Binary Classifier using Tensorflow model from course 2 last assignment
I am trying to build a binary classification model using the model we made in course 2 last assignment using tensorflow. The problem I am facing is that it always shows an accuracy of 50% on my training and test set and gives only one class output on unseen images. I have tried loads of combos of batch size and learning rate.
Can anyone provide some insights here?
I am new in the area of deep learning.
I am trying to design one clustering module using autoencoder.
I am using one vanilla auto encoder to extract the feature for simplicity. the steps are as follows:
1. Design one vanilla autoencoder and train it with training data.
2. Save the weight of the trained network.
3. Remove the last layer
4. Run the model with the test data in feed-forward mode
5. Extract the feature vector from the latent layer, i.e., output of encoder.
6. Run kmenas clustering algorithm on the feature vector
7. Got the cluster centres with overlapping clusters.
My query is, is that the correct method of fusing neural network with any clustering /Classification algorithm or some thing else?
If it is wrong method, what is the actual method to do the classification/clustering ?