https://github.com/clibdev/ssr_net_pytorch
SSR-Net in Pytorch and ONNX
Science Score: 13.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (6.1%) to scientific vocabulary
Repository
SSR-Net in Pytorch and ONNX
Basic Info
Statistics
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
- Releases: 1
Metadata Files
ReadMe.md
Fork of oukohou/SSRNetPytorch
Differences between original repository and fork:
- Compatibility with PyTorch >=2.4. (🔥)
- Original pretrained models and converted ONNX models from GitHub releases page. (🔥)
- Model conversion to ONNX format using the export.py file. (🔥)
- Installation with updated requirements.txt file.
- The following deprecations has been fixed:
- FutureWarning: You are using 'torch.load' with 'weights_only=False'.
Installation
shell
pip install -r requirements.txt
Pretrained models
- Download links:
| Name | Model Size (MB) | Link | SHA-256 |
|---------|-----------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------|
| SSR-Net | 0.6
0.2 | PyTorch, ONNX | bcf6d1413f9b0e70095eb20b5d95e3d13e1e73ad8c1585a62278c170bcfeda4c
5e97869699ce0d7b9a3c1fbf034011f140cf61ba037d37ead96d1740c1ed7a88 |
- Evaluation results on MegaAge_Asian dataset:
| Name | Train | Valid | Test |
|---------|----------------------------------------------------|--------------------------------------------------|---------------------------------------------------|
| SSR-Net | Train Loss: 2.9401
CA3: 0.6326
CA5: 0.8123 | Val Loss: 4.7221
CA3: 0.4438
CA5: 0.6295 | Test Loss: 3.9311
CA3: 0.5151
CA5: 0.7163 |
Inference
shell
python inference_images.py --graph ssr-net.pth --image data/images/88_megaage_asian_32_age.jpg
Export to ONNX format
shell
pip install onnx
shell
python export.py --weights ssr-net.pth
Owner
- Login: clibdev
- Kind: user
- Repositories: 1
- Profile: https://github.com/clibdev