autism_plus_edynamix_demo_14

src/minicpm/response.py

@@ -2,7 +2,8 @@
 import sys
 import gradio as gr
 import spaces
-
+from decord import VideoReader, cpu
+from PIL import Image
 # Local imports
 from src.config import (
     device,
@@ -18,7 +19,24 @@ from src.exception import CustomExceptionHandling
 
 # Model, tokenizer and processor
 model, tokenizer, processor = load_model_tokenizer_and_processor(model_name, device)
+MAX_NUM_FRAMES=64
+
+def encode_video(video_path):
+    MAX_NUM_FRAMES=64
+    def uniform_sample(l, n):
+        gap = len(l) / n
+        idxs = [int(i * gap + gap / 2) for i in range(n)]
+        return [l[i] for i in idxs]
 
+    vr = VideoReader(video_path, ctx=cpu(0))
+    sample_fps = round(vr.get_avg_fps() / 1)  # FPS
+    frame_idx = [i for i in range(0, len(vr), sample_fps)]
+    if len(frame_idx) > MAX_NUM_FRAMES:
+        frame_idx = uniform_sample(frame_idx, MAX_NUM_FRAMES)
+    frames = vr.get_batch(frame_idx).asnumpy()
+    frames = [Image.fromarray(v.astype('uint8')) for v in frames]
+    print('num frames:', len(frames))
+    return frames
 
 @spaces.GPU(duration=120)
 def describe_image(