rename /checkpoints to /weights

detect.py

@@ -33,7 +33,7 @@ def detect(opt):
     # Load model
     model = Darknet(opt.cfg, opt.img_size)
 
-    weights_path = 'checkpoints/yolov3.pt'
+    weights_path = 'weights/yolov3.pt'
     if weights_path.endswith('.weights'):  # saved in darknet format
         load_weights(model, weights_path)
     else:  # endswith('.pt'), saved in pytorch format

test.py

@@ -8,7 +8,7 @@ parser = argparse.ArgumentParser()
 parser.add_argument('-batch_size', type=int, default=32, help='size of each image batch')
 parser.add_argument('-cfg', type=str, default='cfg/yolov3.cfg', help='path to model config file')
 parser.add_argument('-data_config_path', type=str, default='cfg/coco.data', help='path to data config file')
-parser.add_argument('-weights_path', type=str, default='checkpoints/yolov3.pt', help='path to weights file')
+parser.add_argument('-weights_path', type=str, default='weights/yolov3.pt', help='path to weights file')
 parser.add_argument('-class_path', type=str, default='data/coco.names', help='path to class label file')
 parser.add_argument('-iou_thres', type=float, default=0.5, help='iou threshold required to qualify as detected')
 parser.add_argument('-conf_thres', type=float, default=0.5, help='object confidence threshold')

train.py

@@ -28,7 +28,7 @@ if cuda:
 
 
 def main(opt):
-    os.makedirs('checkpoints', exist_ok=True)
+    os.makedirs('weights', exist_ok=True)
 
     # Configure run
     data_config = parse_data_config(opt.data_config_path)
@@ -48,7 +48,7 @@ def main(opt):
     start_epoch = 0
     best_loss = float('inf')
     if opt.resume:
-        checkpoint = torch.load('checkpoints/latest.pt', map_location='cpu')
+        checkpoint = torch.load('weights/latest.pt', map_location='cpu')
 
         model.load_state_dict(checkpoint['model'])
         if torch.cuda.device_count() > 1:
@@ -175,15 +175,15 @@ def main(opt):
                       'best_loss': best_loss,
                       'model': model.state_dict(),
                       'optimizer': optimizer.state_dict()}
-        torch.save(checkpoint, 'checkpoints/latest.pt')
+        torch.save(checkpoint, 'weights/latest.pt')
 
         # Save best checkpoint
         if best_loss == loss_per_target:
-            os.system('cp checkpoints/latest.pt checkpoints/best.pt')
+            os.system('cp weights/latest.pt weights/best.pt')
 
-        # Save backup checkpoints every 5 epochs
+        # Save backup weights every 5 epochs
         if (epoch > 0) & (epoch % 5 == 0):
-            os.system('cp checkpoints/latest.pt checkpoints/backup' + str(epoch) + '.pt')
+            os.system('cp weights/latest.pt weights/backup' + str(epoch) + '.pt')
 
     # Save final model
     dt = time.time() - t0

utils/gcp.sh

@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 
 # Start
-sudo rm -rf yolov3 && git clone https://github.com/ultralytics/yolov3 && cd yolov3 && python3 train.py -img_size 416 -epochs 160
+sudo rm -rf yolov3 && git clone https://github.com/ultralytics/yolov3 && cd yolov3 && python3 train.py -img_size 416
 
 # Resume
 python3 train.py -img_size 416 -resume 1

utils/utils.py

@@ -410,7 +410,7 @@ def non_max_suppression(prediction, conf_thres=0.5, nms_thres=0.4):
     return output
 
 
-def strip_optimizer_from_checkpoint(filename='checkpoints/best.pt'):
+def strip_optimizer_from_checkpoint(filename='weights/best.pt'):
     # Strip optimizer from *.pt files for lighter files (reduced by 2/3 size)
     import torch
     a = torch.load(filename, map_location='cpu')