-
Notifications
You must be signed in to change notification settings - Fork 914
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Training: invalid value encountered in less + nan's #26
Comments
I can confirm the issue. I have tested it on two different setups - one with tiny and one with notiny. Although I didn't get nans right from the start, both ended up with the above outcome. |
can you paste some of your sample data here, its hard to tell without training data |
Unfortunately it was a long time ago and I switched. I'm not using this project anymore. Thank you for reply :) |
I am seeing a similar error. My sample data looks like below, this is before converting it to tfrecord img1.jpeg 0.2901965,0.492121,0.4980395,0.576363,0 0.500981,0.495151,0.701961,0.573333,0 0.6464709999999999,0.5275755,0.696079,0.5809085,1 Can you please help |
Hi @samratkokula , |
I'm encountering the same issue. |
I had the same failure, the problem was that there were some nan's in my data ;) |
python train.py --batch_size 8 --dataset=C:\...\platt.record --val_dataset=C:\...\platt_val.record --epochs 10 --mode eager_fit --transfer fine_tune --weights ./checkpoints/yolov3-tiny.tf --tiny
results in this output:
What might be the cause for that? Also there are other open issues regarding training and I'm wondering if anyone was successfull.
The text was updated successfully, but these errors were encountered: