cleanup

README.md

@@ -67,33 +67,31 @@
 
 ## 🔧 Installation
 
-### From PyPI / Source
+### Conda
+1. Clone Repo
     ```bash
-# install from repo
+    git clone https://github.com/pq-yang/MatAnyone2
-pip install git+https://github.com/pq-yang/MatAnyone2.git#egg=matanyone2
+    cd MatAnyone2
-
-# or install optional extras
-pip install  git+https://github.com/pq-yang/MatAnyone2.git#egg=matanyone2[gui]    # Gradio demo + PySide6
-pip install  git+https://github.com/pq-yang/MatAnyone2.git#egg=matanyone2[dev]    # development / evaluation tools
-pip install  git+https://github.com/pq-yang/MatAnyone2.git#egg=matanyone2[all]    # everything
     ```
 
-### Conda
+2. Create Conda Environment and Install Dependencies
     ```bash
+    # create new conda env
     conda create -n matanyone2 python=3.10 -y
     conda activate matanyone2
-pip install  git+https://github.com/pq-yang/MatAnyone2.git#egg=matanyone2[all]
+
+    # install python dependencies
+    pip install -e .
+    # [optional] install python dependencies for gradio demo
+    pip3 install -r hugging_face/requirements.txt
     ```
 
-### uv (recommended)
+### uv
+You may also install via [uv](https://docs.astral.sh/uv/):
 ```bash
 # create a new project and add matanyone2
 uv init my-matting-project && cd my-matting-project
 uv add matanyone2@git+https://github.com/pq-yang/MatAnyone2.git
-
-# or with optional extras
-uv add matanyone2[gui]@git+https://github.com/pq-yang/MatAnyone2.git
-uv add matanyone2[all]@git+https://github.com/pq-yang/MatAnyone2.git
 ```
 
 ## 🔥 Inference
@@ -122,23 +120,29 @@ Run the following command to try it out:
 
 ```shell
 # intput format: video folder
-matanyone2 -i inputs/video/test-sample1 -m inputs/mask/test-sample1.png
+python inference_matanyone2.py -i inputs/video/test-sample1 -m inputs/mask/test-sample1.png
 
 # intput format: mp4
-matanyone2 -i inputs/video/test-sample2.mp4 -m inputs/mask/test-sample2.png
+python inference_matanyone2.py -i inputs/video/test-sample2.mp4 -m inputs/mask/test-sample2.png
-
-# or via python
-python inference_matanyone2.py -i inputs/video/test-sample1 -m inputs/mask/test-sample1.png
 ```
-The results will be saved in the `results` folder, including the foreground output video and the alpha output video.
+- The results will be saved in the `results` folder, including the foreground output video and the alpha output video.
+- If you want to save the results as per-frame images, you can set `--save-image`.
+- If you want to set a limit for the maximum input resolution, you can set `--max-size`, and the video will be downsampled if min(w, h) exceeds. By default, we don't set the limit.
 
-### Python API (recommended 🔥)
+### uv
+If you install via uv, you may try the following command:
+```shell
+matanyone2 -i inputs/video/test-sample1 -m inputs/mask/test-sample1.png
+```
+- Run `matanyone2 --help` for a full list of options.
+
+### Python API 🤗
 You can load the model directly from Hugging Face using `from_pretrained` and run inference programmatically:
 
 ```python
 from matanyone2 import MatAnyone2, InferenceCore
 
-model = MatAnyone2.from_pretrained("not-lain/matanyone2")
+model = MatAnyone2.from_pretrained("PeiqingYang/MatAnyone2")
 processor = InferenceCore(model, device="cuda:0")
 processor.process_video(
     input_path="inputs/video/test-sample2.mp4",
@@ -146,9 +150,6 @@ processor.process_video(
     output_path="results",
 )
 ``` 
-- If you want to save the results as per-frame images, you can set `--save-image`.
-- If you want to set a limit for the maximum input resolution, you can set `--max-size`, and the video will be downsampled if min(w, h) exceeds. By default, we don't set the limit.
-- Run `matanyone2 --help` for a full list of options.
 
