Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
handsome222luoke 69a2319429 | 10 months ago | |
---|---|---|
.. | ||
bit | 1 year ago | |
coat | 11 months ago | |
convit | 1 year ago | |
convnext | 1 year ago | |
convnextv2 | 10 months ago | |
crossvit | 1 year ago | |
densenet | 1 year ago | |
dpn | 1 year ago | |
edgenext | 1 year ago | |
efficientnet | 1 year ago | |
ghostnet | 11 months ago | |
googlenet | 1 year ago | |
hrnet | 1 year ago | |
inceptionv3 | 11 months ago | |
inceptionv4 | 11 months ago | |
mixnet | 1 year ago | |
mnasnet | 11 months ago | |
mobilenetv1 | 1 year ago | |
mobilenetv2 | 11 months ago | |
mobilenetv3 | 11 months ago | |
mobilevit | 11 months ago | |
nasnet | 1 year ago | |
pit | 1 year ago | |
poolformer | 1 year ago | |
pvt | 1 year ago | |
pvtv2 | 10 months ago | |
regnet | 10 months ago | |
repmlp | 1 year ago | |
repvgg | 1 year ago | |
res2net | 1 year ago | |
resnest | 1 year ago | |
resnet | 1 year ago | |
resnetv2 | 1 year ago | |
resnext | 1 year ago | |
rexnet | 11 months ago | |
senet | 1 year ago | |
shufflenetv1 | 11 months ago | |
shufflenetv2 | 11 months ago | |
sknet | 1 year ago | |
squeezenet | 1 year ago | |
swintransformer | 1 year ago | |
vgg | 11 months ago | |
visformer | 1 year ago | |
vit | 1 year ago | |
xception | 1 year ago | |
xcit | 1 year ago | |
README.md | 1 year ago |
This folder contains training recipes and model readme files for each model. The folder structure and naming rule of model configurations are as follows.
├── configs
├── model_a // model name in lower case with _ seperator
│ ├─ model_a_small_ascend.yaml // training recipe denated as {model_name}_{specification}_{hardware}.yaml
| ├─ model_a_large_gpu.yaml
│ ├─ README.md //readme file containing performance results and pretrained weight urls
│ └─ README_CN.md //readme file in Chinese
├── model_b
│ ├─ model_b_32_ascend.yaml
| ├─ model_l_16_ascend.yaml
│ ├─ README.md
│ └─ README_CN.md
├── README.md //this file
The model readme file in each sub-folder provides the introduction, reproduced results, and running guideline for each model.
Please follow the outline structure and table format shown in densenet/README.md when contributing your models :)
Model | Context | Top-1 (%) | Top-5 (%) | Params (M) | Recipe | Download |
---|---|---|---|---|---|---|
densenet_121 | D910x8-G | 75.64 | 92.84 | 8.06 | yaml | weights |
Illustration:
The checkpoint (i.e., model weight) name should follow this format: {model_name}_{specification}-{sha256sum}.ckpt, e.g., poolformer_s12-5be5c4e4.ckpt
.
You can run the following command and take the first 8 characters of the computing result as the sha256sum value in the checkpoint name.
sha256sum your_model.ckpt
For consistency, it is recommended to provide distributed training commands based on mpirun -n {num_devices} python train.py
, instead of using shell script such as distrubuted_train.sh
.
# standalone training on a gpu or ascend device
python train.py --config configs/densenet/densenet_121_gpu.yaml --data_dir /path/to/dataset --distribute False
# distributed training on gpu or ascend divices
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
.
Please use absolute path in the hyperlink or url for linking the target resource in the readme file and table.
No Description
Python Markdown 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》