视频的 Pytorch 数据集

如何解决视频的 Pytorch 数据集

嗨，我制作了一个视频帧加载器数据集，用于输入 pytorch 模型。我想从视频中采样帧，但应该从每个视频中统一采样帧。这是我想出来的课程。我想知道是否有更好的方法来加快采样过程。
您对 read_video 方法部分有什么建议吗？？
谢谢

import torch
import torchvision as tv
import cv2
import numpy as np

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
from pathlib import Path

class VideoLoader(torch.utils.data.Dataset):

  def __init__(self,data_path,classes,transforms=None,max_frames=None,frames_ratio=None):
    super(VideoLoader,self).__init__()

    self.data_path = data_path
    self.classes = classes
    self.frames_ratio = frames_ratio

    self.transforms = transforms
    self.max_frames = max_frames
  
  def read_video(self,path):
    frames = []

    vc = cv2.VideoCapture(path)

    total_frames = int(vc.get(cv2.CAP_PROP_FRAME_COUNT))
    
    if self.frames_ratio:
      if type(self.frames_ratio) is float:
        frames_to_pick = int(total_frames * self.frames_ratio)
      else:
        frames_to_pick = self.frames_ratio
    else:
        frames_to_pick = total_frames
    
    idxs = np.linspace(0,total_frames,frames_to_pick,endpoint=False)

    for i in idxs:
      ok,f = vc.read()
      if ok:

        f = tv.transforms.ToTensor()(f)
        f = self.transforms(f) if self.transforms else f
        frames.append(f)
        
        vc.set(cv2.CAP_PROP_POS_FRAMES,i)
        if self.max_frames and len(frames) == self.max_frames: break
      else: break
    vc.release()
    return torch.stack(frames)

  def __getitem__(self,index):
    v_path,label = self.data_path[index]
    return self.read_video(v_path),self.classes[label]

  def __len__(self): return len(self.data_path)