check_orientation's Introduction

Check orientation

Models to check if image was rotated by 0, 90, 180, 270 degrees.

Installation

pip install -U check_orientation

Example inference

Colab notebook with the example:

Training

Define the config.

Example at check_orientation/configs

Define the environmental variable `TRAIN_IMAGE_PATH` that points to the folder with train dataset.

Example:

export TRAIN_IMAGE_PATH=<path to the tranining folder>

Define the environmental variable `VAL_IMAGE_PATH` that points to the folder with validation dataset.

Example:

export VAL_IMAGE_PATH=<path to the validation folder>

Training

python -m check_orientation.train -c <path to config>

Inference

python -m torch.distributed.launch --nproc_per_node=<num_gpu> check_orientation/inference.py \
                                   -i <path to images> \
                                   -c <path to config> \
                                   -w <path to weights> \
                                   -o <output-path> \
                                   --fp16

Pre-trained models

Models were pre-trained on the OpenImages dataset.

Models	Validation accuracy	Config file	Weights
swsl_resnext50_32x4d	0.9128	Link	Link

check_orientation's People

Contributors

Stargazers

Watchers

check_orientation's Issues

TypeError: init() got an unexpected keyword argument 'filepath'

File "/home/pdguest/enviroments/mmdet/lib/python3.6/site-packages/iglovikov_helper_functions/config_parsing/utils.py", line 88, in object_from_dict
return pydoc.locate(object_type)(**kwargs)
TypeError: init() got an unexpected keyword argument 'filepath'

I'm having this error when I'm calling the parameter checkpoint_callback in training. Can someone help me this?

2020-11-16_resnext50_32x4d.pth has been trained?

When I use the model of 2020-11-16_resnext50_32x4d.pth,the result of sofrmax alway like [0.25959268 0.25396952 0.24766599 0.23877187].
The model has been trained?

Recommend Projects