Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Lcy-star 921e4c16c1 | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
README_CN.md | 1 year ago | |
mobilenetv1.png | 1 year ago | |
mobilenetv1_025_ascend.yaml | 1 year ago | |
mobilenetv1_025_gpu.yaml | 1 year ago | |
mobilenetv1_050_ascend.yaml | 1 year ago | |
mobilenetv1_050_gpu.yaml | 1 year ago | |
mobilenetv1_075_ascend.yaml | 1 year ago | |
mobilenetv1_075_gpu.yaml | 1 year ago | |
mobilenetv1_100_ascend.yaml | 1 year ago | |
mobilenetv1_100_gpu.yaml | 1 year ago |
MobileNetV1: Efficient Convolutional Neural Networks for Mobile Vision Applications
Compared with the traditional convolutional neural network, MobileNetV1's parameters and the amount of computation are
greatly reduced on the premise that the accuracy rate is slightly reduced.
(Compared to VGG16, the accuracy rate is reduced by 0.9%, but the model parameters are only 1/32 of VGG). The model is
based on a streamlined architecture that uses depthwise separable convolutions to build lightweight deep neural
networks.
At the same time, two simple global hyperparameters are introduced, which can effectively trade off latency and
accuracy.
Model | Context | Top-1 (%) | Top-5 (%) | Params (M) | Train T. | Infer T. | Download | Config | Log |
---|---|---|---|---|---|---|---|---|---|
MobileNet_v1_025 | D910x8-G | 54.64 | 78.29 | 0.47 | 113s/epoch | model | cfg | log | |
MobileNet_v1_050 | D910x8-G | 66.39 | 86.71 | 1.34 | 120s/epoch | model | cfg | log | |
MobileNet_v1_075 | D910x8-G | 70.66 | 89.49 | 2.60 | 128s/epoch | model | cfg | log | |
MobileNet_v1_100 | D910x8-G | 71.83 | 90.26 | 4.25 | 130s/epoch | model | cfg | log |
Please refer to the installation instruction in MindCV.
Please download the ImageNet-1K dataset for model training and validation.
Hyper-parameters. The hyper-parameter configurations for producing the reported results are stored in the yaml files in mindcv/configs/mobilenetv1
folder. For example, to train with one of these configurations, you can run:
# train densenet121 on 8 GPUs
export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
mpirun -n 8 python train.py -c configs/mobilenetv1/mobilenetv1_100_gpu.yaml --data_dir /path/to/imagenet
Note that the number of GPUs/Ascends and batch size will influence the training results. To reproduce the training result at most, it is recommended to use the same number of GPUs/Ascneds with the same batch size.
Finetuning. Here is an example for finetuning a pretrained mobilenet_050 on CIFAR10 dataset using Momentum optimizer.
python train.py --model=mobilenet_v1_100_224 --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 trained model, you can use validate.py
. Here is an example for mobilenet_100 to verify the accuracy of
pretrained weights.
python validate.py --model=mobilenet_v1_100_224 --dataset=imagenet --val_split=val --pretrained
To validate the model, you can use validate.py
. Here is an example for mobilenetv1_100 to verify the accuracy of your
training.
python validate.py --model=mobilenet_v1_100_224 --dataset=imagenet --val_split=val --ckpt_path='./ckpt/mobilenet_v1_100_224-200_2502.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》