Building a LSTM model for binary image classification with RGB images - tensorflow

I am struggling to build a binary image classification model for my custom image datasets (RGB) using LSTM. I found some excellent tutorials that solve the same kind of problem but with Grayscale images, but unable able to sort out how I can reshape my inputs.
Thanks in advance..

Related

Pre-trained CLIP Image Encoder Model in Tensorflow Format

I am looking to get a pre-trained CLIP image encoder model in tensorflow format. Where can one find this?

Keras model val_accuracy 1.00, and gives wrong output when testing

I've trained a Kaggle dataset (this one) to detect hand gestures. when training, it gives the val_accuracy = 1.00, here is an image or you can see it using the
link to colab
when I try to test the model using an image from the dataset, it gives right predictions, but when I try to use real-world image for "ok" gesture (you can see it in the end of the colab project), it just gives wrong outputs, I've tries other images, it gives also wrong predictions.
any help please?
When you have a real world image you want to predict you must process that image in exactly the same as you processed the training images. For example
image size must be the same
pixels must be scaled the same
if trained on rgb images real world image must be an rgb image
if trained on grayscale real world image must be gray scale

dimentions of images as an input of LeNet_5

I am still a beginner in deep learning, I am wondering is it necessary to have for the input images of a size equal to 32*32 (or X*X)? the dimensions of my images are 457*143.
Thank you.
If you want to implement a LeNet and train it from the scratch, you don't have to resize your images. However, if you want to do transfer learning, you'd better resize your images according to the image size of the dataset on which your neural net is already trained.

Grayscale input image for SSD detector in Tensorflow Detection API

I'm creating a dataset of images to train a detector using Tensoflow Detection API (SSD/MobileNet).
Images are grayscale but it seems the input should be RGB image.
Do I need to convert grayscale images to a three channel RGB by just copying first channel to two other channels? (If yes, is there any software for doing this?) or Two other channel should be empty? (Is there any software for doing this?)
Best regards.
Yes, you have to convert your grayscale images to RGB images.
A possible solution is to use OpenCV:
import cv2
# suppose that gray_img is your grayscale image
input = cv2.cvtColor(gray_img, cv2.COLOR_GRAY2RGB)
Now you can use input as a valid input image for your model

change the input image size for mobilenet_ssd using tensorflow

I am using tensorflow and tflite to detect object. The model I use is mobilenet_ssd (version 2) from https://github.com/tensorflow/models/tree/master/research/object_detection
the input image size for detection is fixed 300*300, which is hard-coded in the model.
I want to input 1280*720 image for detection, how to do this? I do not have the traing image dataset of resolution 1280*720. I only have pascal and coco dataset.
How to modify the model to accept 1280*720 image(do not scale the image) for detection?
To change the input size of the image, you need to redesign the anchor box position. Because the anchors are fixed to the input image resolution. Once you change the anchor positions to 720P, then the mobilenet can accept 720p as input.
The common practice is scaling the input image before feeding the data into TensorFlow / TensorFlow Lite.
Note: The image in the training data set aren't 300*300 originally. The original resolution may be bigger and non-square, and it's downscaled to 300*300. It means it's totally fine to downscale 1280*720 image to 300*300 image and it should work fine.
Do you mind to try scaling and see if it works?