diff --git a/cfg.py b/cfg.py
index ab7d5873..bfc68e44 100644
--- a/cfg.py
+++ b/cfg.py
@@ -154,7 +154,7 @@ def load_conv(buf, start, conv_model):
     num_w = conv_model.weight.numel()
     num_b = conv_model.bias.numel()
     conv_model.bias.data.copy_(torch.from_numpy(buf[start:start+num_b]));   start = start + num_b
-    conv_model.weight.data.copy_(torch.from_numpy(buf[start:start+num_w])); start = start + num_w
+    conv_model.weight.data.copy_(torch.from_numpy(buf[start:start+num_w]).view_as(conv_model.weight.data)); start = start + num_w
     return start
 
 def save_conv(fp, conv_model):
@@ -172,7 +172,7 @@ def load_conv_bn(buf, start, conv_model, bn_model):
     bn_model.weight.data.copy_(torch.from_numpy(buf[start:start+num_b]));   start = start + num_b
     bn_model.running_mean.copy_(torch.from_numpy(buf[start:start+num_b]));  start = start + num_b
     bn_model.running_var.copy_(torch.from_numpy(buf[start:start+num_b]));   start = start + num_b
-    conv_model.weight.data.copy_(torch.from_numpy(buf[start:start+num_w])); start = start + num_w 
+    conv_model.weight.data.copy_(torch.from_numpy(buf[start:start+num_w]).view_as(conv_model.weight.data)); start = start + num_w
     return start
 
 def save_conv_bn(fp, conv_model, bn_model):
@@ -193,7 +193,7 @@ def load_fc(buf, start, fc_model):
     num_w = fc_model.weight.numel()
     num_b = fc_model.bias.numel()
     fc_model.bias.data.copy_(torch.from_numpy(buf[start:start+num_b]));     start = start + num_b
-    fc_model.weight.data.copy_(torch.from_numpy(buf[start:start+num_w]));   start = start + num_w 
+    fc_model.weight.data.copy_(torch.from_numpy(buf[start:start+num_w]).view_as(fc_model.weight.data));   start = start + num_w
     return start
 
 def save_fc(fp, fc_model):
diff --git a/darknet.py b/darknet.py
index 623da39f..e5cb5dda 100644
--- a/darknet.py
+++ b/darknet.py
@@ -28,10 +28,10 @@ def forward(self, x):
         assert(W % stride == 0)
         ws = stride
         hs = stride
-        x = x.view(B, C, H/hs, hs, W/ws, ws).transpose(3,4).contiguous()
-        x = x.view(B, C, H/hs*W/ws, hs*ws).transpose(2,3).contiguous()
-        x = x.view(B, C, hs*ws, H/hs, W/ws).transpose(1,2).contiguous()
-        x = x.view(B, hs*ws*C, H/hs, W/ws)
+        x = x.view(B, C, H//hs, hs, W//ws, ws).transpose(3,4).contiguous()
+        x = x.view(B, C, H//hs*W//ws, hs*ws).transpose(2,3).contiguous()
+        x = x.view(B, C, hs*ws, H//hs, W//ws).transpose(1,2).contiguous()
+        x = x.view(B, hs*ws*C, H//hs, W//ws)
         return x
 
 class GlobalAvgPool2d(nn.Module):
@@ -146,7 +146,7 @@ def create_network(self, blocks):
                 kernel_size = int(block['size'])
                 stride = int(block['stride'])
                 is_pad = int(block['pad'])
-                pad = (kernel_size-1)/2 if is_pad else 0
+                pad = (kernel_size-1)//2 if is_pad else 0
                 activation = block['activation']
                 model = nn.Sequential()
                 if batch_normalize:
diff --git a/utils.py b/utils.py
index c4f1b754..af074f6a 100644
--- a/utils.py
+++ b/utils.py
@@ -884,7 +884,7 @@ def get_color(c, x, max_val):
 def read_truths(lab_path):
     if os.path.getsize(lab_path):
         truths = np.loadtxt(lab_path)
-        truths = truths.reshape(truths.size/21, 21) # to avoid single truth problem
+        truths = truths.reshape(truths.size//21, 21) # to avoid single truth problem
         return truths
     else:
         return np.array([])
@@ -1008,7 +1008,7 @@ def file_lines(thefilepath):
         buffer = thefile.read(8192*1024)
         if not buffer:
             break
-        count += buffer.count('\n')
+        count += buffer.count(b'\n')
     thefile.close( )
     return count