ConvNeXt
A ConvNet for the 2020s
Introduction
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]
Results
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 |
Notes
- 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.
Quick Start
Preparation
Installation
Please refer to the installation instruction in MindCV.
Dataset Preparation
Please download the ImageNet-1K dataset for model training and validation.
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/imagenet
If the script is executed by the root user, the --allow-run-as-root
parameter must be added to mpirun
.
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.
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 False
Validation
To 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/ckpt
Deployment
Please refer to the deployment tutorial in MindCV.
References
[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.