HF integration +uv + cli

matanyone2/utils/download_util.py

@@ -0,0 +1,109 @@
+import math
+import os
+import requests
+from torch.hub import download_url_to_file, get_dir
+from tqdm import tqdm
+from urllib.parse import urlparse
+
+def sizeof_fmt(size, suffix='B'):
+    """Get human readable file size.
+
+    Args:
+        size (int): File size.
+        suffix (str): Suffix. Default: 'B'.
+
+    Return:
+        str: Formated file siz.
+    """
+    for unit in ['', 'K', 'M', 'G', 'T', 'P', 'E', 'Z']:
+        if abs(size) < 1024.0:
+            return f'{size:3.1f} {unit}{suffix}'
+        size /= 1024.0
+    return f'{size:3.1f} Y{suffix}'
+
+
+def download_file_from_google_drive(file_id, save_path):
+    """Download files from google drive.
+    Ref:
+    https://stackoverflow.com/questions/25010369/wget-curl-large-file-from-google-drive  # noqa E501
+    Args:
+        file_id (str): File id.
+        save_path (str): Save path.
+    """
+
+    session = requests.Session()
+    URL = 'https://docs.google.com/uc?export=download'
+    params = {'id': file_id}
+
+    response = session.get(URL, params=params, stream=True)
+    token = get_confirm_token(response)
+    if token:
+        params['confirm'] = token
+        response = session.get(URL, params=params, stream=True)
+
+    # get file size
+    response_file_size = session.get(URL, params=params, stream=True, headers={'Range': 'bytes=0-2'})
+    print(response_file_size)
+    if 'Content-Range' in response_file_size.headers:
+        file_size = int(response_file_size.headers['Content-Range'].split('/')[1])
+    else:
+        file_size = None
+
+    save_response_content(response, save_path, file_size)
+
+
+def get_confirm_token(response):
+    for key, value in response.cookies.items():
+        if key.startswith('download_warning'):
+            return value
+    return None
+
+
+def save_response_content(response, destination, file_size=None, chunk_size=32768):
+    if file_size is not None:
+        pbar = tqdm(total=math.ceil(file_size / chunk_size), unit='chunk')
+
+        readable_file_size = sizeof_fmt(file_size)
+    else:
+        pbar = None
+
+    with open(destination, 'wb') as f:
+        downloaded_size = 0
+        for chunk in response.iter_content(chunk_size):
+            downloaded_size += chunk_size
+            if pbar is not None:
+                pbar.update(1)
+                pbar.set_description(f'Download {sizeof_fmt(downloaded_size)} / {readable_file_size}')
+            if chunk:  # filter out keep-alive new chunks
+                f.write(chunk)
+        if pbar is not None:
+            pbar.close()
+
+
+def load_file_from_url(url, model_dir=None, progress=True, file_name=None):
+    """Load file form http url, will download models if necessary.
+    Ref:https://github.com/1adrianb/face-alignment/blob/master/face_alignment/utils.py
+    Args:
+        url (str): URL to be downloaded.
+        model_dir (str): The path to save the downloaded model. Should be a full path. If None, use pytorch hub_dir.
+            Default: None.
+        progress (bool): Whether to show the download progress. Default: True.
+        file_name (str): The downloaded file name. If None, use the file name in the url. Default: None.
+    Returns:
+        str: The path to the downloaded file.
+    """
+    if model_dir is None:  # use the pytorch hub_dir
+        hub_dir = get_dir()
+        model_dir = os.path.join(hub_dir, 'checkpoints')
+
+    os.makedirs(model_dir, exist_ok=True)
+
+    parts = urlparse(url)
+    filename = os.path.basename(parts.path)
+    if file_name is not None:
+        filename = file_name
+    cached_file = os.path.abspath(os.path.join(model_dir, filename))
+    if not os.path.exists(cached_file):
+        print(f'Downloading: "{url}" to {cached_file}\n')
+        download_url_to_file(url, cached_file, hash_prefix=None, progress=progress)
+    return cached_file

matanyone2/utils/inference_utils.py

@@ -4,7 +4,6 @@ import random
 import numpy as np
 
 import torch
-import torchvision
 
 IMAGE_EXTENSIONS = ('.jpg', '.jpeg', '.png', '.JPG', '.JPEG', '.PNG')
 VIDEO_EXTENSIONS = ('.mp4', '.mov', '.avi', '.MP4', '.MOV', '.AVI')
@@ -12,8 +11,18 @@ VIDEO_EXTENSIONS = ('.mp4', '.mov', '.avi', '.MP4', '.MOV', '.AVI')
 def read_frame_from_videos(frame_root):
     if frame_root.endswith(VIDEO_EXTENSIONS):  # Video file path
         video_name = os.path.basename(frame_root)[:-4]
-        frames, _, info = torchvision.io.read_video(filename=frame_root, pts_unit='sec', output_format='TCHW') # RGB
-        fps = info['video_fps']
+        cap = cv2.VideoCapture(frame_root)
+        fps = cap.get(cv2.CAP_PROP_FPS)
+        if fps <= 0:
+            fps = 24
+        frames = []
+        while True:
+            ret, frame = cap.read()
+            if not ret:
+                break
+            frames.append(frame[..., [2, 1, 0]])  # BGR to RGB, HWC
+        cap.release()
+        frames = torch.Tensor(np.array(frames)).permute(0, 3, 1, 2).contiguous()  # TCHW
     else:
         video_name = os.path.basename(frame_root)
         frames = []