Expected accuracy for Sentence Classifier - accuracy currently 25%?

salaniz / pytorch-gve-lrcn

PyTorch implementations for "Generating Visual Explanations" (GVE) and "Long-term Recurrent Convolutional Networks" (LRCN)

MIT License

92 stars 22 forks source link

Expected accuracy for Sentence Classifier - accuracy currently 25%? #20

Closed katelyn98 closed 1 year ago

katelyn98 commented 1 year ago

I am training the sentence classifier on CUB to ultimately train the GVE model, but my model converges around 10 epochs at about 25% accuracy. Has anyone reached higher accuracy for their sentence classifier? I am using 1 GPU and following the default scripts that were given. Thanks!

katelyn98 commented 1 year ago

I guess the accuracy doesn't matter for the sentence classifier? I was able to successfully train the model and get reasonable visual explanations out of it. Thanks!