Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
pesi
/
rtmo
like
3
Follow
Prime Electronics and Satellitics Inc.
13
Object Detection
ONNX
Pose Estimation
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
0cdc9a7
rtmo
503 MB
Ctrl+K
Ctrl+K
3 contributors
History:
38 commits
luigi-liu-tw
Support Inference over batch with TensorRT Engine Model
0cdc9a7
about 2 years ago
video
Add a sample video
over 2 years ago
.gitattributes
Safe
1.66 kB
Add a sample video
over 2 years ago
README.md
Safe
1.47 kB
Update README.md
over 2 years ago
constant_folding.sh
Safe
337 Bytes
Apply constant folding
over 2 years ago
convert_to_fp16.py
Safe
1.25 kB
Re-quantize models in FP16 in keep positional encoding in FP32 to avoid bad accuracy
over 2 years ago
convert_to_fp16_all.py
Safe
1.36 kB
Bugfix: correct batch dimension fixation then regenerate ONNX models
over 2 years ago
convert_to_mixed.py
Safe
5.26 kB
Improve Debug Message Layout in Validate Funciton
over 2 years ago
demo.sh
Safe
56 Bytes
Remove models with fixed batch size as dynamic batch is generally supported
over 2 years ago
demo_batch.sh
64 Bytes
Remove models with fixed batch size as dynamic batch is generally supported
over 2 years ago
onnx_to_engine.py
Safe
7.05 kB
Use dynamic batch size by default
about 2 years ago
rtmo-l.fp16.onnx
88 MB
xet
Re-quantize models in FP16 in keep positional encoding in FP32 to avoid bad accuracy
over 2 years ago
rtmo-l.onnx
Safe
176 MB
xet
Apply constant folding
over 2 years ago
rtmo-m.fp16.onnx
Safe
44.7 MB
xet
Re-quantize models in FP16 in keep positional encoding in FP32 to avoid bad accuracy
over 2 years ago
rtmo-m.onnx
Safe
89.3 MB
xet
Apply constant folding
over 2 years ago
rtmo-s.fp16.onnx
Safe
19.9 MB
xet
Re-quantize models in FP16 in keep positional encoding in FP32 to avoid bad accuracy
over 2 years ago
rtmo-s.onnx
Safe
39.6 MB
xet
Apply constant folding
over 2 years ago
rtmo-t.fp16.onnx
Safe
13.7 MB
xet
Re-quantize models in FP16 in keep positional encoding in FP32 to avoid bad accuracy
over 2 years ago
rtmo-t.onnx
Safe
27.4 MB
xet
Apply constant folding
over 2 years ago
rtmo_demo.py
1.99 kB
Resize in keeping aspect ratio in visualization
about 2 years ago
rtmo_demo_batch.py
3.06 kB
Resize in keeping aspect ratio in visualization
about 2 years ago
rtmo_gpu.py
21.8 kB
Support Inference over batch with TensorRT Engine Model
about 2 years ago
symbolic_shape_infer.py
Safe
138 kB
Make ONNX models compatible with ONNXruntime's TensorrtExecutionProvider
over 2 years ago
symbolic_shape_infer_all.sh
Safe
135 Bytes
Make ONNX models compatible with ONNXruntime's TensorrtExecutionProvider
over 2 years ago
