MyCNN | simple implementation of CNN | Machine Learning library

in tensorflow, I intend to tune hyperparams in pre-trained CNN for the image classification tasks. To do so, I used a pre-trained model like vgg16 to extract features and used extracted embedded features as inputs for convolutional neural net (CNN). Basically, I place CNN on the top of the pre-trained model for training. I am trying to optimize hyperparameter like batch_size, epochs, drop-rate, using GridSeatchCV, but I got the following type error:

I am trying to implement the Keras libraries for Convolutional Neural Networks on my Spyder IDE using Anaconda as such:

I have a CNN, takes in an image, outs a single value - an angle. The data set is made of (x = image, y = angle) couples.

I want the network for each image, to predict an angle.

I have found this suggestion: https://stats.stackexchange.com/a/218547 But I can't seem to understand how to translate it into a working Tensorflow in Python code.

I have a Keras CNN model that I converted to CoreML using coremltools. It works perfectly on simulator but not on the iPhone X. It crashes just on initialization:

I have CNN model which has 4 output nodes, and I am trying to compute the confusion matrix so that i can know the individual class accuracy. I am able to compute the overall accuracy. In the link here, Igor Valantic gave a function which can compute the confusion matrix variables. it gives me an error at correct_prediction = tf.nn.in_top_k(logits, labels, 1, name="correct_answers") and the error is TypeError: DataType float32 for attr 'T' not in list of allowed values: int32, int64

I have tried typecasting logits to int32 inside function mentioned def evaluation(logits, labels), it gives another error at computing correct_prediction = ... as TypeError:Input 'predictions' of 'InTopK' Op has type int32 that does not match expected type of float32

how to calculate this confusion matrix ?

I have the tensorflow as the backend. I'm using the 3D convolution layer in keras. My final x training data is in shape (7,9,384,1), channel equals to 1, y training data is in shape (7,1,384,1). I keep getting this error when it runs model.fit().

I checked out most of the related problems posted online, but they all kind of focus on whether it's theaon or tensorflow as the backend. Some of them suggests expand dimensions, but still doesn't work and some other problems showed up.

According to the keras documents, 3D convolution should have a 5D input shape, and I am lacking the first dimension samples. I only have this one 3D data input (in shape 7,9,384), and I tried adding a 1 at the beginning of the input_shape parameter in the first layer, and it will cause another problem saying that I exceeded one dimension in the input shape.

Can anyone please take a look and tell me what's wrong? Thank you so much!

I am getting the Exception when I attempt to update the record with "tableGateway" object:

I am trying to execute on a stored procedure in my database with the following code: