updates

train.py

@@ -131,7 +131,7 @@ def train(
     dataloader = DataLoader(dataset,
                             batch_size=batch_size,
                             num_workers=opt.num_workers,
-                            shuffle=False,
+                            shuffle=False,  # disable rectangular training if True
                             pin_memory=True,
                             collate_fn=dataset.collate_fn)
 
@@ -274,7 +274,7 @@ if __name__ == '__main__':
     parser.add_argument('--batch-size', type=int, default=16, help='size of each image batch')
     parser.add_argument('--accumulate', type=int, default=1, help='accumulate gradient x batches before optimizing')
     parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='cfg file path')
-    parser.add_argument('--data-cfg', type=str, default='data/coco.data', help='coco.data file path')
+    parser.add_argument('--data-cfg', type=str, default='data/coco_32img.data', help='coco.data file path')
     parser.add_argument('--multi-scale', action='store_true', help='random image sizes per batch 320 - 608')
     parser.add_argument('--img-size', type=int, default=416, help='pixels')
     parser.add_argument('--resume', action='store_true', help='resume training flag')

utils/gcp.sh

@@ -65,9 +65,9 @@ rm -rf yolov3
 git clone https://github.com/ultralytics/yolov3  # master
 cp -r cocoapi/PythonAPI/pycocotools yolov3
 cp -r weights yolov3 && cd yolov3
-python3 detect.py  # detect
-python3 test.py --data data/coco_32img.data  # test
-python3 train.py --data data/coco_32img.data --epochs 4 --nosave  # train
+python3 detect.py  # detect 2 persons, 1 tie
+python3 test.py --data data/coco_32img.data  # test mAP = 0.78
+python3 train.py --data data/coco_32img.data --epochs 4 --nosave  # train 4 epochs
 
 # Debug/Development
 rm -rf yolov3