Varun Gupta

@jacobgil Thank you for this repository. I am trying to implement this in my keras trained segmentation model (FCN8+VGG19). I have referenced the Segmentation Notebook from your gradcam repo for...

I wish to define a custom binary crossentropy loss, in which I plan to apply the binary crossentropy loss on the foreground (1), and on the background(0), and then train...

Hey @windj007 I'm trying to inpaint my images - Size (360x640), with mask size of 360x640 as well. I have created masks such that: `np.unique(mask) = [0,1]` I'm using the...

No inpainted results generated on JPG

8

I have followed all the instructions to setup lama on my system. I went with the conda installation, and the `big-lama.zip` model. I'm running on a custom `.jpg` image, and...

Implementing GradCam

1

Requesting help with implementing GradCam in this repo? Any help is appreciated, Thanks. @shekkizh

I ran the training for a few epoch and was only getting an 'etropy' curve on tensorboard. How can I log and visalise metrics like - accuracy, mean accuracy. mean...

API for YOLOv4

1

@theAIGuysCode Kindly make a repo for yolov4 deployment as well. Same/similar approach is not working for it. How shall I make an API for YOLOv4?

How to specify type of image to download?

1

Open Images Dataset now has 3 types available - Detection, Segmentation and Relationships. **I want to download images of type - Relationships** for the class 'drink', How shall I do...

CLI commands to dump all annotations for a project

1

### My actions before raising this issue - [x] Read/searched [the docs](https://github.com/opencv/cvat/tree/master#documentation) - [x] Searched [past issues](/issues) ### Context I have about 600+ annotated videos and downloading completed annotations (either...

Hey @nguyenhoa93, I have trained a VGG19 based FCN8 model for segmentation task and wish to run GradCam visuals on my predictions. Please help me out if possible, Thank you.