| library_name: pytorch | |
|  | |
| ConvNeXt revisits and modernizes convolutional neural network design by incorporating architectural insights from Vision Transformers, such as large kernels, simplified blocks, and improved normalization, while retaining convolutional efficiency. | |
| Original paper: [A ConvNet for the 2020s, Liu et al., 2022](https://arxiv.org/abs/2201.03545) | |
| # ConvNeXt-T | |
| This model uses the ConvNeXt-Tiny variant, a lightweight configuration that delivers strong accuracy with relatively low computational cost. It is well suited for high-resolution image classification and as a general-purpose backbone for detection and segmentation tasks where CNN efficiency is preferred. | |
| Model Configuration: | |
| - Reference implementation: [ConvNeXt_T](https://pytorch.org/vision/stable/models/generated/torchvision.models.convnext_tiny.html) | |
| - Original Weight: [ConvNeXt_Tiny_Weights.IMAGENET1K_V1](https://download.pytorch.org/models/convnext_tiny-983f1562.pth) | |
| - Resolution: 3x224x224 | |
| - Support Cooper version: | |
| - Cooper SDK: [2.5.2] | |
| - Cooper Foundry: [2.2] | |
| | Model | Device | Model Link | | |
| | :-----: | :-----: | :-----: | | |
| | ConvNeXt-T | N1-655 | [Model_Link](https://huggingface.co/Ambarella/ConvNeXt/blob/main/n1-655_convnext_tiny.bin) | | |
| | ConvNeXt-T | CV72 | [Model_Link](https://huggingface.co/Ambarella/ConvNeXt/blob/main/cv72_convnext_tiny.bin) | | |
| | ConvNeXt-T | CV75 | [Model_Link](https://huggingface.co/Ambarella/ConvNeXt/blob/main/cv75_convnext_tiny.bin) | |