Questions tagged [image-classification]

579 questions
-1
votes
1 answer

Use a pre-trained model to classify images in 50 categories of my choice

As I said in the title, I would like to use a pre-trained ML model like InceptionV3 or similar to classify images from Instagram profiles. I'm currently using PyTorch and I can correctly made inference on the models that I'm trying, but I'm not…
-1
votes
1 answer

Image classification CNN model loss and accuracy flatline

I am working on a CNN model for multi-class image classification, while both loss and accuracy show flatline and values stay almost same. Could you please help have a look if any mistakes made and much appreciate if any advice? thanks a lot in…
-1
votes
1 answer

I have used softmax function with loss='binary_crossentropy' for a two class classification problem

for two class classification problem sigmoid + binary_crossentropy is fine or softmax + categorical_crossentropy is fine. But in my case I have used softmax(2 dense layers) + binary_crossentropy and trained a DL model.. Is this correct? Does the…
-1
votes
1 answer

PyTorch NotImplementedError in forward

i'm making a code that classifies numbers by using pytorch epochess =[] train_losses = [] test_losses = [] acc_training =[] acc_testing = [] for epoch in range (epochs): train_acc, train_epoch_loss = train_CNN(model,loss_function,…
-1
votes
1 answer

Adjustment of CNN Architecture when size of input image is changed

I am working on a CNN for color classification problem in pytorch. This is the architecture of my CNN : class Net(nn.Module): def __init__(self): super().__init__() self.conv1 = nn.Conv2d(3, 6, 5) self.pool =…
-1
votes
1 answer

Vgg16 and Resnet50 overfits despite including 100k images - Tensorflow

I am training a classifier using vgg16 and Resnet50. The data I have collected contains 100k RGB images belonging to four classes, each containing ~25k (the unbalanced issue was minor and compensated by augmentations). The dimension of each image is…
-1
votes
1 answer

Can we do predictions for sub-classes i.e. class within class?

I need to classify an object into multiple classes. Normally we are familiar with multi-class classification with a single hierarchy, but in my case I have two levels of hierarchy. See the below images to get a clear picture of what I am talking…
-1
votes
1 answer

Python CNN image classification model fails to classify individual images

I am very new to machine learning. Looking at other work, I trained the following model https://www.kaggle.com/code/konstansan/cat-and-flower-image-classifier, which shows very high accuracy (98 - 99%) based on calculations for the testing set. To…
-1
votes
1 answer

How to create a dataset for image classification

I trained a model using images I gathered from the web. Then, when inferences were made using images newly collected from the web, performance was poor. I am wondering how I can improve my dataset using misclassified images. Can I add all the…
-1
votes
1 answer

Can't deploy my large image classification model on Heroku

I trained an image classification model that I productionized using FastAPI and I want to deploy it via Heroku. My model is large (859 MB), hence I added it to my repo via GitHub LFS. However Heroku does not support GitHubs LFS by default and even…
-1
votes
1 answer

Trouble Understanding ResNet Implementation

I'm having trouble understanding and replicating the original implementation of ResNet on the CIFAR-10 dataset, as described in the paper "Deep Residual Learning for Image Recognition". Specifically, I have a few questions about the following…
-1
votes
1 answer

Why VGG16 model cannot be trained with its FC Layers

I am trying to train the VGG16 model code, but the loss is not optimized and seems that model's parameters are not updated. here is the model : import torch import torch.nn as nn import math import torch.nn.functional as F from utils import…
-1
votes
1 answer

How to resize(reshape) the images in CNN? Mathematical intuition behind resizing

I have been working on Images for few months for my internship, and recently I have been wondering that is there a mathematical way of resizing the images. This becomes a fairly difficult task to resize the images because many a times freshers like…
-1
votes
1 answer

Why am I getting very small number as CNN prediction?

I created a CNN using Tensorflow to identify pneumonia and sometimes it returns a very small number as a prediction. why is this happening? I have attached the link for the dataset Here I how I process and load the data. from…
-1
votes
1 answer

How to load your own labels for the classifier

I am a newbie here. I have a file path that lists all the images but I am stuck with connecting the labels to the images. I have a CSV file that has image no and the label. What would be the best way to approach this issue? FYI I am using a…
7006
  • 1