while running the code I am getting all loss values as NaN, filepath I have mentioned as suggested in runtime checkpoint_path = '/tmp/ckpt/checkpoint.model.keras.weights.h5'
Thank you for this explanatory tutorial. I have also followed the same code for building ANN model on regression data having 4 input variables and 1 output variable and the model is built successfully. But now, I want to optimize the ANN model's solutions by Genetic Algorithm (GA). So, for this I am following "ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-ljjfrrHlxCw.htmlsi=-DBs2Bki0p1LgABm", this tutorial as a reference but, they have used Random Classifier in place of ANN model to optimize their regression data. So, at their 19th step, they are calling their trained model into a new variable which is used later as a "fitness function" for GA. I am using "model_full = ann_viz(model, view=False, filename= 'network.gv', title='My Neural Network')" instead of their Rnadomforest classifier. So, please help me in this as I am getting error in "input_shape" i.e., "AttributeError: 'Dense' object has no attribute 'input_shape'". Although I have changed the input_shape as mentioned by you while building ANN modelto "4" as I have 4 variables.
can model.fit() be used on multiple datasets. For example, model.fit(normed_training_data1, train_labels1) model.fit(nromed_training_data2, train_labels 2) y_pred = model.predict(normed_test_data) I have 2 datasets that I want to train for the model
Thank you for the video; most places, including sklearn, show (X_train, X_test, y_train, y_test = train_test_split), why does your model have only two of them? is it because you separate the validation, or does it have any other reason?
If all data types in your dataset are integer or float so no need to use any encoding. Encoding is used for transfering your non-numircal data to numerical values because the model can work only with numbers.
@@hggaming911 if i want to change the order, what is the code for example "Iris-setosa" = 3, "Iris-versicolor"=2, Iris-virginica" =1 instead of writing "Iris-setosa" = 1, "Iris-versicolor"=2, Iris-virginica" =3
Nice video. I followed your tutorial and it worked brilliantly on my project. On thing at the end, did you made a mistake on the confusion matrix? it seems like you are plotting predicted results against predicted results.
yeah, i think he made a mistake on the confusion matrix, and i correct it into "cm = confusion_matrix(test_labels, y_pred)" but i'am not really sure that is correct. XD