search

zhmiao / OpenLongTailRecognition-OLTR

Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)
BSD 3-Clause "New" or "Revised" License
839 stars 128 forks source link

Table 2 results #58

Closed zaeemzadeh closed 4 years ago

zaeemzadeh commented 4 years ago

Hi, Thanks for sharing your work. Is there an easy way (without changing the code much) to reproduce Table 2 results? (CIFAR100 + TinyImagenet (resized))

zhmiao commented 4 years ago

Hello @zaeemzadeh , thank you very much for asking and sorry for the late reply. Yes, if you want to apply out code to other datasets, the easiest way is to change the dataset object defined in the code. However, CIFAR has different dimensions than ImageNet. So I think you will also want to change the model definition. On the other hand, direct using the hyperparameters we have for ImageNet won't provide good results either. Does that make sense?

zaeemzadeh commented 4 years ago

Thanks. Yes it makes sense