jeremiedb commented on issue #7968: [R] Transfer Learning using VGG-16 URL: https://github.com/apache/incubator-mxnet/issues/7968#issuecomment-419299563 @ankkhedia I'm still having some difficulty to wrap my head around this. Memory footprint remains constant on my run even on large model (resnet-50 / 101). Footprint of 6GB on vgg19 and batch size of 150 appears quite low. Have you fixed the parameters of all but the last layer? I can fine-tune with vgg19 with parameters fixed and batch size of 8. Memory rise at 6GB at model inception then drops to 3GB and remains constant, so I have cannot reproduce how gc() in the training loop would help. I don't have a better solution for now, but given than adding a gc in impairs training speed I would be reluctant to add it at this point given the it seems very specific to vgg.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
