Update handler.py

handler.py

@@ -308,7 +308,7 @@ class RealESRGAN:
 
         input_batch = torch.concat(list_of_inputs)
 
-        print('input_batch.shape', input_batch.shape)
+        # print('input_batch.shape', input_batch.shape)
 
         start2 = time.time()
         with torch.no_grad():
@@ -316,8 +316,8 @@ class RealESRGAN:
 
             # okay what does the input size really need to be?
 
-            print('input_batch.shape', input_batch.shape)
-            print('input_batch[0:batch_size].shape', input_batch[0:batch_size].shape)
+            # print('input_batch.shape', input_batch.shape)
+            # print('input_batch[0:batch_size].shape', input_batch[0:batch_size].shape)
             # 1/0
             res = self.model(input_batch[0:batch_size])
 
@@ -327,7 +327,7 @@ class RealESRGAN:
             for i in range(batch_size, img.shape[0], batch_size):
                 print('i is', i)
                 res = torch.cat((res, self.model(img[i:i+batch_size])), 0)
-                print('res.shape 2', res.shape)
+                # print('res.shape 2', res.shape)
         print('inference alone takes', time.time() - start2)
         # print('res.shape 3', res.shape)
 
@@ -479,14 +479,14 @@ class RRDBNet(nn.Module):
         self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
 
     def forward(self, x):
-        print('IN FORWARD, X.shape is', x.shape)
+        # print('IN FORWARD, X.shape is', x.shape)
         if self.scale == 2:
             feat = pixel_unshuffle(x, scale=2)
         elif self.scale == 1:
             feat = pixel_unshuffle(x, scale=4)
         else:
             feat = x
-        print('feat shape', feat.shape)
+        # print('feat shape', feat.shape)
         # breaks here ...
         feat = self.conv_first(feat)
         body_feat = self.conv_body(self.body(feat))
@@ -511,13 +511,13 @@ def pad_reflect(image, pad_size):
     print('imsize', imsize)
     new_img = np.zeros([height+pad_size*2, width+pad_size*2, imsize[2]]).astype(np.uint8)
     new_img[pad_size:-pad_size, pad_size:-pad_size, :] = image
-    print('new_img.shape 1', new_img.shape)
+    # print('new_img.shape 1', new_img.shape)
 
     new_img[0:pad_size, pad_size:-pad_size, :] = np.flip(image[0:pad_size, :, :], axis=0) #top
     new_img[-pad_size:, pad_size:-pad_size, :] = np.flip(image[-pad_size:, :, :], axis=0) #bottom
     new_img[:, 0:pad_size, :] = np.flip(new_img[:, pad_size:pad_size*2, :], axis=1) #left
     new_img[:, -pad_size:, :] = np.flip(new_img[:, -pad_size*2:-pad_size, :], axis=1) #right
-    print('new_img.shape 2', new_img.shape)
+    # print('new_img.shape 2', new_img.shape)
 
     return new_img