Skip to content

Improve HF integration #1

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
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Improve HF integration #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
22 changes: 22 additions & 0 deletions depth_anything/dpt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,6 +188,28 @@ class DepthAnything_AC(DPT_DINOv2):
def __init__(self, config):
super().__init__(**config)

def from_pretrained(self, repo_id: str, encoder='vits'):
from huggingface_hub import hf_hub_download

filepath = hf_hub_download(repo_id=repo_id, filename=f"checkpoints/depth_anything_AC_{encoder}.pth")

model_configs = {
'vitl': {'encoder': 'vitl', 'features': 256, 'out_channels': [256, 512, 1024, 1024], 'version': 'v2'},
'vitb': {'encoder': 'vitb', 'features': 128, 'out_channels': [96, 192, 384, 768], 'version': 'v2'},
'vits': {'encoder': 'vits', 'features': 64, 'out_channels': [48, 96, 192, 384], 'version': 'v2'}
}

model = self(**model_configs[encoder])
checkpoint = torch.load(filepath, map_location='cpu')
model.load_state_dict(checkpoint, strict=False)
model.eval()
if torch.cuda.is_available():
model.cuda()
print("Using GPU for inference")
else:
print("Using CPU for inference")

return model

def get_intermediate_features(self, x):
"""
Expand Down
24 changes: 1 addition & 23 deletions tools/infer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,28 +36,6 @@ def normalize_depth(disparity_tensor):
return normalized_disparity


def load_model(model_path, encoder='vits'):
"""Load trained depth estimation model"""
print(f"Loading model: {model_path}")
model_configs = {
'vitl': {'encoder': 'vitl', 'features': 256, 'out_channels': [256, 512, 1024, 1024], 'version': 'v2'},
'vitb': {'encoder': 'vitb', 'features': 128, 'out_channels': [96, 192, 384, 768], 'version': 'v2'},
'vits': {'encoder': 'vits', 'features': 64, 'out_channels': [48, 96, 192, 384], 'version': 'v2'}
}

model = DepthAnything_AC(model_configs[encoder])
checkpoint = torch.load(model_path, map_location='cpu')
model.load_state_dict(checkpoint, strict=False)
model.eval()
if torch.cuda.is_available():
model.cuda()
print("Using GPU for inference")
else:
print("Using CPU for inference")

return model


def preprocess_image(image_path, target_size=518):
"""Preprocess input image"""

Expand Down Expand Up @@ -503,7 +481,7 @@ def main():
return

try:
model = load_model(args.model, args.encoder)
model = DepthAnything_AC.from_pretrained(args.model, args.encoder)
except Exception as e:
print(f"Failed to load model: {str(e)}")
return
Expand Down