 ## 🎪 Interactive Demo
 To get rid of the preparation for first-frame segmentation mask, we prepare a gradio demo on [hugging face](https://huggingface.co/spaces/PeiqingYang/MatAnyone2) and could also **launch locally**. Just drop your video/image, assign the target masks with a few clicks, and get the the matting results!
@@ -158,7 +159,7 @@ To get rid of the preparation for first-frame segmentation mask, we prepare a gr
 ```shell
 cd hugging_face
 
-# install GUI dependencies (if not already installed via pip install -e ".[gui]")
+# install GUI dependencies
 pip3 install -r requirements.txt # FFmpeg required
 
 # launch the demo

matanyone2/utils/inference_utils.py

@@ -4,6 +4,7 @@ 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')
@@ -11,18 +12,8 @@ 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]
-        cap = cv2.VideoCapture(frame_root)
+        frames, _, info = torchvision.io.read_video(filename=frame_root, pts_unit='sec', output_format='TCHW') # RGB
-        fps = cap.get(cv2.CAP_PROP_FPS)
+        fps = info['video_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 = []

pyproject.toml

@@ -22,54 +22,35 @@ classifiers = [
   "Operating System :: OS Independent",
 ]
 dependencies = [
+  'cython',
+  'gitpython >= 3.1',
+  'thinplate@git+https://github.com/cheind/py-thin-plate-spline',
+  'hickle >= 5.0',
+  'tensorboard >= 2.11',
   'numpy >= 1.21',
   'Pillow >= 9.5',
   'opencv-python >= 4.8',
   'scipy >= 1.7',
+  'pycocotools >= 2.0.7',
   'tqdm >= 4.66.1',
+  'gradio >= 3.34',
+  'gdown >= 4.7.1',
   'einops >= 0.6',
   'hydra-core >= 1.3.2',
-  'requests',
+  'PySide6 >= 6.2.0',
-  'imageio >= 2.25.0',
+  'charset-normalizer >= 3.1.0',
-  'imageio[ffmpeg]',
+  'netifaces >= 0.11.0',
-  'huggingface_hub >= 0.25.0',
+  'cchardet >= 2.1.7',
-  'safetensors',
-  'kornia',
   'easydict',
-  'torch',
+  'av >= 0.5.2',
-  'torchvision',
+  'requests',
-  'typer >= 0.9.0',
-  "av>=16.1.0",
-]
-
-[project.optional-dependencies]
-dev = [
-  'cython',
-  'gitpython >= 3.1',
-  'thinplate@git+https://github.com/cheind/py-thin-plate-spline',
-  'hickle >= 5.0',
-  'tensorboard >= 2.11',
-  'pycocotools >= 2.0.7',
-  'gdown >= 4.7.1',
-  'xlsxwriter',
-]
-gui = [
-  'gradio >= 6.9.0',
-  'PySide6 >= 6.2.0',
   'pyqtdarktheme',
-]
+  'imageio == 2.25.0',
-all = [
+  'imageio[ffmpeg]',
-  'cython',
+  'huggingface_hub == 0.36.2',
-  'gitpython >= 3.1',
+  'safetensors',
-  'thinplate@git+https://github.com/cheind/py-thin-plate-spline',
-  'hickle >= 5.0',
-  'tensorboard >= 2.11',
-  'pycocotools >= 2.0.7',
-  'gdown >= 4.7.1',
   'xlsxwriter',
-  'gradio >= 6.9.0',
+  'kornia',
-  'PySide6 >= 6.2.0',
-  'pyqtdarktheme',
 ]
 
 [project.scripts]
@@ -104,3 +85,6 @@ torchvision = { index = "pytorch-cu128" }
 [project.urls]
 "Homepage" = "https://github.com/pq-yang/MatAnyone2"
 "Bug Tracker" = "https://github.com/pq-yang/MatAnyone2/issues"
+
+[tool.setuptools]
+package-dir = {"" = "."}