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
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-0.0.13.tar.gz
(27.8 kB
view details)
Built Distribution
File details
Details for the file efficient-det-0.0.13.tar.gz.
File metadata
- Download URL: efficient-det-0.0.13.tar.gz
- Upload date:
- Size: 27.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.25.0 requests-toolbelt/0.9.1 tqdm/4.54.0 CPython/3.7.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 3aebd899b68850ae546c4840bc0fccb9d9e74822683aa08d1c2d77225ec90634 |
|
| MD5 | 6e6ea33f0543818cc8d6995bb164b74e |
|
| BLAKE2b-256 | beed38c7a10722b9baa5335ede8da3c06c00972bf19406841880d9bc5462721a |
File details
Details for the file efficient_det-0.0.13-py3-none-any.whl.
File metadata
- Download URL: efficient_det-0.0.13-py3-none-any.whl
- Upload date:
- Size: 36.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.25.0 requests-toolbelt/0.9.1 tqdm/4.54.0 CPython/3.7.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 9c84edb9039c267325b61935a8e5cb67409398ce51b5efaaae9c85d888e38c96 |
|
| MD5 | c326725e9ad96b4aa5b28f1ceffaecc8 |
|
| BLAKE2b-256 | ccca59970b73e03344c6b9576af17a103f0f03aac310678eb2be680132def24c |
