extractor(image, return_tensors="pt")
50
+
51
+ with torch.no_grad():
52
+ logits = model(**inputs).logits
53
+
54
+ # model predicts one of the 22k ImageNet classes
55
+ predicted_label = logits.argmax(-1).item()
56
+ print(model.config.id2label[predicted_label]),
57
+ ```
58
+
59
+ For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/convnext).
60
+
61
+ ### BibTeX entry and citation info
62
+
63
+ ```bibtex
64
+ @article{DBLP:journals/corr/abs-2201-03545,
65
+ author = {Zhuang Liu and
66
+ Hanzi Mao and
67
+ Chao{-}Yuan Wu and
68
+ Christoph Feichtenhofer and
69
+ Trevor Darrell and
70
+ Saining Xie},
71
+ title = {A ConvNet for the 2020s},
72
+ journal = {CoRR},
73
+ volume = {abs/2201.03545},
74
+ year = {2022},
75
+ url = {https://arxiv.org/abs/2201.03545},
76
+ eprinttype = {arXiv},
77
+ eprint = {2201.03545},
78
+ timestamp = {Thu, 20 Jan 2022 14:21:35 +0100},
79
+ biburl = {https://dblp.org/rec/journals/corr/abs-2201-03545.bib},
80
+ bibsource = {dblp computer science bibliography, https://dblp.org}
81
+ }
82
+ ```