8000 Unable to run train_mrcnn_model.ipynb · Issue #20 · rgmyr/corebreakout · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Unable to run train_mrcnn_model.ipynb #20

New issue

Have a question about this project? Sign up for a free GitHub 7F48 account to open an issue and contact its maintainers and the community.

Sign up for GitHub

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

Jump to bottom
Open
MonkeyLever opened this issue Aug 20, 2021 · 0 comments
Open

Unable to run train_mrcnn_model.ipynb #20

MonkeyLever opened this issue Aug 20, 2021 · 0 comments

Comments

@MonkeyLever
Copy link

When running train_mrcnn_model.ipynb with tensorflow gpu I got the following erros.

import warnings

with warnings.catch_warnings():
warnings.simplefilter("ignore")

# Train network heads
print('Training network heads')
model.train(dataset, test_dataset, 
            learning_rate=config.LEARNING_RATE, 
            epochs=15, 
            layers='heads')

# Finetune layers from ResNet stage 4 and up
print('Tuning stage 4 and up')
model.train(dataset, test_dataset, 
            learning_rate=config.LEARNING_RATE / 5, 
            epochs=50, 
            layers='4+')

print('Tuning all layers')
model.train(dataset, test_dataset, 
            learning_rate=config.LEARNING_RATE / 50, 
            epochs=100, 
            layers='all')
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@MonkeyLever
0