We changed our privacy policy. Read more.

Questions tagged [image-classification]

For questions about image classification: a decision problem where an algorithm must decide to which class ('cat', 'chair', 'tree') an input image belongs.

Filter by
Sorted by
Tagged with
1
vote
0answers
5 views

Pre-processing images for fine-tuning

When you are fine-tuning a CNN like ResNet, VGG, EfficientNet, etc and you want to train the model with your own images, or even when you want to do a inference with any image of your dataset, do you ...
1
vote
3answers
36 views

100% Accuracy and 0 loss in image classification

I am working on image classification using CNNs and the pretrained model VGG16, my dataset has 3 classes with almost 900 images per class. after traning for 5 epochs my model reached 1 accuracy with 0....
1
vote
1answer
26 views

Trained model performs worse on the whole dataset

I used pytorch as the training framework and the official pytorch imagenet example to train the image classification model with my custom dataset. My custom dataset has 2 different label (good and bad)...
1
vote
0answers
12 views

Why concatenating these layers, why applying masks over and over to partial convoluted image?

I have to ask some questions about one topic. In this sentence of Nvidia's article they are saying: "The last partial convolution layer’s input will contain the concatenation of the original ...
0
votes
0answers
12 views

Multiclass to Binary Classification

Before I start, I would like to let you know that I am a novice in deep learning. I have an image dataset which contains around 900K images. The dataset divided by 3 classes and 3 subclasses for each ...
1
vote
0answers
9 views

Classification of RGB images

What is the preferred way to specify the features for image classification when the input consists of RGB images? Is it a good approach to flatten the image into a single vector (where for instance '...
0
votes
0answers
9 views

Can i segment/crop out image using image processing?

I have a large dataset of bottles. I want to train a model with this dataset. But before feeding the input images to the model I want to crop out the bottle from the background. Is there a way to do ...
3
votes
1answer
159 views

How do you add negative class sample for binary classification?

How do you prepare the negative dataset for binary classification? Let us say that I am building a classifier that has to classify whether the input image is of a car or not. I already have a dataset ...
0
votes
0answers
22 views

Keras data augmentation for fashion minst data set performs worse than without it

I am trying to build an image classification model for fashion mnist data set. I designed a network and achieved accuracy of ~93%. I wanted to improve it further, so I decided to augment data using <...
0
votes
0answers
4 views

Transfer learning on images with higher dynamic range

Is it possible to fine-tune a CNN-based model previously trained on images with 8 bits depth [0 ~ 2^8] to fit a 16 bits depth [0 ~ 2^16] images? if there is any research paper that confirm that, it ...
0
votes
0answers
12 views

Tensorflow convolutional neural network error during training

I built a simple CNN for binary image classification (cat/dog). ...
0
votes
1answer
32 views

Classification of scanned documents in pdf files using deep learning or NLP

I know classifying images using cnn but I have a problem where I have multiple types of scanned documents in a pdf file on different pages. Some types of scanned documents present in multiple pages ...
0
votes
0answers
4 views

Best smoothing image techniques for digit recognition

There are several ways to smooth an image like - Gaussian Blur Median Blurr etc. as mentioned on the page - https://docs.opencv.org/4.5.2/d4/d13/tutorial_py_filtering.html Suppose I have an image ...
0
votes
0answers
10 views

Can smbd tell why ViT takes ~twice as much time to train?

I'm using a dataset with 300k images (ChestXray). On ViT paper authors claim that ViT is 2-4 times faster in training due to parallelization capability, but in reality it's the opposite. I played with ...
0
votes
0answers
18 views

Digit recognition images for testing

I made a python program to solve the digit recognition problem that is mentioned here - https://www.kaggle.com/c/digit-recognizer The sample dataset that is given on this website is basically pixel ...
1
vote
0answers
15 views

Forward height/width information into classification model?

