Fork of oukohou/SSR_Net_Pytorch

Differences between original repository and fork:

• Compatibility with PyTorch >=2.0. (🔥)
• 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.

Installation

pip install -r requirements.txt

Pretrained models

Name	Train	Valid	Test	Link
SSR-Net	Train Loss: 2.9401 CA_3: 0.6326 CA_5: 0.8123	Val Loss: 4.7221 CA_3: 0.4438 CA_5: 0.6295	Test Loss: 3.9311 CA_3: 0.5151 CA_5: 0.7163	PyTorch, ONNX

Note: results on MegaAge_Asian dataset.

Inference

python inference_images.py --graph pretrained_model/model_Adam_MSELoss_LRDecay_weightDecay0.0001_batch50_lr0.0005_epoch90_64x64.pth --image data/images/88_megaage_asian_32_age.jpg

Export to ONNX format

pip install onnx

python export.py --weights pretrained_model/model_Adam_MSELoss_LRDecay_weightDecay0.0001_batch50_lr0.0005_epoch90_64x64.pth