An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
In the DARTS tutorial, I replaced Cifar10 with my own dataset and the val results were good, but the Acc performance on my custom test.py file was very poor. I think there is a problem with model loading. Could you tell me how to load the model correctly and run it on the test dataset?
Retrain result:
test result
Help me!!!!
In the DARTS tutorial, I replaced Cifar10 with my own dataset and the val results were good, but the Acc performance on my custom test.py file was very poor. I think there is a problem with model loading. Could you tell me how to load the model correctly and run it on the test dataset? Retrain result: test result Help me!!!!