README.md
| 1 | --- |
| 2 | license: apache-2.0 |
| 3 | tags: |
| 4 | - vision |
| 5 | - image-classification |
| 6 | datasets: |
| 7 | - imagenet-1k |
| 8 | --- |
| 9 | |
| 10 | # ResNet-50 v1.5 |
| 11 | |
| 12 | ResNet model pre-trained on ImageNet-1k at resolution 224x224. It was introduced in the paper [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385) by He et al. |
| 13 | |
| 14 | Disclaimer: The team releasing ResNet did not write a model card for this model so this model card has been written by the Hugging Face team. |
| 15 | |
| 16 | ## Model description |
| 17 | |
| 18 | ResNet (Residual Network) is a convolutional neural network that democratized the concepts of residual learning and skip connections. This enables to train much deeper models. |
| 19 | |
| 20 | This is ResNet v1.5, which differs from the original model: in the bottleneck blocks which require downsampling, v1 has stride = 2 in the first 1x1 convolution, whereas v1.5 has stride = 2 in the 3x3 convolution. This difference makes ResNet50 v1.5 slightly more accurate (\~0.5% top1) than v1, but comes with a small performance drawback (~5% imgs/sec) according to [Nvidia](https://catalog.ngc.nvidia.com/orgs/nvidia/resources/resnet_50_v1_5_for_pytorch). |
| 21 | |
| 22 |  |
| 23 | |
| 24 | ## Intended uses & limitations |
| 25 | |
| 26 | You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=resnet) to look for |
| 27 | fine-tuned versions on a task that interests you. |
| 28 | |
| 29 | ### How to use |
| 30 | |
| 31 | Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes: |
| 32 | |
| 33 | ```python |
| 34 | from transformers import AutoImageProcessor, ResNetForImageClassification |
| 35 | import torch |
| 36 | from datasets import load_dataset |
| 37 | |
| 38 | dataset = load_dataset("huggingface/cats-image") |
| 39 | image = dataset["test"]["image"][0] |
| 40 | |
| 41 | processor = AutoImageProcessor.from_pretrained("microsoft/resnet-50") |
| 42 | model = ResNetForImageClassification.from_pretrained("microsoft/resnet-50") |
| 43 | |
| 44 | inputs = processor(image, return_tensors="pt") |
| 45 | |
| 46 | with torch.no_grad(): |
| 47 | logits = model(**inputs).logits |
| 48 | |
| 49 | # model predicts one of the 1000 ImageNet classes |
| 50 | predicted_label = logits.argmax(-1).item() |
| 51 | print(model.config.id2label[predicted_label]) |
| 52 | ``` |
| 53 | |
| 54 | For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/resnet). |
| 55 | |
| 56 | ### BibTeX entry and citation info |
| 57 | |
| 58 | ```bibtex |
| 59 | @inproceedings{he2016deep, |
| 60 | title={Deep residual learning for image recognition}, |
| 61 | author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian}, |
| 62 | booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition}, |
| 63 | pages={770--778}, |
| 64 | year={2016} |
| 65 | } |
| 66 | ``` |
| 67 | |