search

yangze0930 / NTS-Net

This is a PyTorch implementation of the ECCV2018 paper "Learning to Navigate for Fine-grained Classification" (Ze Yang, Tiange Luo, Dong Wang, Zhiqiang Hu, Jun Gao, Liwei Wang).
MIT License
452 stars 118 forks source link

Time cost on Training #3

Closed ygean closed 6 years ago

ygean commented 6 years ago

Hey,your job is excellent!Recently,I have a task which contains 2000+ classes and 5.6 millions images about cars, I had tried to train BCNN on my dataset, but it spent too much time on convergence of network.I did not get answer after reading your paper. Could you tell me about how long you had trained NTS-Net using CUB dataset on your 4 GPUs machine?Thank you.

yangze0930 commented 6 years ago

You will need about 10 hours to train 100 epoch on CUB dataset using 4 Titan X, and 100 epoch is enough for CUB.