Open Sssssuperior opened 9 months ago
Thanks for your interest in our work. 'freq_adaptor' in an extended version here, please specify model['encoder_mode']['name'] to 'fp' in the config file to use it, and find the corresponding model here. If you want to compare your results with EVP, please specify model['encoder_mode']['name'] to 'evp' and use the corresponding model.
Hello, this is a very good job. We recently want to compare our results with EVP, but the provided results do not include SOD saliency maps. Also, when I load the EVP pretrained model, it prompts that the main component is "freq_adaptor", but this seems to be FP's parameter? Can you please tell me if I made any mistakes here? Or can you provide your saliency maps? Thank you!