Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
lgoodsky 24a8fcaefb | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
README_CN.md | 1 year ago | |
res2net.png | 1 year ago | |
res2net_50-v1b_ascend.yaml | 1 year ago | |
res2net_50-v1b_gpu.yaml | 1 year ago | |
res2net_50_ascend.yaml | 1 year ago | |
res2net_50_gpu.yaml | 1 year ago | |
res2net_101-v1b_ascend.yaml | 1 year ago | |
res2net_101-v1b_gpu.yaml | 1 year ago | |
res2net_101_ascend.yaml | 1 year ago | |
res2net_101_gpu.yaml | 1 year ago |
We propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections
within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the
range of receptive fields for each network layer. The proposed Res2Net block can be plugged into the state-of-the-art
backbone CNN models, e.g. , ResNet, ResNeXt, BigLittleNet, and DLA. We evaluate the Res2Net block on all these models
and demonstrate consistent performance gains over baseline models.
Pynative | Pynative | Graph | Graph | ||||||
---|---|---|---|---|---|---|---|---|---|
Model | Top-1 (%) | Top-5 (%) | train (s/epoch) | Infer (ms) | train(s/epoch) | Infer (ms) | Download | Config | |
GPU | res2net50 | model | config | ||||||
Ascend | res2net50 | ||||||||
GPU | res2net101 | model | config | ||||||
Ascend | res2net101 | ||||||||
GPU | res2net50_v1b | model | config | ||||||
Ascend | res2net50_v1b | ||||||||
GPU | res2net101_v1b | model | config | ||||||
Ascend | res2net101_v1b |
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.
comming soon
Here is the example for finetuning a pretrained InceptionV3 on CIFAR10 dataset using Adam optimizer.
python train.py --model=res2net50 --pretrained --opt=momentum --lr=0.001 dataset=cifar10 --num_classes=10 --dataset_download
Detailed adjustable parameters and their default value can be seen in config.py.
To validate the model, you can use validate.py
. Here is an example for res2net50 to verify the accuracy of
pretrained weights.
python validate.py --model=res2net50 --dataset=imagenet --val_split=val --pretrained
To validate the model, you can use validate.py
. Here is an example for res2net50 to verify the accuracy of your
training.
python validate.py --model=res2net50 --dataset=imagenet --val_split=val --ckpt_path='./ckpt/res2net50-best.ckpt'
mindspore-Levit
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》