search

dqshuai / MetaFormer

A PyTorch implementation of "MetaFormer: A Unified Meta Framework for Fine-Grained Recognition". A reference PyTorch implementation of “CoAtNet: Marrying Convolution and Attention for All Data Sizes”
MIT License
226 stars 40 forks source link

Regarding Inferencing. #9

Closed BakingBrains closed 2 years ago

BakingBrains commented 2 years ago

I have trained the model for 28 epochs on CUB-200 dataset, also I wrote a small inferencing script which accepts a single image along with its meta info. but while predicting it is not at all giving good result. Do I need to train more?

Any suggestions here?

Thank you.

dqshuai commented 2 years ago

I recommend training more epochs, like 100 or 200. If you use a pre-trained model, it is recommended to train with a smaller learning rate (1e-4, 1e-5).

BakingBrains commented 2 years ago

@dqshuai Thank you. Will train more with the mentioned LR.