Simple straightfoward repo for simple task of image classsification. Uses yaml config files to set hyperparameters for training. And loads data through list-style datasets. Training logs are written to console and also to tensorboard.

Each dataset (train/val/test) is defined in csv files:

<path to image>,<class name>
...
...
...
<path to image>,<class name>

Accompanied by class names in classes.txt

classA
classB
...
classZ

1. Copy configs/config-example.yaml and modify accordingly.
2. python3 train.py --config <path to config>

1. Copy configs/config-example.yaml and modify accordingly. Make sure pointing to the right path of the trained weights.
2. python3 test.py --config <path to config>

1. Copy configs/config-infer-example.yaml and modify accordingly. Make sure pointing to the right path of the trained weights.
2. python3 infer.py --config <path to config>
3. Look at the example under the if __name__=='__main__' portion of infer.py and adapt to your own application accordingly. Main thing is instantiating the Classifier object with your config yaml file and running its predict method.

• Augmentations/preprocessing transformations are defined in their own .yaml files, supports torchvision.transforms.