We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
I am doing training from scratch in the way of:
python train.py --data_file_path test2.csv --gpus=0 --pin_memory --max_epochs=12 --min_products_for_category 1
my csv file contains 7376 items in 2 categories
(my file contains only 1 validation record and the rest are training)
I wants sure how to proceed categories in i2cat... file, so i just grab those 2 categories and placed them in i2cat....... file.
Then i got file from
lighting_logs/version_0/checkpoints/epoch3=1-step=3.ckpt
and i copied that file to main product category
and after i am trying to use it with following command:
python predict.py -t "Acura TL" --trained_model_path=ready.ckpt
and predictions numbers are way off activities: 0.585 cars-trucks: 0.283
Please suggest what might be wrong
The text was updated successfully, but these errors were encountered:
No branches or pull requests
I am doing training from scratch in the way of:
python train.py --data_file_path test2.csv --gpus=0 --pin_memory --max_epochs=12 --min_products_for_category 1
my csv file contains 7376 items in 2 categories
(my file contains only 1 validation record and the rest are training)
I wants sure how to proceed categories in i2cat... file, so i just grab those 2 categories and placed them in i2cat....... file.
Then i got file from
lighting_logs/version_0/checkpoints/epoch3=1-step=3.ckpt
and i copied that file to main product category
and after i am trying to use it with following command:
python predict.py -t "Acura TL" --trained_model_path=ready.ckpt
and predictions numbers are way off
activities: 0.585
cars-trucks: 0.283
Please suggest what might be wrong
The text was updated successfully, but these errors were encountered: