Confusezius / Revisiting_Deep_Metric_Learning_PyTorch

(ICML 2020) This repo contains code for our paper "Revisiting Training Strategies and Generalization Performance in Deep Metric Learning" (https://arxiv.org/abs/2002.08473) to facilitate consistent research in the field of Deep Metric Learning.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

BUG?

interestingzhuo opened this issue · comments

commented

When I run the basic sample,
'''
python main.py --loss margin --batch_mining distance --log_online
--project DML_Project --group Margin_with_Distance --seed 0
--gpu 0 --bs 112 --data_sampler class_random --samples_per_class 2
--arch resnet50_frozen_normalize --source $datapath --n_epochs 150
--lr 0.00001 --embed_dim 128 --evaluate_on_gpu
'''
There is an error,
"""
Traceback (most recent call last):
File "main.py", line 44, in
if opt.log_online:
AttributeError: 'Namespace' object has no attribute 'online_backend'
"""
I haven't found the 'online_backend' either

Thanks for noticing! This was an issue caused by me removing Comet-ML as a logging option in the parameters.py-file but not accounting for that in main.py. Fixed it now!

Also FYI: If you use the --log_online option, make sure to also pass your W&B key via --wandb_key (or set it as default inparameters.py)