Xinwei He comments

Results 9 comments of


                                            Xinwei He

How to contribute

@PavlosMelissinos i have come across the same problem about ```meteor``` when importing it into python3, have you solved your problem (all other metrics works properly)?

Unnecessary computation in backward pass

it is still very slow when turnning this flag off, donot know the reason.

Unnecessary computation in backward pass

I find that training this net on GPU for 1 iterations ,with batch size 64 on celeba , costs me nearly 30 seconds.

Unnecessary computation in backward pass

Hi, I use the default setup of the parameters. And my GPU has a memory of 12G. I donot know the reason why it is too slow..

Indexing and shape incoherent with module conversion

I have the same issue here. Do you solve this problem?

AttributeError: 'tensorrt.tensorrt.Builder' object has no attribute 'max_workspace_size'

I have come across the same problem. can anyone solve this problem?

got error when loading without binary file?

hi, i have changed the file caffe.lua to support loading caffe model with only prototxt file, hope you can check it.

Benchmarks

i am wondering if you only use the 80K dataset to get such a high performance on validation set, or use 110K dataset? I am doing experiment on karpathy split...

Benchmarks

BTW, i am using show attend model for my experiment.