---
library_name: pytorch
---

![resnet_logo](resource/ResNet.png)

ResNet is a family of deep convolutional neural networks that introduced residual (skip) connections to enable stable training of very deep architectures with strong representational capacity.

Original paper: [Deep Residual Learning for Image Recognition, He et al., 2015](https://arxiv.org/abs/1512.03385)

# ResNet-50

ResNet-50 is a commonly used 50-layer variant that offers a strong balance between accuracy and computational cost and is widely adopted as a baseline and as a backbone feature extractor for tasks such as object detection, segmentation, and re-identification.

Model Configuration:
- Reference implementation: [ResNet50_v1.5](https://pytorch.org/vision/stable/models/generated/torchvision.models.resnet50.html)
- Original Weight: [ResNet50_Weights.IMAGENET1K_V2](https://download.pytorch.org/models/resnet50-11ad3fa6.pth)
- Resolution: 3x224x224
- Support Cooper version:
    - Cooper SDK: [2.5.2]
    - Cooper Foundry: [2.2]

| Model | Device | Model Link |
| :-----: | :-----: | :-----: |
| Resnet50 | N1-655 | [Model_Link](https://huggingface.co/Ambarella/ResNet/blob/main/n1-655_resnet_v1.5_50.bin) |
| Resnet50 | CV72 | [Model_Link](https://huggingface.co/Ambarella/ResNet/blob/main/cv72_resnet_v1.5_50.bin) |
| Resnet50 | CV75 | [Model_Link](https://huggingface.co/Ambarella/ResNet/blob/main/cv75_resnet_v1.5_50.bin) |