Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Genius Patrick d992a99fc7 | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
repmlp_t224_ascend.yaml | 1 year ago |
RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality
Compared to convolutional layers, fully-connected (FC) layers are better at modeling the long-range dependencies
but worse at capturing the local patterns, hence usually less favored for image recognition. In this paper, the authors propose a
methodology, Locality Injection, to incorporate local priors into an FC layer via merging the trained parameters of a
parallel conv kernel into the FC kernel. Locality Injection can be viewed as a novel Structural Re-parameterization
method since it equivalently converts the structures via transforming the parameters. Based on that, the authors propose a
multi-layer-perceptron (MLP) block named RepMLP Block, which uses three FC layers to extract features, and a novel
architecture named RepMLPNet. The hierarchical design distinguishes RepMLPNet from the other concurrently proposed vision MLPs.
As it produces feature maps of different levels, it qualifies as a backbone model for downstream tasks like semantic segmentation.
Their results reveal that 1) Locality Injection is a general methodology for MLP models; 2) RepMLPNet has favorable accuracy-efficiency
trade-off compared to the other MLPs; 3) RepMLPNet is the first MLP that seamlessly transfer to Cityscapes semantic segmentation.
Figure 1. RepMLP Block.[1]
Our reproduced model performance on ImageNet-1K is reported as follows.
Model | Context | Top-1 (%) | Top-5 (%) | Params (M) | Recipe | Download |
---|---|---|---|---|---|---|
repmlp_t224 | D910x8-G | 76.68 | 93.30 | 38.30 | yaml | weights |
Please refer to the installation instruction in MindCV.
Please download the ImageNet-1K dataset for model training and validation.
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/repmlp/repmlp_t224_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 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.
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/repmlp/repmlp_t224_ascend.yaml --data_dir /path/to/imagenet --distribute False
To validate the accuracy of the trained model, you can use validate.py
and parse the checkpoint path with --ckpt_path
.
python validate.py --model=RepMLPNet_T224 --data_dir /path/to/imagenet --ckpt_path /path/to/ckpt
To deploy online inference services with the trained model efficiently, please refer to the deployment tutorial.
[1]. Ding X, Chen H, Zhang X, et al. Repmlpnet: Hierarchical vision mlp with re-parameterized locality[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 578-587.
No Description
Python Markdown Text other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》