datasets.py self.batch_shapes fix

models/yolo.py

@@ -20,7 +20,6 @@ def __init__(self, nc=80, anchors=()):  # detection layer
         self.export = False  # onnx export
 
     def forward(self, x):
-        x = x.copy()
         z = []  # inference output
         self.training |= self.export
         for i in range(self.nl):

test.py

@@ -244,7 +244,7 @@ def test(data,
     print(opt)
 
     # task = 'val', 'test', 'study'
-    if opt.task == 'val':  # (default) run normally
+    if opt.task in ['val', 'test']:  # (default) run normally
         test(opt.data,
              opt.weights,
              opt.batch_size,
@@ -258,7 +258,7 @@ def test(data,
     elif opt.task == 'study':  # run over a range of settings and save/plot
         for weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt', 'yolov3-spp.pt']:
             f = 'study_%s_%s.txt' % (Path(opt.data).stem, Path(weights).stem)  # filename to save to
-            x = list(range(256, 1024, 32))  # x axis
+            x = list(range(256, 1024, 64))  # x axis
             y = []  # y axis
             for i in x:  # img-size
                 print('\nRunning %s point %s...' % (f, i))

utils/datasets.py

@@ -322,7 +322,7 @@ def __init__(self, path, img_size=416, batch_size=16, augment=False, hyp=None, r
                 elif mini > 1:
                     shapes[i] = [1, 1 / mini]
 
-            self.batch_shapes = np.ceil(np.array(shapes) * img_size / 64.).astype(np.int) * 64
+            self.batch_shapes = np.round(np.array(shapes) * img_size / 32. + 1.).astype(np.int) * 32
 
         # Cache labels
         self.imgs = [None] * n