Closed YesDargo closed 6 years ago
In my opinion, just change the class number to 2. Increase weight to 1e-3 and sure that you have enough training data. Otherwise, you can retrain from resnet101
Thanks for reminding!
The initial setting was to load the checkpoint from deeplab_resnet_init.cpkt
. Now I change to deeplab_resnet.cpkt
, and the loss starts to drop to 1.189 from 1.231.
Hi, I am new to the ML/CV, now I am doing image segmentation for skin lesion. I only need to separate lesion area from background (two classes)
When I configure the main.py and run train, the
loss
remains in 1.231 after a few steps. Then I run test, thepixel accuracy
keeps 1.00 andmean IoU
keeps 0.5. Did you encounter the same problem?I found in Dr.Sleep's note that when load checkpoint for different class number (not 21), the
--not-restore-last
should be passed. Have you also implement this?