fix(video) remove file:// prefix for torchvision < 0.19.0

qwen-vl-utils/pyproject.toml

@@ -9,6 +9,7 @@ dependencies = [
     "requests",
     "pillow",
     "av",
+    "packaging",
 ]
 readme = "README.md"
 requires-python = ">= 3.8"

qwen-vl-utils/requirements-dev.lock

@@ -64,6 +64,8 @@ nvidia-nvjitlink-cu12==12.6.68
     # via nvidia-cusparse-cu12
 nvidia-nvtx-cu12==12.1.105
     # via torch
+packaging==24.1
+    # via qwen-vl-utils
 pillow==10.2.0
     # via qwen-vl-utils
     # via torchvision

qwen-vl-utils/requirements.lock

@@ -22,6 +22,8 @@ idna==3.4
     # via requests
 numpy==1.24.4
     # via decord
+packaging==24.1
+    # via qwen-vl-utils
 pillow==10.2.0
     # via qwen-vl-utils
 requests==2.28.1

qwen-vl-utils/src/qwen_vl_utils/vision_process.py

@@ -6,11 +6,14 @@
 import os
 import sys
 import time
+import warnings
 from functools import lru_cache
 from io import BytesIO
 
 import requests
 import torch
+import torchvision
+from packaging import version
 from PIL import Image
 from torchvision import io, transforms
 from torchvision.transforms import InterpolationMode
@@ -174,6 +177,11 @@ def _read_video_torchvision(
         torch.Tensor: the video tensor with shape (T, C, H, W).
     """
     video_path = ele["video"]
+    if version(torchvision.__version__) < version.parse("0.19.0"):
+        if "http://" in video_path or "https://" in video_path:
+            warnings.warn("torchvision < 0.19.0 does not support http/https video path, please upgrade to 0.19.0.")
+        if "file://" in video_path:
+            video_path = video_path[7:]
     st = time.time()
     video, audio, info = io.read_video(
         video_path,