莫小苝

> Hey @lovejing0306 thanks for your interest in our project. You can try to train `cyclegan` with 1 GPU. The name field `b1x1_270k` means `batch_size` equals to 1, number of...

> Hey @lovejing0306 thanks for your interest in our project. You can try to train `cyclegan` with 1 GPU. The name field `b1x1_270k` means `batch_size` equals to 1, number of...

> Since the test dataset is very sma Thanks for your advice, I will set the interval=100 and try it.

> You use 0.0001 as base learning rate? Or you means when your lr up to 0.0001, the loss get larger? > Can use share more details about this appearance?...

you need use L_Resnet_E_IR_fix_issue9 > do you solve this problem? i have the problem "FailedPreconditionError (see above for traceback): Attempting to use uninitialized value resnet_v1_50/block4/unit_3/bottleneck_v1/conv2_bn/BatchNorm/beta" > l have the problem...

Have you the dataset?

I think so, I try to download the dataset but failure.

I got the same problem

> Hello: > I got the similar issue when converting a pb to trt plan. Have you guys got solution? > Thanks > > Warning: No conversion function registered for...

> Another way to do what @Scottchou7 does is: > > 1. Uninstall your local `keras-applications` (`pip uninstall keras-applications`). > 2. Then install it via git (`pip install git+https://github.com/keras-team/keras-applications.git@master`). >...