search

chengchunhsu / EveryPixelMatters

Implementation of ECCV 2020 paper "Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector"
Other
165 stars 21 forks source link

Confirmation of the step parameter in the config files #4

Open liubl1217 opened 4 years ago

liubl1217 commented 4 years ago

I notice the step parameters are set to be (120000, 160000) in most config files while the max_iter is 20,000. I am wondering should it be (12000, 16000) for the step parameters? Or the learning rate for the last iteration is better to equal to base_lr? Thx!

mochaojie commented 3 years ago

Hi, i have received the cityscapes dataset. However, when i click the link for foggy cityscapes, i don't know which one is i really need. In the website, i see some foggy cityscapes datasets for semantic segmentation, not for object detection. Can you give me the link for foggy dataset specifically. Thanks!

liubl1217 commented 3 years ago

Hi, i have received the cityscapes dataset. However, when i click the link for foggy cityscapes, i don't know which one is i really need. In the website, i see some foggy cityscapes datasets for semantic segmentation, not for object detection. Can you give me the link for foggy dataset specifically. Thanks!

I think it's leftImg8bit_trainvaltest_foggy.zip (30GB) [md5]

mochaojie commented 3 years ago

Hi, i have received the cityscapes dataset. However, when i click the link for foggy cityscapes, i don't know which one is i really need. In the website, i see some foggy cityscapes datasets for semantic segmentation, not for object detection. Can you give me the link for foggy dataset specifically. Thanks!

I think it's leftImg8bit_trainvaltest_foggy.zip (30GB) [md5]

Thank you

sunshehai commented 1 year ago

Do you meet the error: In the last step of installing：python setup.py build develop , I encountered problem：Couldn t find a setup script in /tmp/easy_install-2xsxsqeq/scikit_image-0.20.0.tar.gz. Thank you @mochaojie @liubl1217