-
Notifications
You must be signed in to change notification settings - Fork 360
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
Partial accuracy 0.000??? #8
Comments
The commented line #saver.restore(sess, ckpt.model_checkpoint_path) is responsible for loading the saved model . Without it , the script does not load anything and tests a model that was not trained, so the result is 0% accuracy. |
Okay, i have commented out
|
It seems that the ckpt object is not properly initialized by the |
Yes i can see in the fruit_models folder which is created during training. The following 5 files available
Even i tried by doing fresh training:
But still same problem during testing |
What is the value of the "checkpoint_dir" variable when it executes |
Yes its has same. |
I have resolved that issues but accuracy is coming always 0
|
From the prints it looks like it counts the number of correctly classified images as well as the total number of images. |
I guess you are right but still showing same accuracy 0.0000. No luck
|
I think I was mistaken. Please try |
Great now its working absolutely fine. just one more doubt while detecting fruits from
I am running as per: Any idea whats wrong? |
For this script you need to provide the path to a jpg file, not the folder. |
Thanks a lot. |
Hello @Horea94
I have used
useCkpt = False
during training and it gave me error during testing as per below.In order to resolve above issue i commented
#saver.restore(sess, ckpt.model_checkpoint_path)
in thefruit_test_net.py
test script. After that it runs well but it gave me Partial accuracy 0.000.The text was updated successfully, but these errors were encountered: