This library is to help you train and evaluate PyTorch classification model easily and quickly
Project description
pytorch-vision-classifier
The main target of this template is to help during building your classification model where:
- It helps load the dataset whether the dataset in one directory or multiple directories
- It shows the dataset details once the dataset directory has been specified
- It helps know the available GPU devices and pick one to use easily
- It helps get a pre-trained model for you with the last layer updated with or without a dropout layer and initialized by an algorithm you choose from the most common initialization algorithms
- It helps know the GPU memory usage of your model
- It helps understand the timing of different steps during model training
- It helps find the best learning rate using the algorithm published by Leslie N. Smith in the paper Cyclical Learning Rates for Training Neural Networks. The original code
- It provides a dashboard to monitor your model during the training process
- It helps track the metric that you choose to find the best model for your problem
- It provides a compressed version of your model to be used for deployment purpose
In order to install, you need to download pytorch. then open the command prompt and type:
pip install pytorch_vision_classifier
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
Built Distribution
Close
Hashes for pytorch_vision_classifier-0.0.2.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 30c6c81eee200511120abbb5c6337751f4a646a703e6238d07511fc70334791c |
|
MD5 | b885a4ea1ac99e117ef0c4ba7eeac0fc |
|
BLAKE2b-256 | 51a8d0e3450b1c7049c0812f72a879af28962d3de9e1f1f8ccebbe8ff0c8d00a |
Close
Hashes for pytorch_vision_classifier-0.0.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b89f27abace9401d3922911f42c5e27117ad4a4e2b4a61f8109de667d57076a1 |
|
MD5 | de762376b8b2518436905628da83af83 |
|
BLAKE2b-256 | 80487db9aede451f47a73e1eb46beae420bdd2e5d269a80d4c85ba755dc21c21 |