Update app.py

app.py

@@ -72,28 +72,28 @@ def classify_image(inp):
     prediction = model(img_t.unsqueeze(0)).softmax(-1).flatten()
 
     modulator = model.layers[0].blocks[11].modulation.modulator.norm(2, 1, keepdim=True)
-    modulator = nn.Upsample(size=img_t.shape[1:], mode='bilinear')(modulator)
+    # modulator = nn.Upsample(size=img_t.shape[1:], mode='bilinear')(modulator)
     modulator = modulator.squeeze(1).detach().permute(1, 2, 0).numpy()
     modulator = (modulator - modulator.min()) / (modulator.max() - modulator.min())
-    cam0 = show_cam_on_image(img_d, modulator, use_rgb=True)
+    cam0 = np.uint8(255 * modulator)  # show_cam_on_image(img_d, modulator, use_rgb=True)
 
     modulator = model.layers[0].blocks[8].modulation.modulator.norm(2, 1, keepdim=True)
-    modulator = nn.Upsample(size=img_t.shape[1:], mode='bilinear')(modulator)
+    # modulator = nn.Upsample(size=img_t.shape[1:], mode='bilinear')(modulator)
     modulator = modulator.squeeze(1).detach().permute(1, 2, 0).numpy()
     modulator = (modulator - modulator.min()) / (modulator.max() - modulator.min())
-    cam1 = show_cam_on_image(img_d, modulator, use_rgb=True)
+    cam1 = np.uint8(255 * modulator) # show_cam_on_image(img_d, modulator, use_rgb=True)
 
     modulator = model.layers[0].blocks[5].modulation.modulator.norm(2, 1, keepdim=True)
-    modulator = nn.Upsample(size=img_t.shape[1:], mode='bilinear')(modulator)
+    # modulator = nn.Upsample(size=img_t.shape[1:], mode='bilinear')(modulator)
     modulator = modulator.squeeze(1).detach().permute(1, 2, 0).numpy()
     modulator = (modulator - modulator.min()) / (modulator.max() - modulator.min())
-    cam2 = show_cam_on_image(img_d, modulator, use_rgb=True)
+    cam2 = np.uint8(255 * modulator) # show_cam_on_image(img_d, modulator, use_rgb=True)
 
     modulator = model.layers[0].blocks[2].modulation.modulator.norm(2, 1, keepdim=True)
-    modulator = nn.Upsample(size=img_t.shape[1:], mode='bilinear')(modulator)
+    # modulator = nn.Upsample(size=img_t.shape[1:], mode='bilinear')(modulator)
     modulator = modulator.squeeze(1).detach().permute(1, 2, 0).numpy()
     modulator = (modulator - modulator.min()) / (modulator.max() - modulator.min())
-    cam3 = show_cam_on_image(img_d, modulator, use_rgb=True)
+    cam3 = np.uint8(255 * modulator) # show_cam_on_image(img_d, modulator, use_rgb=True)
 
     return {labels[i]: float(prediction[i]) for i in range(1000)}, Image.fromarray(cam0), Image.fromarray(cam1), Image.fromarray(cam2), Image.fromarray(cam3)