Support inference on MacOS with MPS or CPU and add face detection script

.gitignore

@@ -0,0 +1,180 @@
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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/
+
+# PyPI configuration file
+.pypirc
+
+*-bk
+*_bk
+*-bk*
+*_bk*
+*copy*
+
+# MacOS
+.DS_Store

README.md

@@ -94,16 +94,31 @@ conda env create -f environment.yml
 source activate deep3d_pytorch
 ```
 
-2. Install Nvdiffrast library:
-```
-git clone -b 0.3.0 https://github.com/NVlabs/nvdiffrast
-cd nvdiffrast    # ./Deep3DFaceRecon_pytorch/nvdiffrast
-pip install .
-```
+2. Install mesh renderer:
+   1.  Nvdiffrast library (necessary for training, optional for testing):
+    ```
+    git clone -b 0.3.0 https://github.com/NVlabs/nvdiffrast
+    cd nvdiffrast    # ./Deep3DFaceRecon_pytorch/nvdiffrast
+    pip install .
+    cd ..    # ./Deep3DFaceRecon_pytorch
+    ```
+   2.  Use a cpu renderer from 3DDFA-V3 instead for testing (which can work on MacOS):
+    ```
+    git clone --depth=1 https://github.com/wang-zidu/3DDFA-V3
+    cp 3DDFA-V3/utils/cpu_renderer.py ./utils/
+    cp -r 3DDFA-V3/utils/cython_renderer ./utils/
+
+    pip install Cython
+
+    cd util/cython_renderer/
+    python setup.py build_ext -i
+    cd ../..     # ./Deep3DFaceRecon_pytorch
+    ```
+    3. Skip this step for inference/test, but you need run test.py with "--renderer_type none --no_viz" options
+
 
 3. Install Arcface Pytorch:
 ```
-cd ..    # ./Deep3DFaceRecon_pytorch
 git clone https://github.com/deepinsight/insightface.git
 cp -r ./insightface/recognition/arcface_torch ./models/
 ```
@@ -137,6 +152,24 @@ Deep3DFaceRecon_pytorch
 ```
 
 ### Test with custom images
+
+#### Face detection
+To detect 5 facial landmarks from test images, first we need install [InsightFace](https://github.com/deepinsight/insightface) library:
+```
+pip install insightface onnxruntime
+```
+or 
+```
+pip install insightface onnxruntime-gpu
+```
+
+and then, run the following command:
+```
+python detect_faces_by_insightface.py <folder_to_test_images>
+```
+
+#### Face reconstruction
+
 To reconstruct 3d faces from test images, organize the test image folder as follows:
 ```
 Deep3DFaceRecon_pytorch
@@ -159,6 +192,37 @@ python test.py --name=<model_name> --epoch=20 --img_folder=<folder_to_test_image
 # get reconstruction results of example images
 python test.py --name=<model_name> --epoch=20 --img_folder=./datasets/examples
 ```
+
+On **MacOS**, you can run the test script with CPU or Apple Silicon (M1, M2, M3 chips) by adding "--device cpu" or "--device mps" to the command. For example,
+
+run with MPS:
+```
+# get reconstruction results of your custom images
+python test.py --name=<model_name> --epoch=20 --img_folder=<folder_to_test_images> --device mps --renderer_type face3d
+
+# no visualization
+python test.py --name=<model_name> --epoch=20 --img_folder=<folder_to_test_images> --device mps --renderer_type none--no_viz
+
+# get reconstruction results of example images
+python test.py --name=<model_name> --epoch=20 --img_folder=./datasets/examples --device mps --renderer_type face3d
+
+# no visualization
+python test.py --name=<model_name> --epoch=20 --img_folder=./datasets/examples --device mps --renderer_type none --no_viz
+```
+
+or run with CPU:
+```
+# get reconstruction results of your custom images
+python test.py --name=<model_name> --epoch=20 --img_folder=<folder_to_test_images> --device cpu --renderer_type face3d
+
+python test.py --name=<model_name> --epoch=20 --img_folder=<folder_to_test_images> --device cpu --renderer_type none --no_viz
+
+# get reconstruction results of example images
+python test.py --name=<model_name> --epoch=20 --img_folder=./datasets/examples --device cpu --renderer_type face3d
+
+python test.py --name=<model_name> --epoch=20 --img_folder=./datasets/examples --device cpu --renderer_type none --no_viz
+```
+
 **_Following [#108](https://github.com/sicxu/Deep3DFaceRecon_pytorch/issues/108), if you don't have OpenGL environment, you can simply add "--use_opengl False" to use CUDA context. Make sure you have updated the nvdiffrast to the latest version._**
 
