Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
h1a2n3nibal 9cc08eeec5 | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
rexnet_x09.yaml | 1 year ago | |
rexnet_x10.yaml | 1 year ago | |
rexnet_x13.yaml | 1 year ago | |
rexnet_x15.yaml | 1 year ago | |
rexnet_x20.yaml | 1 year ago |
ReXNet: Rethinking Channel Dimensions for Efficient Model Design
Rank Expansion Networks (ReXNets) follow a set of new design principles for designing bottlenecks in image classification models. Authors refine each layer by 1) expanding the input channel size of the convolution layer and 2) replacing the ReLU6s.
Pynative | Pynative | Graph | Graph | ||||||
---|---|---|---|---|---|---|---|---|---|
Model | Top-1 (%) | Top-5 (%) | train (s/epoch) | Infer (ms) | train(s/epoch) | Infer (ms) | Download | Config | |
GPU | rexnet_x09 | model | config | ||||||
Ascend | rexnet_x09 | ||||||||
GPU | rexnet_x10 | model | config | ||||||
Ascend | rexnet_x10 | ||||||||
GPU | rexnet_x13 | model | config | ||||||
Ascend | rexnet_x13 | ||||||||
GPU | rexnet_x15 | model | config | ||||||
Ascend | rexnet_x15 | ||||||||
GPU | rexnet_x20 | model | config | ||||||
Ascend | rexnet_x20 |
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 --config ./config/rexnet/rexnet_x10.yaml
Here is the example for finetuning a pretrained rexnet x1.0 on CIFAR10 dataset using Adam optimizer.
python train.py --model=rexnet_x10 --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 to verify the accuracy of pretrained weights.
python validate.py --model=rexnet_x10 --dataset=imagenet --val_split=val --pretrained
To validate the model, you can use validate.py
. Here is an example to verify the accuracy of your training.
python validate.py --model=rexnet_x10 --dataset=imagenet --val_split=val --ckpt_path='./rexnetx10_ckpt/rexnet-best.ckpt'
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》