In this work, the authors reexamine the design spaces and test the limits of what a pure ConvNet can achieve. The authors gradually "modernize" a standard ResNet toward the design of a vision Transformer, and discover several key components that contribute to the performance difference along the way. The outcome of this exploration is a family of pure ConvNet models dubbed ConvNeXt. Constructed entirely from standard ConvNet modules, ConvNeXts compete favorably with Transformers in terms of accuracy and scalability, achieving 87.8% ImageNet top-1 accuracy, while maintaining the simplicity and efficiency of standard ConvNets.[1]
Figure 1. Architecture of ConvNeXt [1]
Our reproduced model performance on ImageNet-1K is reported as follows.
| Model | Context | Top-1 (%) | Top-5 (%) | Params (M) | Recipe | Download |
|---|---|---|---|---|---|---|
| convnext_tiny | D910x64-G | 81.91 | 95.79 | 28.59 | yaml | weights |
| convnext_small | D910x64-G | 83.40 | 96.36 | 50.22 | yaml | weights |
| convnext_base | D910x64-G | 83.32 | 96.24 | 88.59 | yaml | weights |
- Context: Training context denoted as {device}x{pieces}-{MS mode}, where mindspore mode can be G - graph mode or F - pynative mode with ms function. For example, D910x8-G is for training on 8 pieces of Ascend 910 NPU using graph mode.
- Top-1 and Top-5: Accuracy reported on the validation set of ImageNet-1K.
Please refer to the installation instruction in MindCV.
Please download the ImageNet-1K dataset for model training and validation.
- Distributed Training
It is easy to reproduce the reported results with the pre-defined training recipe. For distributed training on multiple Ascend 910 devices, please run
# distributed training on multiple GPU/Ascend devices
mpirun -n 8 python train.py --config configs/convnext/convnext_tiny_ascend.yaml --data_dir /path/to/imagenetIf the script is executed by the root user, the
--allow-run-as-rootparameter must be added tompirun.
Similarly, you can train the model on multiple GPU devices with the above mpirun command.
For detailed illustration of all hyper-parameters, please refer to config.py.
Note: As the global batch size (batch_size x num_devices) is an important hyper-parameter, it is recommended to keep the global batch size unchanged for reproduction or adjust the learning rate linearly to a new global batch size.
- Standalone Training
If you want to train or finetune the model on a smaller dataset without distributed training, please run:
# standalone training on a CPU/GPU/Ascend device
python train.py --config configs/convnext/convnext_tiny_ascend.yaml --data_dir /path/to/dataset --distribute FalseTo validate the accuracy of the trained model, you can use validate.py and parse the checkpoint path with --ckpt_path.
python validate.py -c configs/convnext/convnext_tiny_ascend.yaml --data_dir /path/to/imagenet --ckpt_path /path/to/ckptPlease refer to the deployment tutorial in MindCV.
[1] Liu Z, Mao H, Wu C Y, et al. A convnet for the 2020s[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 11976-11986.