-
Run with ` -DUSE_CUTENSOR=OFF ` and `-DUSE_CUQUANTUM=OFF`:
```
279 - BlockUniTensorTest.gpu_Trace (Failed)
331 - BlockUniTensorTest.gpu_at_for_sparse (Failed)
332 - DenseU…
-
The datafile logic for loading files in activecode.j does not handle absolute URLs when hosted on Runestone. I believe this is a combo of code and server setup.
Replication:
Go to https://runeston…
-
Many networks have the capability to run inference via ncnn, but require their .param file to be edited and adjust accordingly to properly work.
Currently if you give vs-ncnn a onnx network it resu…
-
Hi, first of all thanks to everyone that worked on DCTLSA.
I want to give some feedback regarding this project: I've added it to [neosr](https://github.com/muslll/neosr) and trained both bicubic and …
-
Projector.py converts your target image to RGB but this of course causes an assertion error with a network trained on greyscale images. I am working on resolving this on my own. Here is the snippet of…
-
**Problem description**
I am having problems reconstructing a scene taken with a not so good camera.
The problem I would like to address is the quality of the depth estimation performed by the Dep…
-
### Feature description
I have an extensive imagery processing pipeline, including computation intensive histogram matching, many image adjustments and many compositing steps, but running gdal2tile…
-
I want to use your code with the Proba-V dataset, but I'm facing the following error.
`$ python src/train.py --config config/config.json
0%| …
-
Is it okay to use different criterions in the training phase and visualization phase?
Also, what other criterions can be used ?
-
Current options for upscale are fixed ratios like 2x,3x,4x etc.
Currently I am using this to upscale images (long-strip style ones) from around 600-650px wide to 800px wide.
But the only option for …