fix bugs and edge cases

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

depth_anything_v2/dpt.py

@@ -175,10 +175,10 @@ def __init__(
 
         self.device = 'cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu'
         self.mean_tensor = (
-            torch.tensor([0.485, 0.456, 0.406]).view(3, 1, 1).to(self.DEVICE)
+            torch.tensor([0.485, 0.456, 0.406]).view(3, 1, 1).to(self.device)
         )
         self.std_tensor = (
-            torch.tensor([0.229, 0.224, 0.225]).view(3, 1, 1).to(self.DEVICE)
+            torch.tensor([0.229, 0.224, 0.225]).view(3, 1, 1).to(self.device)
         )
 
     def forward(self, x):
@@ -229,7 +229,7 @@ def image2tensor(self, frame, input_size=518, precision: str = 'fp32', newHeight
         """
 
         h, w = frame.shape[:2]
-        frame = frame.to(self.device).mul(1.0 / 255.0).permute(2, 0, 1).unsqueeze(0)
+        frame = torch.from_numpy(frame).to(self.device).mul(1.0 / 255.0).permute(2, 0, 1).unsqueeze(0)
         frame = F.interpolate(
             frame.float(),
             (newHeight, newWidth),

requirements.txt

@@ -3,5 +3,6 @@ gradio_imageslider
 gradio==4.29.0
 matplotlib
 opencv-python
+tqdm
 torch==2.2.2
 torchvision=0.17.2

run_video.py

@@ -6,6 +6,7 @@
 import os
 import torch
 
+from tqdm import tqdm
 from depth_anything_v2.dpt import DepthAnythingV2
 
 
@@ -20,7 +21,7 @@
 
     parser.add_argument('--pred-only', dest='pred_only', action='store_true', help='only display the prediction')
     parser.add_argument('--grayscale', dest='grayscale', action='store_true', help='do not apply colorful palette')
-    parser.set_defaults("--precision", type=str, default='fp32', choices= ['fp32', 'fp16'])
+    parser.add_argument("--precision", type=str, default='fp32', choices= ['fp32', 'fp16'])
 
     args = parser.parse_args()
 
@@ -37,8 +38,13 @@
     depth_anything.load_state_dict(torch.load(f'checkpoints/depth_anything_v2_{args.encoder}.pth', map_location='cpu'))
     depth_anything = depth_anything.to(DEVICE).eval()
 
-    if args.precision == 'fp16':
+    if args.precision == 'fp16' and DEVICE == 'cuda':
         depth_anything = depth_anything.half()
+    else:
+        print('FP16 precision is only available on CUDA devices. Using FP32 instead.')
+        args.precision = 'fp32'
+        depth_anything = depth_anything.float()
+
 
     if os.path.isfile(args.video_path):
         if args.video_path.endswith('txt'):
@@ -77,7 +83,9 @@
         output_path = os.path.join(args.outdir, os.path.splitext(os.path.basename(filename))[0] + '.mp4')
         out = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*"mp4v"), frame_rate, (output_width, frame_height))
 
-        while raw_video.isOpened():
+        totalFrameCount = int(raw_video.get(cv2.CAP_PROP_FRAME_COUNT))
+
+        for _ in tqdm(range(totalFrameCount)):
             ret, raw_frame = raw_video.read()
             if not ret:
                 break