Arulkumar03/Fox_Sheep_Detector_Computer_Vision_model

1 2This directory contains a few example scripts that demonstrate features of detectron2.3 4 5* `train_net.py`6 7An example training script that's made to train builtin models of detectron2.8 9For usage, see [GETTING_STARTED.md](../GETTING_STARTED.md).10 11* `plain_train_net.py`12 13Similar to `train_net.py`, but implements a training loop instead of using `Trainer`.14This script includes fewer features but it may be more friendly to hackers.15 16* `benchmark.py`17 18Benchmark the training speed, inference speed or data loading speed of a given config.19 20Usage:21```22python benchmark.py --config-file config.yaml --task train/eval/data [optional DDP flags]23```24 25* `analyze_model.py`26 27Analyze FLOPs, parameters, activations of a detectron2 model.  See its `--help` for usage.28 29* `visualize_json_results.py`30 31Visualize the json instance detection/segmentation results dumped by `COCOEvalutor` or `LVISEvaluator`32 33Usage:34```35python visualize_json_results.py --input x.json --output dir/ --dataset coco_2017_val36```37If not using a builtin dataset, you'll need your own script or modify this script.38 39* `visualize_data.py`40 41Visualize ground truth raw annotations or training data (after preprocessing/augmentations).42 43Usage:44```45python visualize_data.py --config-file config.yaml --source annotation/dataloader --output-dir dir/ [--show]46```47 48NOTE: the script does not stop by itself when using `--source dataloader` because a training49dataloader is usually infinite.50