[GitHub] lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16

lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16 URL: https://github.com/apache/incubator-mxnet/issues/7968#issuecomment-356726078 I added gc() quite a few times before training and three times within training. Please see below: gc() model <- mx.model

[GitHub] lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16

lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16 URL: https://github.com/apache/incubator-mxnet/issues/7968#issuecomment-355711093 I added gc() before mx.model.FeedForward.create and also within mx.model.FeedForward.create. Then I immediately ran nvidia-smi. At

[GitHub] lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16

lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16 URL: https://github.com/apache/incubator-mxnet/issues/7968#issuecomment-355711093 I added gc() before mx.model.FeedForward.create and also within mx.model.FeedForward.create. Then I immediately ran nvidia-smi. At

[GitHub] lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16

lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16 URL: https://github.com/apache/incubator-mxnet/issues/7968#issuecomment-355379685 Hi, I recently attempted transfer learning on ResNet101. I only retrain the last fully connected layer. resnet101<- mx.model.l

[GitHub] lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16

lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16 URL: https://github.com/apache/incubator-mxnet/issues/7968#issuecomment-348334046 I am running Linux: R version 3.3.3 (2017-03-06) Platform: x86_64-redhat-linux-gnu (64-bit) Running under: CentOS Linux 7 (Core) Y

[GitHub] lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16

lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16 URL: https://github.com/apache/incubator-mxnet/issues/7968#issuecomment-332685732 I changed the line for input.shape to input.shape = list(data = c(224, 224, 3, 8)), then I am getting the error

[GitHub] lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16

lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16 URL: https://github.com/apache/incubator-mxnet/issues/7968#issuecomment-332665757 I can run the code in

[GitHub] lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16

lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16 URL: https://github.com/apache/incubator-mxnet/issues/7968#issuecomment-332657040 I got the files from .

[GitHub] lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16

lichen11 commented on issue #7968: [R] Transfer Learning using VGG-16 URL: https://github.com/apache/incubator-mxnet/issues/7968#issuecomment-332622479 Hi, I believe I have set up the transfer learning correctly, retraining the last fully connected layer. I also made sure the names match t