Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Genius Patrick 55590ccb05 | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
README_CN.md | 1 year ago | |
regnet.png | 1 year ago | |
regnet_x_800mf_ascend.yaml | 1 year ago |
In this work, we present a new network design paradigm that combines the advantages of manual design and NAS. Instead of focusing on designing individual network instances, we design design spaces that parametrize populations of networks. Like in manual design, we aim for interpretability and to discover general design principles that describe networks that are simple, work well, and generalize across settings. Like in NAS, we aim to take advantage of semi-automated procedures to help achieve these goals The general strategy we adopt is to progressively design simplified versions of an initial, relatively unconstrained, design space while maintaining or improving its quality. The overall process is analogous to manual design, elevated to the population level and guided via distribution estimates of network design spaces. As a testbed for this paradigm, our focus is on exploring network structure (e.g., width, depth, groups, etc.) assuming standard model families including VGG, ResNet, and ResNeXt. We start with a relatively unconstrained design space we call AnyNet (e.g., widths and depths vary freely across stages) and apply our humanin-the-loop methodology to arrive at a low-dimensional design space consisting of simple “regular” networks, that we call RegNet. The core of the RegNet design space is simple: stage widths and depths are determined by a quantized linear function. Compared to AnyNet, the RegNet design space has simpler models, is easier to interpret, and has a higher concentration of good models.
Model | Context | Top-1 (%) | Top-5 (%) | Params (M) | Train T. | Infer T. | Download | Config | Log |
---|---|---|---|---|---|---|---|---|---|
RegNetX-800MF | D910x8-G | 76.09 | 92.968 | 7.3 | 115s/epoch | 1.8ms/step | model | cfg | log |
Please refer to the installation instruction in MindCV.
Please download the ImageNet-1K dataset for model training and validation.
The yaml config files that yield competitive results on ImageNet for different models are listed in the configs folder. To trigger training using preset yaml config.
python train.py --model=regnet_x_800mf --config=configs/regnet/regnet_x_800mf_ascend.yaml
To validate the trained model, you can use validate.py
. Here is an example for regnetx800mf to verify the accuracy of
pretrained weights.
python validate.py --model=regnet_x_800mf --dataset=imagenet --val_split=val --pretrained
To validate the model, you can use validate.py
. Here is an example for regnetx800mf to verify the accuracy of your
training.
python validate.py --model=regnet_x_800mf --dataset=imagenet --val_split=val --ckpt_path='./ckpt/regnet_x_800mf-best.ckpt'
Please refer to the deployment tutorial in MindCV.
No Description
Jupyter Notebook Python Markdown Text
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》