Train loss is 0.0000 at every iteration

roatienza / deep-text-recognition-benchmark

PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)

Apache License 2.0

284 stars 57 forks source link

Train loss is 0.0000 at every iteration #38

Open Ashish0091 opened 1 year ago

Ashish0091 commented 1 year ago

I am training the VITSTR-tiny model on my custom text dataset and it is giving the same training loss for every iteration which is 0..0000. I have not changed any parameters in the model. What might be the cause

roatienza commented 1 year ago

Pls make sure you have the same packages in the requirements.txt installed. The results are all replicable.