iqa_metric=pyiqa.create_metric('topiq_nr',device=device,**custom_opts)# Note that if you train the model with this package, the weights will be saved in weight_dict['params']. Otherwise, please set weight_keys=None.iqa_metric.load_weights('path/to/weights.pth',weight_keys='params')...
High-fidelity performance metrics for generative models in PyTorch - torch-fidelity/torch_fidelity/sample_similarity_lpips.py at master · toshas/torch-fidelity
This is the official implementation of "Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors", which is accepted at ICLR2025. - Vec2Face/lpips/vgg.pth at main · HaiyuWu/Vec2Face