When attempting to download cityscapes_2048x1024 I got: ./download-models.sh: line 721: download_fcn_resnet18_cityscapes_2048x512: command not found
It looks like there was a typo, and line 721 needs to be changed from:
download_fcn_resnet18_cityscapes_2048x512 to download_fcn_resnet18_cityscapes_2048x1024

Thanks for the amazing repo!

It seems trt6.0.1.5 has involved the restriction. In trt5.1.5.0, the ExecutionContext can be destroyed after its corresponding ICudaEngine.

Currently, they are just all over the place! I propose the following rule-of-thumb:

1. If a header file contains cuda kernels and/or device methods, then it should be a .cuh.
2. Else, it should be a .hpp (if the current header file is already named as a .h, feel free to leave it as it is, in order to minimize the amount of ripple changes this will cause).
3. If a header file is used to de

e.g. based on the google doc https://docs.google.com/document/d/1ZI1V_2I3tETAeGnAwYZnrYTdeiOfdtWCL4l4DmRimFc/

p.s. I think that using docker for the course is an overhead which is not justified. As people create a designated VM for the course it would have been better to share a VM image so installation is one click and forget about docker. Docker is great when you need multiple environment or

@benbarsdell @yinghai For more detail see the issue originally posted in the tensorflow-onnx repo. Can you guys help look into this? I guess something is not quite right either in onnx-tensorrt parser or tensorflow-onnx conversion tool.

Show difference quality as a numerical value between original (full size) image and upscaled image in the waif2x implementation comparison chart.

Probably using SSIM. Would be a informative comparison.

I use your easiest way to inpaint a face that blocks one eye in your link ''www.fixmyphoto.ai'. Why can't it fix

Looks like there's no example using vector types defined in cltypes while the doc itself for these types are not so understandable. There are many examples having kernels taking vector type arguments, but the python code is using the numpy type, instead of the defined vector type. E.g. https://github.com/inducer/pyopencl/blob/master/examples/demo_elementwise_complex.py

• host renders and streams the app
• client receives the stream
• app is the item selected to stream
• address is the combined term for IP or hostname used to contact the host

I'm playing CudaSift. Cool job...
But, in order to have it installed easily, you may have to:

1. Add "Copyright.txt" file under root folder
2. Better to have a version file, now 4.0.0?
3. sm_52 is for my computer now. So, maybe, you can let the users to choose their own Cuda architecture???

Cheers
Pei

doc under Anakin/benchmark/README_CPU.md is out of data.
Three links of models points to 404 page
Those links in Anakin/benchmark/RNN/prepare.sh are also invalid.

As soon as both futures 0.2 and tokio 0.2 begin to stabilize, create an example which could potentially double as a tutorial and that uses some basic asynchronous features.