|
--- |
|
license: apache-2.0 |
|
tags: |
|
- vision |
|
- image-classification |
|
datasets: |
|
- imagenet-1k |
|
library_name: openvino |
|
--- |
|
|
|
# ResNet-50 v1.5 |
|
|
|
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. |
|
|
|
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. |
|
|
|
## Model description |
|
|
|
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. |
|
|
|
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). |
|
|
|
 |
|
|
|
## Intended uses & limitations |
|
|
|
You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=resnet) to look for |
|
fine-tuned versions on a task that interests you. |
|
|
|
### convert to openvino |
|
```bash |
|
pip install --upgrade --upgrade-strategy eager optimum[openvino] |
|
optimum-cli export openvino --model microsoft/resnet-50 ov_model/ |
|
``` |
|
|
|
### How to use |
|
|
|
Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes: |
|
|
|
```python |
|
from transformers import AutoImageProcessor, ResNetForImageClassification |
|
from optimum.intel import OVModelForImageClassification |
|
import torch |
|
from PIL import Image |
|
import requests |
|
|
|
url = "http://images.cocodataset.org/val2017/000000039769.jpg" |
|
image = Image.open(requests.get(url, stream=True).raw) |
|
|
|
processor = AutoImageProcessor.from_pretrained("Charles95/openvino_resnet50") |
|
model = OVModelForImageClassification.from_pretrained("Charles95/openvino_resnet50") |
|
|
|
inputs = processor(image, return_tensors="pt") |
|
|
|
with torch.no_grad(): |
|
logits = model(**inputs).logits |
|
|
|
# model predicts one of the 1000 ImageNet classes |
|
predicted_label = logits.argmax(-1).item() |
|
print(model.config.id2label[predicted_label]) |
|
``` |
|
|
|
For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/resnet). |
|
|
|
### performance improvement |
|
|
|
pytorch infer avg ≈66.5ms |
|
openvino infer avg ≈7.9ms |
|
3090 with transformers infer avg ≈6.3ms |
|
|
|
improve ≈800% |
|
|
|
### BibTeX entry and citation info |
|
|
|
```bibtex |
|
@inproceedings{he2016deep, |
|
title={Deep residual learning for image recognition}, |
|
author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian}, |
|
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition}, |
|
pages={770--778}, |
|
year={2016} |
|
} |
|
``` |
