ColdCodeCool comments

Results 13 comments of


                                            ColdCodeCool

Bad results - Investigate reason

@dkorkino @jmtatsch I am also looking forward to the release of the converted weights.

Generating Image from Model

hi, guys, did you solve the problem and get the rgb image?

[RFC] A high-level GSPMD API in PT/XLA (based on `xs.mark_sharding`)

hi all, is there any update for this RFC? Has it been merged into the code base?

Any hints about using the pre-trained pkl file?

Yes, the API of serializer.load_hdf5(args.pretrainedmodel, model) seems did not work, and even if I changed the extension of file pkl to h5 or hdf5.

Any hints about using the pre-trained pkl file?

@shiba24 Could you please redesign the part of loading pre-trained model?

Any hints about using the pre-trained pkl file?

@shiba24 Great! Hope to see it soon. Thank you!

Any hints about using the pre-trained pkl file?

@shiba24 After I digged deeper into the code, I recognized that it seems the VGG model is double loaded. Since the line "model = HumanParts(n_class = 15)" has loaded the...

tensorflow.python.framework.errors_impl.NotFoundError: /home/research/data/hdrnet/hdrnet/lib/hdrnet_ops.so: undefined symbol: _ZN10tensorflow7strings6StrCatB5cxx11ERKNS0_8AlphaNumE Backend TkAgg is interactive backend. Turning interactive mode on.

> Facing similar issue when we try to freeze the pretrained models ... > > **/hdrnet/lib/hdrnet_ops.so: undefined symbol: _Z37BilateralSliceApplyGradKernelLauncherRKN5Eigen9GpuDeviceEPKfPKxS4_S6_S4_S6_S4_bPfS7_S7_** > > Using gcc 4.8, Python 2.7, Ubuntu 16.04, TF: 1.12.0,...

Inconsistencies in branch hop, file HighPerfCodeGen.md

is there any update?

How long it takes for training?

hi, guys, did you train yourself? did you figure out how much time it costs to train light and full version respectively?