updates

README.md

@@ -86,7 +86,7 @@ GPUs | `batch_size` | images/sec | epoch time | epoch cost
 K80 | 64 (32x2) | 11  | 175 min  | $0.58
 T4 | 64 (32x2) | 40  | 49 min  | $0.29
 T4 x2 | 64 (64x1) | 61  | 32 min  | $0.36
-V100 | 64 (32x2) | 115 | 17 min | $0.24
+V100 | 64 (32x2) | 122 | 16 min | $0.23
 V100 x2 | 64 (64x1) | 150 | 13 min | $0.36
 2080Ti | 64 (32x2) | 81  | 24 min  | - 
 2080Ti x2 | 64 (64x1) | 140  | 14 min  | - 

test.py

@@ -64,8 +64,8 @@ def test(cfg,
     loss = torch.zeros(3)
     jdict, stats, ap, ap_class = [], [], [], []
     for batch_i, (imgs, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
+        imgs = imgs.to(device).float() / 255.0  # uint8 to float32, 0 - 255 to 0.0 - 1.0
         targets = targets.to(device)
-        imgs = imgs.to(device)
         _, _, height, width = imgs.shape  # batch size, channels, height, width
 
         # Plot images with bounding boxes

train.py

@@ -251,7 +251,7 @@ def train():
         pbar = tqdm(enumerate(dataloader), total=nb)  # progress bar
         for i, (imgs, targets, paths, _) in pbar:  # batch -------------------------------------------------------------
             ni = i + nb * epoch  # number integrated batches (since train start)
-            imgs = imgs.to(device)
+            imgs = imgs.to(device).float() / 255.0  # uint8 to float32, 0 - 255 to 0.0 - 1.0
             targets = targets.to(device)
 
             # Multi-Scale training

utils/datasets.py

@@ -487,8 +487,7 @@ class LoadImagesAndLabels(Dataset):  # for training/testing
 
         # Convert
         img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
-        img = np.ascontiguousarray(img, dtype=np.float32)  # uint8 to float32
-        img /= 255.0  # 0 - 255 to 0.0 - 1.0
+        img = np.ascontiguousarray(img)
 
         return torch.from_numpy(img), labels_out, img_path, ((h, w), (ratio, pad))