SFoever 80e7b13e94 | 1 year ago | |
---|---|---|
.. | ||
scripts | 1 year ago | |
README.md | 1 year ago | |
finetune.py | 1 year ago | |
train_parallel_with_func_example.py | 1 year ago | |
train_with_func_example.py | 1 year ago |
This folder contains examples for various tasks, which users can run easily.
python examples/finetune.py
This example shows how to finetune a pretrained model on your own dataset. You can also specifiy --freeze_backbone
to choose whether to freeze the backbone and finetune the classifier head only.
python examples/train_with_func_example.py
This example shows how to train and evaluate a model on your own dataset.
export CUDA_VISIBLE_DEVICES=0,1,2,3 # suppose there are 4 GPUs
mpirun --allow-run-as-root -n 4 python examples/train_parallel_with_func_example.py
This example shows how to train and evaluate a mode with multiprocess on your own dataset on GPU.
从一个相对不受约束的设计空间开始,逐步探索、改进网络设计空间的规则,直到一个由简单的“规则”网络组成的低维设计空间,称之为RegNet。RegNet设计空间的核心很简单:stage的宽度和深度由量化的线性函数决定。与AnyNet相比,RegNet设计空间的模型更简单,更容易解释,好模型的集中度更高。RegNet网络和当时最先进的不同体量网络在ImageNet数据集上进行了比较,体量较大时,RegNet超越了当时的最先进网络EfficientNet的结果。
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》