302 - Tuning deep learning hyperparameters​ using GridSearchCV

Tuning deep learning hyperparameters using Gridsearch
Code generated in the video can be downloaded from here:
github.com/bns...
All other code:
github.com/bns...
The grid search provided by GridSearchCV exhaustively generates candidates from a grid of parameter values specified with the param_grid parameter.
The GridSearchCV instance when “fitting” on a dataset, all the possible
combinations of parameter values are evaluated, and the best combination is retained.
cv parameter can be defined for the cross-validation splitting strategy.
GridSearch is designed to work with models from sklearn. But, we can also use it to tune deep learning hyper parameters - at least for keras models.
Wisconsin breast cancer example
Dataset link: www.kaggle.com...

[@Anil-io]

I needed this video ! Currently working on finding defects in leather seat but was having trouble finding the optimal values for the hyperparameters. this will save the day ! Thank you !

[@pedroramon3942]

The tensorflow.keras.wrappers are depreciated and it is recommended to use scikeras package instead.

[@paromitakundu4034]

i have used scikeras to use keras classifier. but i am getting errors."ValueError: Invalid parameter neurons for estimator KerasClassifier.
This issue can likely be resolved by setting this parameter in the KerasClassifier constructor:
KerasClassifier(neurons=2)
Check the list of available parameters with estimator.get_params().keys()"

[@darrentan271]

I have the same problem too

[@MH-ny3sd]

It doesn’t work for me too, I can’t do it.

[@AbdulSyed-y8z]

Thank you. You are sharing your precious knowledge, its really helpful.

[@JovitaLewis]

great video. can you make a video on hyperparameter tuning on custom data for yolov8 model?

[@SonGoku-rl9qf]

Guys why is the validation loss not monitored? I can not see it in his video. Is the accuracy calculated by the validation set?

[@muhammad529]

Hope U r doing good sir.
Thanks a lot for ur wonderful lectures.
Sir i m a research scholar pursuing PhD.
Sir I face issues in using GPU of my laptop for image processing.
Sir i have gone through all steps u mentioned like cuda, cudnn, py37env...
Support needed.
Thank you sir.

[@shubhamverma8610]

to search optimum parameter total no of epochs are 18*3*2*number of epochs what is 2 here?

[@SanobarAkbarova-t4e]

why you didn't split data into train and test?

[@kumargie]

Sir, can you upload the video on how to perform hyperparameter tuning using cuckoo search algorithm in deep learning architecture

[@muhammadtahirnaseem1448]

Excellent videos. Sir, I am working on image registration (IR and RGB) and facing some issues. How can I contact you?

[@abdogassar9246]

Great always, thank you Sir.