Skip to content

Update inference.py #13

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
AnirbanMukherjeeXD wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Update inference.py #13

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
21991d5
Update inference.py
AnirbanMukherjeeXD Dec 19, 2023
c7e3dec
Update inference.py
AnirbanMukherjeeXD Feb 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 6 additions & 4 deletions inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,5 @@
### INFERENCE.PY:

import argparse
import subprocess
import python_speech_features
Expand Down Expand Up @@ -40,7 +42,7 @@ def draw_annotation_box( image, rotation_vector, translation_vector, color=(255,
point_3d.append((front_size, front_size, front_depth))
point_3d.append((front_size, -front_size, front_depth))
point_3d.append((-front_size, -front_size, front_depth))
point_3d = np.array(point_3d, dtype=np.float).reshape(-1, 3)
point_3d = np.array(point_3d, dtype=float).reshape(-1, 3)

# Map to 2d image points
(point_2d, _) = cv2.projectPoints(point_3d,
Expand Down Expand Up @@ -138,15 +140,15 @@ def audio2head(audio_path, img_path, model_path, save_path):

config_file = r"./config/vox-256.yaml"
with open(config_file) as f:
config = yaml.load(f)
config = yaml.safe_load(f)
kp_detector = KPDetector(**config['model_params']['kp_detector_params'],
**config['model_params']['common_params'])
generator = OcclusionAwareGenerator(**config['model_params']['generator_params'],
**config['model_params']['common_params'])
kp_detector = kp_detector.cuda()
generator = generator.cuda()

opt = argparse.Namespace(**yaml.load(open("./config/parameters.yaml")))
opt = argparse.Namespace(**yaml.safe_load(open("./config/parameters.yaml")))
audio2kp = AudioModel3D(opt).cuda()

checkpoint = torch.load(model_path)
Expand Down Expand Up @@ -248,4 +250,4 @@ def audio2head(audio_path, img_path, model_path, save_path):
parse = parser.parse_args()

os.makedirs(parse.save_path,exist_ok=True)
audio2head(parse.audio_path,parse.img_path,parse.model_path,parse.save_path)
audio2head(parse.audio_path,parse.img_path,parse.model_path,parse.save_path)