problem description
during the training process, the loss of the training set decreased and the acc increased, and the performance was normal. However, the loss of the validation set is rising, and so is the acc.
training process
during the training process, the loss of the training set decreased and the acc increased, and the performance was normal. However, the loss of the validation set is rising, and so is the acc.
Previous: Nuxtjs asyncData () did not get the data to render to the page
Next: Py requests codec can't decode byte 0x8b to appear on the web page
such as the title. what I m doing is language classification of picture text the following figure shows the results of my experiment I would like to ask what measures can be taken to further improve accuracy? ...
after several iterations, the loss function remains unchanged, and the learning rate is still changed. I hope the great god will guide you what the problem is this is the code https: github.com yaoqinchua. uses multi-perspective CNN (mvcnn) . ...