Please forgive me if it's not the right StackExchange, but I didn't find any related to computer vision questions. Problem: I have a pipeline for object detection and classification where I first ...
0
votes
0answers
4 views

How to create COCO format data out of list of boxes

I have $N$ images. I have a script that extracts boundary boxes of an object that I am interested in. For each image, I may get $m$ boxes. There is only one item that I am interested in which is cat. ...
0
votes
0answers
22 views

Encoding technique used in Keras ImageDataGenrator class

I would like to know what encoding is used by ImageDataGenerator for encoding the class labels. I have done a lot of research and found that there is a variable called ...
0
votes
0answers
13 views

How to modify this training function in order to print the aggregation of models

I have 3 VGG: VGGA, VGGB and VGG*, trained with the following training function: ...
3
votes
1answer
111 views

Train-test split and augmentation strategy for small dataset for video classification problem

I have a small data set of videos of approximately 100 videos for each class for a binary classification problem. This results in a total of 200 videos. I am applying two types of augmentations on the ...
0
votes
0answers
17 views

how to make image classification model to detect object and track object in a video

i have built a disaster classification model . now i want to use this classification model to detect ex- cyclone in a video to draw bounding box around it and track the cyclone if possible.is it ...
0
votes
0answers
13 views

can i do object detection on pretrained classification model...?

so i built a natural disaster classification model using transfer learning Renet50(tensor flow) got 98% accuracy and now instead of just classifying natural disaster lets say a cyclone appeared in ...
0
votes
0answers
8 views

Mobile or web app to standardize image collection

Is there an app that I can use to unify / standardize how I take pictures to form a data set? Assuming that the image size, object location are, maybe picture quality are of importance for a CNN ...
1
vote
2answers
50 views

Combining CNNs for image classification

I would like to take the output of an intermediate layer of a CNN (layer G) and feed it to an intermediate layer of a wider CNN (layer H) to complete the inference. Challenge: The two layers G, H have ...
0
votes
0answers
16 views

How to extract undetected object class labels after extracting `y_pred` from `predictions. pth` inference file for Mask rcnn

I training maskrcnn on a custom dataset with two classes (1 and 2). After testing, I get some files segm.json, predictions.pth, <...
0
votes
1answer
33 views

Underfitting issue [closed]

I have a small datset (530 images) trained on a simple CNN called AquaSight. This is the architecture. I had an underfitting problem, 75% accuracy and 0.6 loss. How can I solve the underfitting ...
0
votes
1answer
23 views

SageMaker - mini_batch_size what is it and why can't I get it higher than 5?

I'm following this tutorial but I keep getting the error: "The number of input images must be bigger or equal to the mini_batch_size." I've tried a series ...
0
votes
0answers
30 views

Imagenet2012-Subset dataset

I want to use imagenet2012-subset. As I understood, I should first download imagenet dataset manually (it is about 150 GB). I thought it is not reasonable. Is there any way to use imagenet2012 subset, ...
-1
votes
1answer
22 views

how to debug model that why that model prediction goes to a particular label for an incorrect prediction?

Let's say I have implemented a model to predict whether the image is dog, cat, bird, elephant. my model predicts the input dog image as a cat how to interpret the model how/why it goes high prediction ...
0
votes
0answers
18 views

Low accuracy in the image classification model

I am trying to build an image classification model to classify whether Thistle Caterpillar is present in an image or not. The classification is a single label classification. The dataset and the code ...
0
votes
0answers
9 views

Understanding how anchors are created in a regional proposal network

I understand that in Faster R-CNN, the image is fed into a pre-trained CNN (such as VG16). So say I have a 37x50x512 feature map. Firstly, I assume that each feature map (37x50x1) is fed into the RPN? ...
0
votes
1answer
152 views

Problem with batching tensors - InvalidArgumentError: Cannot batch tensors with different shapes in component

So, I am trying to build this model for an image classifier using the oxford flower dataset 102, and I am having issues when trying to fit the model. The error says: ...
0
votes
0answers
21 views

Don't understand Channels in Covolutional Layers [duplicate]

I'm struggling to understand the concept of 'Channels'. What does a channel mean in the context of an image. I understand that a grey scale image only has 1 channel, and a RGB has 3, but then I see ...
0
votes
0answers
18 views

