Miguel Campos Romero

Add Gaussian noise transformation

8

### 🚀 The feature Add gaussian noise transformation in the functionalities of torchvision.transforms. ### Motivation, pitch Using Normalizing Flows, is good to add some light noise in the inputs. Right...

Why if I increase the skewing angle the size image is reduced?

1

Why happends? python run.py -c 2 -t 10 -w 10 **-k 0** **-f 64** -b 0  python run.py -c 2 -t 10 -w 10 **-k 60** **-f 64** -b...

Detection AUROC and segmentation AUROC behavior

1

Hello! I wonder if the detection AUROC snd segmentation AUROC have the same behavior. In other words, when the model achieves the best seg_auroc,should it be when it has also...

BUG IN THE CODE

1

Hello, in my case i need to train a corpus with this characters '0123456789abcdefghijklmnopqrstuvwxyz-' Note that **-** is needed for my propose. If I use `opt.character = '0123456789abcdefghijklmnopqrstuvwxyz-' ` the...

How can i assign a token for all the character that are not in opt.character

1

Hello comunity. I am working in a project to recognize **just numbers** My recognizer is trained with "0123456789" characters Moreover, I created a pipeline with a **text detector** + **deep-text-recognition-benchmark-model**...

I need to train a 4k dataset of airplanes and make inferences in similar data. This is how the images look https://ibb.co/QvbL7kp (yes there is one plane in the bottom-left...

By not providing "FindTorch.cmake" in CMAKE_MODULE_PATH this project has asked CMake to find a package configuration file provided by "Torch", but CMake did not find one

1

Hi, im getting problems installing warp_ctc. I dont know what can i do, i cant resolver it rtx 2060 nvidia-drivers: 418.67 CUDA version 10.1 This is my error: **CMake Warning...

Why should we use cfg/somefile.data

2

If i have a trained yolo model on my custom dataset, why is not enought with weights and model.cfg? For instance this is my call ./darknet detector batch **cfg/obj.data** cfg/yolov3-tiny-obj.cfg...

Why square the Z?

2

Hello @marco-rudolph I'm following in deep your research (good job btw). When the NF model returns the log-likelihood, what is the propose of squaring them? (z variable [here](https://github.com/marco-rudolph/cs-flow/blob/ac78bd192c80866ab8db2b8b483650881e6ea44c/train.py#L68)) Thank you...