Image-classification | Image Classification using SIFT Bag of words | Machine Learning library

I am making a neural network architecture to predict whether an image is of a building, forest, glacier, mountain, sea or street. Link to the dataset.

I am using tf.keras.preprocessing.image.ImageDataGenerator() to load and preprocess my data. The directory look like this:

Dataset Directory

The directory contains images of size 150x150 like this:

Photo from class 'Building'

I am following this tutorial with my custom data and my custom S3 buckets where train and validation data are. I am getting the following error:

I am learning the implementation of the TensorFlow model at android. In this tutorial, it put the labels.txt and model.tflite files into assets folder . https://blog.notyouraveragedev.in/android/image-classification-in-android-using-tensor-flow/ What is that labels.txt should be? I have a file that has the following format :

Background:

I'm building a real time image classification app for food items with react-native and the tensorflow HOC Camera.

I'm using this tutorial as a basis which includes a github repo where you can test it via Expo:

Basically, I want the camera preview to remain live and display predictions from the tensorflow model live. There is a function that is called each frame and predicts it. I can console.log() the predictions live but displaying them using a state variable causes the camera to re-render every prediction.

This is obviously poor user experience as only the text containing the prediction should change, the camera doesn't need to rerender. I've tried using React.memo() but that provides a 'Performance hint' and does not guarantee the camera component will not rerender.

Code:

I'm following the "Getting started with the built-in image classification algorithm" tutorial from Google's AI Platform and before submit a training job, one has to specify (it seems optional) the "image_size" which is defined as: "the image size (width and height) used for training". Do I have to specify a couple of scalars (comma delimited?) or a scalar ? How can we interpret this parameter? If I specify something, does it impose that all my input images should be of this particular size or will the images be automatically resized (or cropped?) to this size by the training graph? And equivalently for prediction task do I have to resize my input image to this specific size or does the prediction graph takes care of that.

Really don't have much idea of what I'm doing, followed this tutorial to process deepdream images https://www.youtube.com/watch?v=Wkh72OKmcKI

Trying to change the base model data set to any from here, https://keras.io/api/applications/#models-for-image-classification-with-weights-trained-on-imagenet particularly InceptionResNetV2 currently. InceptionV3 uses "mixed0" up to "mixed10" whereas, the former data set uses a different naming system apparently.

Would have to change this section

I'm running a Keras Neural Network model for a binary classification of images.
I use the first layer of a pretrained VGG16 model and i created the last fully connected layers from the tutorial:
https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html

With Tensorflow backend 2.3.1, Python 3.6, Keras 2.4.3

While i'm training my model (using presaved weights) with an ImageDataGenerator, this exception occurs:

I'm trying to use VGG16 with some modification on it. I followed this blog post from keras.io

Here the code I'm using to create the model:

I have a endpoint in Amazon SageMaker (Image-classification algorithm) in Jupyter notebook that works fine. In Lambda function works fine too, when I call the Lambda function from API Gateway, from test of API Gateway, works fine too.

The problem is when I call the API from Postman according this answer: "Post Image data using POSTMAN"

The code in Lambda is: