Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
Duplicated from
haodongli/Lotus_Depth
sciencellama
/
Lotus_Depth
like
1
Running
on
Zero
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
Lotus_Depth
9.34 MB
Ctrl+K
Ctrl+K
2 contributors
History:
66 commits
sciencellama
Add /normal16 endpoint: raw float16 normals (.npy) to avoid 8-bit quantisation grain
c6a2f5f
verified
30 days ago
files
update for video depth
over 1 year ago
utils
Update to export depth maps for depth estimation as 16bits, not 8 bits
over 1 year ago
.gitattributes
Safe
1.69 kB
update gitattributes
over 1 year ago
.gitignore
Safe
44 Bytes
v1
over 1 year ago
README.md
Safe
286 Bytes
Switch to ZeroGPU hardware (model requires float16 = GPU)
about 1 month ago
app.py
Safe
7.74 kB
Add /normal16 endpoint: raw float16 normals (.npy) to avoid 8-bit quantisation grain
30 days ago
infer.py
Safe
12.3 kB
Add /normal16 endpoint: raw float16 normals (.npy) to avoid 8-bit quantisation grain
30 days ago
pipeline.py
Safe
66 kB
Remove unused import tensorboard
about 1 month ago
requirements.txt
Safe
120 Bytes
Pin transformers==4.44.0 (has FLAX_WEIGHTS_NAME); add torchvision
about 1 month ago
