updates

train.py

@@ -206,7 +206,7 @@ def train():
     model.arc = opt.arc  # attach yolo architecture
     model.hyp = hyp  # attach hyperparameters to model
     # model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device)  # attach class weights
-    model_info(model, report='summary')  # 'full' or 'summary'
+    torch_utils.model_info(model, report='summary')  # 'full' or 'summary'
     nb = len(dataloader)
     maps = np.zeros(nc)  # mAP per class
     results = (0, 0, 0, 0, 0, 0, 0)  # 'P', 'R', 'mAP', 'F1', 'val GIoU', 'val Objectness', 'val Classification'
@@ -387,7 +387,7 @@ if __name__ == '__main__':
     parser.add_argument('--batch-size', type=int, default=32)  # effective bs = batch_size * accumulate = 16 * 4 = 64
     parser.add_argument('--accumulate', type=int, default=2, help='batches to accumulate before optimizing')
     parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='cfg file path')
-    parser.add_argument('--data', type=str, default='data/coco.data', help='*.data file path')
+    parser.add_argument('--data', type=str, default='data/coco_64img.data', help='*.data file path')
     parser.add_argument('--multi-scale', action='store_true', help='adjust (67% - 150%) img_size every 10 batches')
     parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)')
     parser.add_argument('--rect', action='store_true', help='rectangular training')

utils/torch_utils.py

@@ -64,3 +64,16 @@ def fuse_conv_and_bn(conv, bn):
         fusedconv.bias.copy_(b_conv + b_bn)
 
         return fusedconv
+
+
+def model_info(model, report='summary'):
+    # Plots a line-by-line description of a PyTorch model
+    n_p = sum(x.numel() for x in model.parameters())  # number parameters
+    n_g = sum(x.numel() for x in model.parameters() if x.requires_grad)  # number gradients
+    if report is 'full':
+        print('%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
+        for i, (name, p) in enumerate(model.named_parameters()):
+            name = name.replace('module_list.', '')
+            print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
+                  (i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std()))
+    print('Model Summary: %g layers, %g parameters, %g gradients' % (len(list(model.parameters())), n_p, n_g))

utils/utils.py

@@ -41,19 +41,6 @@ def load_classes(path):
     return list(filter(None, names))  # filter removes empty strings (such as last line)
 
 
-def model_info(model, report='summary'):
-    # Plots a line-by-line description of a PyTorch model
-    n_p = sum(x.numel() for x in model.parameters())  # number parameters
-    n_g = sum(x.numel() for x in model.parameters() if x.requires_grad)  # number gradients
-    if report is 'full':
-        print('%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
-        for i, (name, p) in enumerate(model.named_parameters()):
-            name = name.replace('module_list.', '')
-            print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
-                  (i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std()))
-    print('Model Summary: %g layers, %g parameters, %g gradients' % (len(list(model.parameters())), n_p, n_g))
-
-
 def labels_to_class_weights(labels, nc=80):
     # Get class weights (inverse frequency) from training labels
     ni = len(labels)  # number of images