Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
songyuanwei bafcb7ee04 | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
densenet_121_ascend.yaml | 1 year ago | |
densenet_121_gpu.yaml | 1 year ago | |
densenet_161_ascend.yaml | 1 year ago | |
densenet_161_gpu.yaml | 1 year ago | |
densenet_169_ascend.yaml | 1 year ago | |
densenet_169_gpu.yaml | 1 year ago | |
densenet_201_ascend.yaml | 1 year ago | |
densenet_201_gpu.yaml | 1 year ago |
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and more efficient to train if
they contain shorter connections between layers close to the input and those close to the output. Dense Convolutional
Network (DenseNet) is introduced based on this observation, which connects each layer to every other layer in a
feed-forward fashion. Whereas traditional convolutional networks with $L$ layers have $L$ connections-one between each
layer and its subsequent layer, DenseNet has $\frac{L(L+1)}{2}$ direct connections. For each layer, the feature maps
of all preceding layers are used as inputs, and their feature maps are used as inputs into all subsequent layers.
DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature
propagation, encourage feature reuse, and substantially reduce the number of parameters.[1]
Figure 1. Architecture of DenseNet [1]
Our reproduced model performance on ImageNet-1K is reported as follows.
Model | Context | Top-1 (%) | Top-5 (%) | Params (M) | Recipe | Download |
---|---|---|---|---|---|---|
densenet_121 | D910x8-G | 75.64 | 92.84 | 8.06 | yaml | weights |
densenet_161 | D910x8-G | 79.09 | 94.66 | 28.90 | yaml | weights |
densenet_169 | D910x8-G | 77.26 | 93.71 | 14.31 | yaml | weights |
densenet_201 | D910x8-G | 78.14 | 94.08 | 20.24 | yaml | weights |
Please refer to the installation instruction in MindCV.
Please download the ImageNet-1K dataset for model training and validation.
It is easy to reproduce the reported results with the pre-defined training recipe. For distributed training on multiple Ascend 910 devices, please run
# distrubted training on multiple GPU/Ascend devices
mpirun -n 8 python train.py --config configs/densenet/densenet_121_ascend.yaml --data_dir /path/to/imagenet
If the script is executed by the root user, the
--allow-run-as-root
parameter must be added tompirun
.
Similarly, you can train the model on multiple GPU devices with the above mpirun
command.
For detailed illustration of all hyper-parameters, please refer to config.py.
Note: As the global batch size (batch_size x num_devices) is an important hyper-parameter, it is recommended to keep the global batch size unchanged for reproduction or adjust the learning rate linearly to a new global batch size.
If you want to train or finetune the model on a smaller dataset without distributed training, please run:
# standalone training on a CPU/GPU/Ascend device
python train.py --config configs/densenet/densenet_121_ascend.yaml --data_dir /path/to/dataset --distribute False
To validate the accuracy of the trained model, you can use validate.py
and parse the checkpoint path with --ckpt_path
.
python validate.py -c configs/densenet/densenet_121_ascend.yaml --data_dir /path/to/imagenet --ckpt_path /path/to/ckpt
Please refer to the deployment tutorial in MindCV.
[1] Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4700-4708.
No Description
Python Markdown Text other
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》