Skip to content

Instantly share code, notes, and snippets.

@kumarvipu1
Last active February 3, 2021 13:49
Show Gist options
  • Save kumarvipu1/b00e201fb925759f2583f182c1e2c66c to your computer and use it in GitHub Desktop.
Save kumarvipu1/b00e201fb925759f2583f182c1e2c66c to your computer and use it in GitHub Desktop.
image classifier part 4
#reshaping the independant variables
train_X = train_X.reshape(train_X.shape[0], 28, 28, 1)
val_X = val_X .reshape(val_X.shape[0], 28, 28, 1)
#encoding the dependant variable
train_y = np.eye(10)[train_y]
val_y = np.eye(10)[val_y]
#creating model
model = create_model((28,28,1))
#optimizing model
compile_model(model, 'adam', 'categorical_crossentropy')
#training model
history = model.fit(train_X, train_y, validation_data = (val_X, val_y), batch_size = 150, epochs = 80)
model.save("cnn_digitclass.model") #model will be save in root folder to be later called out for prediction
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment