Upamanyu Ghose
Upamanyu Ghose
Hello, thanks for the response. I am using a custom repeat catalog, testing about 1000 STR. I'm using version 4.0.1, precompiled.
The issue was that I had commented out the portion that was zero padding all my labels to the same length. What is the loss you are getting on training...
This is a code I found to generate anchors but I'm not sure how to check their validity: [https://github.com/Jumabek/darknet_scripts/blob/master/gen_anchors/gen_anchors/gen_anchors.py](url)
I managed to train the model on my dataset but it ends up over fitting on the training data. Did you face the same issue at any point of time?...
@AKSHAYUBHAT how did you decide to freeze the first 8 layers? Is there any particular intuition or did you try multiple combinations? I'm asking because i tried to use your...
I did this and tried to train on my own dataset. I made no changes to number of anchors. However at the end of over fitting on one image, it...
I have tried to train it for 1000 epochs but the loss won't fall below 5. Thanks for your help. I'll try to figure out what the problem may be.
Thankyou I'll try retraining it on my dataset
Hello, I tried extracting the data myself and it seems to extract without issues. Not sure what is goign wrong. If you have your own SMI or Tobii files, feel...
Apologies for the very long delay. I've resolved the installation error, so hopefully should be fine now.