Efficient-Det Implementation in Keras
Project description
EfficientDet
Start with following command:
export PYTHONPATH="$PWD/src"
All commands should be executed in efficientdet/.
To test trained model on validation dataset you can use the jupyter notebook or python script in examples/.
For your own implementation set the dataset path and path to the trained model. Default paths are set to efficient/dataset.
To run all tests:
python3 -m unittest
To train neural network
python3 src/efficient_det/train.py --dataset_path /path/to/dataset/
When using Ray Tune verbose is default set to False. Use W&B for visualization.
Pip
python3 -m efficient_det.run_training --dataset_path ~/efficientdet/voc_data --use_wandb
Imports with pip needs to be like
from efficient_det.models.efficient_net import create_efficientnet
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
efficient-det-0.1.0.tar.gz
(27.8 kB
view hashes)
Built Distribution
Close
Hashes for efficient_det-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0547940d23ac30e941847c6b3e8c2a24e98d24a991e07e22a571f54f3f2b1160 |
|
MD5 | 91780671f9aa56663f42ea104058cfaa |
|
BLAKE2b-256 | ccdb4947f6af96125b756e0cd215b4e801cf3d26b722827b2fc5d1eda675d9e7 |