Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
EmmaHAN 062fe1a7c9 | 3 months ago | |
---|---|---|
.. | ||
README.md | 10 months ago | |
skresnet18_ascend.yaml | 3 months ago | |
skresnet34_ascend.yaml | 3 months ago | |
skresnext50_32x4d_ascend.yaml | 3 months ago |
The local receptive fields (RFs) of neurons in the primary visual cortex (V1) of cats [1] have inspired the
construction of Convolutional Neural Networks (CNNs) [2] in the last century, and it continues to inspire mordern CNN
structure construction. For instance, it is well-known that in the visual cortex, the RF sizes of neurons in the
same area (e.g.,V1 region) are different, which enables the neurons to collect multi-scale spatial information in the
same processing stage. This mechanism has been widely adopted in recent Convolutional Neural Networks (CNNs).
A typical example is InceptionNets [3, 4, 5, 6], in which a simple concatenation is designed to aggregate
multi-scale information from, e.g., 3×3, 5×5, 7×7 convolutional kernels inside the “inception” building block.
Figure 1. Selective Kernel Convolution.
Our reproduced model performance on ImageNet-1K is reported as follows.
Model | Context | Top-1 (%) | Top-5 (%) | Params (M) | Recipe | Download |
---|---|---|---|---|---|---|
skresnet18 | D910x8-G | 73.09 | 91.20 | 11.97 | yaml | weights |
skresnet34 | D910x8-G | 76.71 | 93.10 | 22.31 | yaml | weights |
skresnext50_32x4d | D910x8-G | 79.08 | 94.60 | 37.31 | 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/sknet/skresnext50_32x4d_ascend.yaml --data_dir /path/to/imagenet
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/sknet/skresnext50_32x4d_ascend.yaml --data_dir /path/to/dataset --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 -c configs/sknet/skresnext50_32x4d_ascend.yaml --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] D. H. Hubel and T. N. Wiesel. Receptive fields, binocular interaction and functional architecture in the cat’s visual
cortex. The Journal of Physiology, 1962.
[2] Y . LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel. Backpropagation
applied to handwritten zip code recognition. Neural Computation, 1989.
[3] C. Szegedy, V . V anhoucke, S. Ioffe, J. Shlens, and Z. Wojna. Rethinking the inception architecture for computer vision. In
CVPR, 2016.
[4] S. Ioffe and C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift.
arXiv preprint arXiv:1502.03167, 2015.
[5] C. Szegedy, V . V anhoucke, S. Ioffe, J. Shlens, and Z. Wojna. Rethinking the inception architecture for computer vision. In
CVPR, 2016.
[6] C. Szegedy, S. Ioffe, V . V anhoucke, and A. A. Alemi. Inception-v4, inception-resnet and the impact of residual
connections on learning. In AAAI, 2017.
A toolbox of vision models and algorithms based on MindSpore
https://github.com/mindspore-lab/mindcv
Python Markdown 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》