Comparing results of different image splicing methods on a part of the CASIA 2.0 dataset

So I am working on an image splicing detection algorithm using ResNet-50 model. I am using the CASIA 2.0 dataset which consists of 7491 Authentic images and 5123 Fake images. However out of the fake ...
0
votes
0answers
25 views

Training data for image digit recognition

I am creating a digit image recognition algorithm. For this I would like to collect sample data to train the model. Does python have any inbuilt libraries for this? Where could I get good training ...
1
vote
0answers
30 views

Image Classification using ML and Image processing

I'm doing a project in ML and Image processing where I try to classify cats and dogs! dataset: https://www.kaggle.com/chetankv/dogs-cats-images The models I'm using: KNN, Random Forest, SNM, and ...
1
vote
0answers
40 views

Image classification with CNNs

I created an image classification model using CNNs for 235 classes and I got 71% accuracy on the test set. My dataset contains some classes with more than 1000 images and others with 30 images. For ...
4
votes
1answer
39 views

Can you use fully convolutional networks for binary classification?

I know that fully convolutional networks can be used for image segmentation and similar but I wondered if you could also apply them to simple image classification tasks. And if so, what is the proper ...
0
votes
0answers
13 views

Image classification - first production coding try

TLDR Experienced non-ML developer has done the basics to learn beginner ML, now needs to put it to real use - looking for help. ...I guess a common/frequent situation for many! For mods - I've tried ...
1
vote
1answer
48 views

Comparing two data distributions, not the probability distribution

Let's assume that I have the 200 MNIST data. These 200 data are divided into two training dataset. one training dataset has 100 and another training dataset has the remaining 100. I trained my two CNN ...
1
vote
1answer
61 views

Difference in performance Sigmoid vs. Softmax

For the same Binary Image Classification task, if in the final layer I use 1 node with Sigmoid activation function and ...
1
vote
0answers
31 views

Is it possible to combine cnn and rnn?

I would like to know if it is possible to combine rnn and cnn. I explain you : I have pictures of bikes, cars and moto and every pictures is linked to a text. For instance for a car I can have the ...
1
vote
1answer
13 views

Classifying visual environment in Tensorflow CNN (video analytics)

I am given a selection of videos of users exploring simulated 3D enviroments (kind of looks like the Sims video game) and I am tasked with being able to classify each room using a tensorflow framework....
0
votes
0answers
16 views

How to utilize the multilabel calssification labels during the course of training

I have a data set that consists of images. I am trying to perform multi-label classification on this data set. But the training labels consist of too many labels which are CSV file format. Now I find ...
1
vote
1answer
23 views

Studying and choosing between different neural network structures

I would like to develop a model that uses convolutional neural networks for image classification. From the many different network structures described in papers and articles online, I would like to ...
1
vote
0answers
14 views

Is it possible for class activation maps where the predicted class has no activations?

I'm trying out grad CAM from the captum library in pytorch for a 3 class image classifier that uses transfer learning on resnet50. The model has good accuracy, but when I was looking at the generated ...
0
votes
0answers
42 views

How deep learning extracts the features from images in image classification?

I'm working on an image classification project. I just want to know some basic level clarification. how does a neural network learn only the relevant features based on the label? Let's say I'm ...
4
votes
2answers
57 views

Is it advisable to use a model which is underfit but gives very high accuracy?

I am training a model for a single-label classification task in Vision. In this training, I am using oversampling of all the classes, and MixUp augmentation, along with rotation and dihedral ...
2
votes
1answer
34 views

Deep Learning Classification Model for data with time dimension

I know it might be a generic question but I would still appreciate some feedback. So I have a dataset with 4 dimensions (time, x, y, color). Where I have a total of 24000 records each with (5, 188, ...
0
votes
0answers
155 views

Call keras model in a C# desktop Application

I have a keras model for image classification saved in a .h5 file or Json file, and then I created a C# desktop app ( in visual studio 2019) which contains two buttons one to load an image and an ...

1
2 3 4 5
14