Merge pull request #358 from glide-the/rile

bug fix rife

Author: zRzRzRzRzRzRzR

inference/gradio_composite_demo/rife_model.py

@@ -8,8 +8,9 @@
 import logging
 import skvideo.io
 from rife.RIFE_HDv3 import Model
-
+from huggingface_hub import hf_hub_download, snapshot_download
 logger = logging.getLogger(__name__)
+
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
 
@@ -18,8 +19,8 @@ def pad_image(img, scale):
     tmp = max(32, int(32 / scale))
     ph = ((h - 1) // tmp + 1) * tmp
     pw = ((w - 1) // tmp + 1) * tmp
-    padding = (0, 0, pw - w, ph - h)
-    return F.pad(img, padding)
+    padding = (0,  pw - w, 0, ph - h)
+    return F.pad(img, padding), padding
 
 
 def make_inference(model, I0, I1, upscale_amount, n):
@@ -36,30 +37,56 @@ def make_inference(model, I0, I1, upscale_amount, n):
 
 @torch.inference_mode()
 def ssim_interpolation_rife(model, samples, exp=1, upscale_amount=1, output_device="cpu"):
-
+    print(f"samples dtype:{samples.dtype}")
+    print(f"samples shape:{samples.shape}")
     output = []
+    pbar = utils.ProgressBar(samples.shape[0], desc="RIFE inference")
     # [f, c, h, w]
     for b in range(samples.shape[0]):
         frame = samples[b : b + 1]
         _, _, h, w = frame.shape
+        
         I0 = samples[b : b + 1]
         I1 = samples[b + 1 : b + 2] if b + 2 < samples.shape[0] else samples[-1:]
-        I1 = pad_image(I1, upscale_amount)
+         
+        I0, padding = pad_image(I0, upscale_amount)
+        I0 = I0.to(torch.float)
+        I1, _ = pad_image(I1, upscale_amount)
+        I1 = I1.to(torch.float)
+         
         # [c, h, w]
         I0_small = F.interpolate(I0, (32, 32), mode="bilinear", align_corners=False)
         I1_small = F.interpolate(I1, (32, 32), mode="bilinear", align_corners=False)
 
         ssim = ssim_matlab(I0_small[:, :3], I1_small[:, :3])
 
         if ssim > 0.996:
-            I1 = I0
-            I1 = pad_image(I1, upscale_amount)
+            I1 = samples[b : b + 1]
+            # print(f'upscale_amount:{upscale_amount}')
+            # print(f'ssim:{upscale_amount}')
+            # print(f'I0 shape:{I0.shape}')
+            # print(f'I1 shape:{I1.shape}')
+            I1, padding = pad_image(I1, upscale_amount)
+            # print(f'I0 shape:{I0.shape}')
+            # print(f'I1 shape:{I1.shape}')
             I1 = make_inference(model, I0, I1, upscale_amount, 1)
-
-            I1_small = F.interpolate(I1[0], (32, 32), mode="bilinear", align_corners=False)
-            ssim = ssim_matlab(I0_small[:, :3], I1_small[:, :3])
-            frame = I1[0]
+            
+            # print(f'I0 shape:{I0.shape}')
+            # print(f'I1[0] shape:{I1[0].shape}') 
             I1 = I1[0]
+            
+            # print(f'I1[0] unpadded shape:{I1.shape}') 
+            I1_small = F.interpolate(I1, (32, 32), mode="bilinear", align_corners=False)
+            ssim = ssim_matlab(I0_small[:, :3], I1_small[:, :3])
+            if padding[3] > 0 and padding[1] >0 :
+
+                frame = I1[:, :, : -padding[3],:-padding[1]]
+            elif padding[3] > 0:
+                frame = I1[:, :, : -padding[3],:]
+            elif padding[1] >0:
+                frame = I1[:, :, :,:-padding[1]]
+            else:
+                frame = I1
 
         tmp_output = []
         if ssim < 0.2:
@@ -69,10 +96,17 @@ def ssim_interpolation_rife(model, samples, exp=1, upscale_amount=1, output_devi
         else:
             tmp_output = make_inference(model, I0, I1, upscale_amount, 2**exp - 1) if exp else []
 
-        frame = pad_image(frame, upscale_amount)
-        tmp_output = [frame] + tmp_output
-        for i, frame in enumerate(tmp_output):
-            output.append(frame.to(output_device))
+        frame, _ = pad_image(frame, upscale_amount)
+        # print(f'frame shape:{frame.shape}')
+
+        frame = F.interpolate(frame, size=(h, w))
+        output.append(frame.to(output_device))
+        for i, tmp_frame in enumerate(tmp_output): 
+
+            # tmp_frame, _ = pad_image(tmp_frame, upscale_amount)
+            tmp_frame = F.interpolate(tmp_frame, size=(h, w))
+            output.append(tmp_frame.to(output_device))
+        pbar.update(1)
     return output
 
 
@@ -94,14 +128,26 @@ def frame_generator(video_capture):
 
 
 def rife_inference_with_path(model, video_path):
+    # Open the video file
     video_capture = cv2.VideoCapture(video_path)
-    tot_frame = video_capture.get(cv2.CAP_PROP_FRAME_COUNT)
+    fps = video_capture.get(cv2.CAP_PROP_FPS)  # Get the frames per second
+    tot_frame = int(video_capture.get(cv2.CAP_PROP_FRAME_COUNT))  # Total frames in the video
     pt_frame_data = []
     pt_frame = skvideo.io.vreader(video_path)
-    for frame in pt_frame:
+    # Cyclic reading of the video frames
+    while video_capture.isOpened():
+        ret, frame = video_capture.read()
+
+        if not ret:
+            break
+
+        # BGR to RGB
+        frame_rgb = frame[..., ::-1]
+        frame_rgb = frame_rgb.copy()
+        tensor = torch.from_numpy(frame_rgb).float().to("cpu", non_blocking=True).float() / 255.0
         pt_frame_data.append(
-            torch.from_numpy(np.transpose(frame, (2, 0, 1))).to("cpu", non_blocking=True).float() / 255.0
-        )
+            tensor.permute(2, 0, 1)
+        )  # to [c, h, w,]
 
     pt_frame = torch.from_numpy(np.stack(pt_frame_data))
     pt_frame = pt_frame.to(device)
@@ -122,8 +168,17 @@ def rife_inference_with_latents(model, latents):
     for i in range(latents.size(0)):
         #  [f, c, w, h]
         latent = latents[i]
+
         frames = ssim_interpolation_rife(model, latent)
         pt_image = torch.stack([frames[i].squeeze(0) for i in range(len(frames))])  # (to [f, c, w, h])
         rife_results.append(pt_image)
 
     return torch.stack(rife_results)
+
+
+# if __name__ == "__main__":
+#     snapshot_download(repo_id="AlexWortega/RIFE", local_dir="model_rife")
+#     model = load_rife_model("model_rife")
+ 
+#     video_path = rife_inference_with_path(model, "/mnt/ceph/develop/jiawei/CogVideo/output/20241003_130720.mp4")
+#     print(video_path)