You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
My goal was to train model to predict eye disease . I collected dataset of 1500 images and did 60 20 20 split. I trained my model with the following command "python train.py --workers 1 --device 0 --batch-size 4 --epochs 100 --img 640 640 --data data/custom_data.yaml --hyp data/hyp.scratch.custom.yaml --cfg cfg/training/yolov7-custom.yaml --name yolov7-custom --weights yolov7.pt".
I modified yolov7-custom.yaml by creating 2 classed namely healthy and glaucoma(diseased).
After training I tried detecting one of the images in training and test dataset but encountered no detection.
These are some of the files in my runs that might require for finding the bug.
Why there is no detection and how can I make my model detect and produce some output. Also, How can I continue from 100 epoch trained model? Thank you for your replies in advanced.
The text was updated successfully, but these errors were encountered:
My goal was to train model to predict eye disease . I collected dataset of 1500 images and did 60 20 20 split. I trained my model with the following command "python train.py --workers 1 --device 0 --batch-size 4 --epochs 100 --img 640 640 --data data/custom_data.yaml --hyp data/hyp.scratch.custom.yaml --cfg cfg/training/yolov7-custom.yaml --name yolov7-custom --weights yolov7.pt".
I modified yolov7-custom.yaml by creating 2 classed namely healthy and glaucoma(diseased).
After training I tried detecting one of the images in training and test dataset but encountered no detection.
These are some of the files in my runs that might require for finding the bug.
Why there is no detection and how can I make my model detect and produce some output. Also, How can I continue from 100 epoch trained model? Thank you for your replies in advanced.
The text was updated successfully, but these errors were encountered: