Mephisto405 / Learning-Loss-for-Active-Learning

Reproducing experimental results of LL4AL [Yoo et al. 2019 CVPR]
215 stars 50 forks source link

question about the backbone model #18

Closed lijiaoyang closed 2 years ago

lijiaoyang commented 2 years ago

If your lossnet module is suitable for high resolution images (such as imageNet) in datasets, replace the backbone network with resnet101, and simply adjust feature_size and num_channels? thx!!

Mephisto405 commented 2 years ago

Yeah, I guess we can definitely try that approach!

lijiaoyang commented 2 years ago

thx