Questions tagged [image-classification]

579 questions
2
votes
2 answers

What information do image pixels hold?

For a color image, say with dimensions 320 by 240, we have 76,800 pixels in the image. What does each pixel represent for a color image? Is it just the RGB values for that pixel? How are shapes and textures represented in pixels? If each pixel in a…
Sid
  • 107
  • 2
  • 8
2
votes
0 answers

Accuracy of Multi Layer Neural Network using Backpropagation around 86% normal?

Recently, I started trying to train a neural network using backpropagation. The network structure is 784-512-10, and I used the Sigmoid activation function. When I tested a single-layer network on the MNIST dataset, I got around 90%. My results are…
2
votes
0 answers

Incorrect printed message in tensorflow image classification tutorial due to warning "Could not load dynamic library 'cudart64_110.dll';...."

I am following along an image classification tutorial from tensorflow from the following link: https://www.tensorflow.org/tutorials/images/classification. I have tried following along and when I reach the lines image_count =…
SRT
  • 21
  • 3
2
votes
0 answers

Why does total size of dataset in neural network affect memory usage

Initially, I was trying transfer learning in image classification model using 268 test images + 65 validation images of 256x256 sizes. (The code I am using is from https://github.com/conan7882/GoogLeNet-Inception) However even with Tesla K80(16 gb…
2
votes
2 answers

Why is my model overfitting on the second epoch?

I'm trying to train a deep learning model to classify different ASL hand signs using Mobilenet_v2 and Inception. Here are my codes create an ImageDataGenerator for creating the training and validation set. # Reformat Images and Create…
2
votes
0 answers

(TensorFlow) TimeDistributed layer for image classification

I know that “Time Distributed” layers are used when we have several images that are chronologically ordered to detect movements, actions, directions etc. However, I work on speech classification using spectrograms. Every speech is transformed into a…
2
votes
2 answers

How to load dataset for in Keras using Python?

I'm a beginner to learn Keras using Python. I've read some sample code of dataset loading using MNIST Dataset. I don't understand the variable (X_train, y_train) and (X_test, y_test). Please, help me explaining the purpose of these variables. Also,…
zml
  • 51
  • 7
1
vote
0 answers

tflite_flutter interpreter.run input error

I'm trying to do image classification in Flutter using tflite_flutter package, the code is from tflite_flutter github but I got this error E/Parcel (29971): Reading a NULL string not supported here. I/flutter (29971): afah aa I/flutter (29971):…
1
vote
0 answers

Is my Neural Network for image classification code properly being trained?

Task: Classify image if it is image of human or not. Train set: Composed of 200 image which is labeled(train_y) 0 = not human, 1 = human Test set: Composed of 49 image which is labeled(test_y) 0 = not human, 1 = human Both 64*64 size image with RGB…
James Jang
  • 31
  • 7
1
vote
0 answers

Training Vision Transformer on Custom dataset

i am trying to use a pre-trained ViT pytorch model. It is pre-trained on imagenet with image size 384x384. Now i want to fine tune this model on my own dataset. But each time when i load the pre-trained ViT model and try to fine tune it i got an…
1
vote
1 answer

How do I get the validation accuracies when using VisionClassifierTrainer

I am unable to plot the validation accuracies Vs epoch curve while using the following code from hugsvision.nnet.VisionClassifierTrainer import VisionClassifierTrainer from transformers import ViTFeatureExtractor,…
1
vote
0 answers

How to calculate SHAP values after transfer learning Resnet18 model?

I modified Resnet18 model so it would predict 2 classes (cats and dogs) instead of 1000. I then used SHAP library for plotting the marginal contributions of the features. On pretrained Resnet18 receiving shap_values works absolutely fine. However,…
1
vote
0 answers

client side tensorflow.js image classification problem

im trying to create a client side web app that uses a pretrained model to classify an image as a fruit or vegetable. the model was pretrained in azure custom vision and was exported as a tensorflow js model. app.js code: // Load the model const…
1
vote
0 answers

Accuracy of the test set for a binary classification model, and using predict() values don't change

i'm doing a relatively simple binary classification model using ResNet50 as transfer learning model. Using Predict on multiple or single images causes various different errors that i mention below. I didn't know what exactly to use as a question…
Heba
  • 31
  • 3
1
vote
1 answer

TensorFlow image classification model gives different prediction when run in Spyder IDE and in CMD

I have made a TensorFlow model script that saves the model for later use. Its a Image classification model with sequential neural network that takes in the image and classifies it based on three output classes. When I run the model on the same file…