updates

detect.py

@@ -7,20 +7,19 @@ from utils.datasets import *
 from utils.utils import *
 
 
-def detect(
-        cfg,
+def detect(cfg,
            data_cfg,
            weights,
            images='data/samples',  # input folder
            output='output',  # output folder
-        fourcc='mp4v',
+           fourcc='mp4v',  # video codec
            img_size=416,
            conf_thres=0.5,
            nms_thres=0.5,
            save_txt=False,
            save_images=True,
-        webcam=False
-):
+           webcam=False):
+    # Initialize
     device = torch_utils.select_device()
     torch.backends.cudnn.benchmark = False  # set False for reproducible results
     if os.path.exists(output):
@@ -74,7 +73,7 @@ def detect(
 
         if det is not None and len(det) > 0:
             # Rescale boxes from 416 to true image size
-            det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()  # TODO: clamp to image border https://github.com/ultralytics/yolov3/issues/368
+            det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
 
             # Print results to screen
             print('%gx%g ' % img.shape[2:], end='')  # print image size

test.py

@@ -8,8 +8,7 @@ from utils.datasets import *
 from utils.utils import *
 
 
-def test(
-        cfg,
+def test(cfg,
          data_cfg,
          weights=None,
          batch_size=16,
@@ -18,8 +17,8 @@ def test(
          conf_thres=0.001,
          nms_thres=0.5,
          save_json=False,
-        model=None
-):
+         model=None):
+    # Initialize/load model and set device
     if model is None:
         device = torch_utils.select_device()
 
@@ -104,12 +103,10 @@ def test(
                 box = xyxy2xywh(box)  # xywh
                 box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
                 for di, d in enumerate(pred):
-                    jdict.append({
-                        'image_id': image_id,
+                    jdict.append({'image_id': image_id,
                                   'category_id': coco91class[int(d[6])],
                                   'bbox': [float3(x) for x in box[di]],
-                        'score': float(d[4])
-                    })
+                                  'score': float(d[4])})
 
             # Assign all predictions as incorrect
             correct = [0] * len(pred)

train.py

@@ -20,6 +20,8 @@ from utils.utils import *
 # 0.268	0.268	0.178	0.240	4.36	1.104	5.596	0.2087	14.47	2.599	16.27	2.406	0.4114	0.001585	-4	0.950	0.000524
 # 0.161	0.327	0.190	0.193	7.82	1.153	4.062	0.1845	24.28	3.05	20.93	2.842	0.2759	0.001357	-4	0.916	0.000572  # 320 --epochs 2
 
+
+# Training hyperparameters
 hyp = {'giou': 0.8541,  # giou loss gain
        'xy': 4.062,  # xy loss gain
        'wh': 0.1845,  # wh loss gain
@@ -34,15 +36,13 @@ hyp = {'giou': 0.8541,  # giou loss gain
        'weight_decay': 0.000467}  # optimizer weight decay
 
 
-def train(
-        cfg,
+def train(cfg,
           data_cfg,
           img_size=416,
           epochs=100,  # 500200 batches at bs 16, 117263 images = 273 epochs
           batch_size=16,
-        accumulate=4,  # effective bs = batch_size * accumulate = 8 * 8 = 64
-        freeze_backbone=False,
-):
+          accumulate=4):  # effective bs = batch_size * accumulate = 8 * 8 = 64
+    # Initialize
     init_seeds()
     weights = 'weights' + os.sep
     latest = weights + 'latest.pt'
@@ -178,6 +178,7 @@ def train(
         scheduler.step()
 
         # Freeze backbone at epoch 0, unfreeze at epoch 1 (optional)
+        freeze_backbone = False
         if freeze_backbone and epoch < 2:
             for name, p in model.named_parameters():
                 if int(name.split('.')[1]) < cutoff:  # if layer < 75