Closed liangchengbeibian closed 1 year ago
Hi,
I have not encountered this kind of problem before.
Please refer to the following supplementary experimental environment:
CUDA 11
cuDNN 8.0.4
For the SALICON dataset, the stimuli and saliency maps were simply resized from 640x480 to 384x288, and the fixation maps (binary) were generated from the coordinates after resizing.
The models were trained without specifying a particular random seed for loading datasets.
thank you for your reply, the problem appears in the processing of the label.
I retrain fine-tune&train.ipynb with the same dataset and setup, but the train loss is very easy to be nan. Have you encountered this situation? Can you provide a more detailed experimental environment such as random seed and progress of dataset?