 Results will be saved into ./checkpoints/<model_name>/results/<folder_to_test_images>, which contain the following files:

detect_faces_by_insightface.py

@@ -0,0 +1,75 @@
+# coding=utf-8
+"""
+Detect faces and landmarks in images using the InsightFace library.
+
+Authors:
+    zhaoyafei (zhaoyafei0210@gmail.com, https://github.com/walkoncross)
+"""
+
+import os
+import os.path as osp
+
+import cv2
+from insightface.app import FaceAnalysis
+
+
+def detect_faces(input_dir):
+    # Initialize the face analysis app
+    app = FaceAnalysis(
+        allowed_modules=["detection", "alignment"],
+        providers=[
+            "CUDAExecutionProvider",
+            "CoreMLExecutionProvider",
+            "CPUExecutionProvider",
+        ],
+    )
+    app.prepare(ctx_id=0, det_size=(640, 640))
+
+    # Create the output directory if it doesn't exist
+    output_dir = os.path.join(input_dir, "detections")
+    os.makedirs(output_dir, exist_ok=True)
+
+    # Iterate over all images in the input directory
+    file_list = [
+        ff
+        for ff in os.listdir(input_dir)
+        if osp.splitext(ff)[-1].lower() in [".png", ".jpg", ".jpeg", ".bmp"]
+    ]
+
+    print(f"--> image files: \n{file_list}")
+
+    for ii, filename in enumerate(file_list):
+        print(f"--> {ii}: {filename}")
+        image_path = os.path.join(input_dir, filename)
+        img = cv2.imread(image_path)
+
+        # Detect faces in the image
+        faces = app.get(img)
+
+        if faces:
+            print(f"Detected {len(faces)} faces")
+            # Get the face with the highest score
+            best_face = max(faces, key=lambda face: face["det_score"])
+
+            # Get the 5 key points of the best face
+            keypoints = best_face["kps"]
+
+            # Write the key points to a txt file
+            output_path = os.path.join(
+                output_dir, f"{os.path.splitext(filename)[0]}.txt"
+            )
+            with open(output_path, "w") as f:
+                for point in keypoints:
+                    f.write(f"{point[0]} {point[1]}\n")
+        else:
+            print(f"No faces detected")
+
+
+if __name__ == "__main__":
+    import argparse
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("input_dir", help="Directory containing images")
+    args = parser.parse_args()
+
+    detect_faces(args.input_dir)

models/.gitignore

@@ -0,0 +1 @@
+arcface_torch/

models/base_model.py

@@ -152,15 +152,16 @@ def eval(self):
                 net = getattr(self, name)
                 net.eval()
 
-    def test(self):
+    def test(self, do_render=True):
         """Forward function used in test time.
 
         This function wraps <forward> function in no_grad() so we don't save intermediate steps for backprop
         It also calls <compute_visuals> to produce additional visualization results
         """
         with torch.no_grad():
-            self.forward()
-            self.compute_visuals()
+            self.forward(do_render=do_render)
+            if do_render:
+                self.compute_visuals()
 
     def compute_visuals(self):
         """Calculate additional output images for visdom and HTML visualization"""