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.
741
questions
0
votes
0
answers
11
views
Accelerated learning when wrapping layers in a class
I am implementing a VGG-like network using Pytorch 1.13.1 (python=3.7.12) for image classification on the CINIC-10 dataset. The following two implementations turn out to have very different training ...
- 1
0
votes
0
answers
15
views
Benchmark dataset with both images and tabular data
In the medical sector, there are situations in which an image dataset is associated with a tabular dataset containing different features but the same labels as the image dataset. For example, suppose ...
- 221
1
vote
2
answers
21
views
How can i implement an confucion matrix?
im trying to do a research but i need to make a confusion matrix how can i do that on this model?
https://www.kaggle.com/code/stpeteishii/race-classify-densenet201
Sorry im so so new to everything.
- 11
0
votes
2
answers
12
views
How to use CIFAR 10 Vs. CIFAR 100 for Out-Of-Distribution (OOD) performance evaluation?
CIFAR 10 vs. CIFAR 100 is the most popular benchmark dataset for Out-of-Distribution (OOD) performance evaluation. Google in their 2022 post "towards-reliability-in-deep-learning"[1] used ...
0
votes
1
answer
14
views
Why CIFAR 10 Vs. CIFAR 100 is the most popular for OOD benchmark?
CIFAR 10 Vs. CIFAR 100 is the most popular dataset for the task of Out-of-Distribution performance evaluation. On the infamous "Papers-with-code" [1] CIFAR 10Vs.100 is the most used ...
0
votes
1
answer
107
views
Pytorch mat1 and mat2 shapes cannot be multiplied
The error message shows
RuntimeError: mat1 and mat2 shapes cannot be multiplied (32x32768 and 512x256)
I have built the following model:
...
- 27
0
votes
0
answers
10
views
What is the most efficient way of image document classification?
So, I am working on a project where I have to extract sales tax invoice from the pdf document which contains other files along with the invoice. I researched on the topic, and am considering two ...
0
votes
1
answer
6
views
How to measure image classification model robustness?
Image Classification models trained on animal classification data like iNaturalist or iWildcam sometimes developed spurious correlations with the background. How to measure model performance ...
0
votes
0
answers
10
views
Is there a way to use CNN to separate/cluster the images into N clusters without online learning or only very mild online learning?
There are lots of examples to use CNN as classifier to separate images into known classes. There also lots of examples to use CNN as encoder and generate embedding to check the similarity of objects.
...
- 101
0
votes
0
answers
12
views
CNN sharing weights in feature map
what do they mean when they say all
neurons in a channel share weights with one another? Do they mean that in a chanel or a featue map the weights are the same ?
0
votes
0
answers
28
views
Large Numpy array causes error when trying to load
I'm making an ai using image recognition, so I recorded each frames of me playing into a numpy array. It worked just fine when the first time I exported all the images and got the 6 thousand of them. ...
0
votes
0
answers
52
views
can I use tf.keras.layers.MultiHeadAttention for image classification task?
Could you please let me know whether it is possible to use tf.keras.layers.MultiHeadAttention() for the image classification task without using Vision Transformer techniqe?
0
votes
0
answers
13
views
How to process batch of images for video, using Object Detection Api?
Neural Networks are capable of processing batch of images at once. I am trying to implement this in my object detection api code but I couldn't do it.
This is where I take video reader's each frame ...
1
vote
2
answers
113
views
Should a CNN generalize to arbitrary positions in the data?
I have trained a CNN on one dimensional data that is the power spectral density (PSD) of a $N$ different classes of signals ($N=4$). Each of the $N$ signals has a different spectral shape (not shown ...
1
vote
0
answers
12
views
How can I test a model on longer sequences that it is trained on
I am trying to train a model on ECGs. Unfortunately, I do not have enough data for 30s ecgs but I have sufficient data for 10s ecgs. I have trained a CNN model and performs really well on the 10s data....
- 11
0
votes
1
answer
20
views
How to differentiate Bitmojis gender?
I have seen this Project Larry-zx's Githubproject
It is used to create a .pth file which can differenciate between a bitmojis gender.
Now I have created that .pth file but no idea how to use it, ...
0
votes
0
answers
8
views
Can accuracy improve when there is evidence of domain-shift between training and deployment?
A model for image analysis was trained using data captured with imaging system A. I then deployed the model on imaging system B. System B has better image contrast than system A. Features in the last ...
- 1
0
votes
0
answers
15
views
Image recognition model with CNN for face gestures is really bad
I have a dataset that contains facial expressions and their label, and I am trying to make a classification model for it. Unfortunatly, I can't manage to create a good model with CNN, as the highest ...
0
votes
0
answers
13
views
How to find a unique feature vector for retail items?
I'm working on this problem where we get images of SKUs (Stock Keeping Unit) or in other words retail products and my job is to classify which product is it.
I want to find a unique feature vector ...
- 101
0
votes
1
answer
269
views
numpy.ndarray' object has no attribute 'batch' [closed]
I am building an image classifier using cnn using the following code-
I am getting this error, despite making several changes-
Kindly help me fix this error.
0
votes
0
answers
24
views
Image Classification task with unevenly sized tiled images
I'm using a Tensorflow CNN in Python for Image Classification. My data consists of huge images that necessitate splitting into smaller tiles. However, the number of tiles differs per image as the ...
- 1
6
votes
2
answers
1k
views
Image classification architecture for dataset with 710 classes, 90,000 subclasses, and anywhere from 10-1000 images per subclass?
Been struggling with finding the best approach to handle this scenario, I'm also a novice when it comes to machine learning. I have a dataset of around 700 classes, 90,000 total subclasses, and ...
- 61
0
votes
0
answers
13
views
How to improve neural network for face classification?
I generated 700 1024x1024 images of female faces using an API. I labelled them either as attractive or unattractive.
The neural net should learn which face I find attractive and which not. But the ...
0
votes
0
answers
18
views
Number of CNN's for processing timeseries using 2D CNN
I am processing time-series for classification using 2D CNN model (single channel) where I have converted stationary time series data into 2D image using an "imaging algorithm" known as ...
- 156
0
votes
0
answers
21
views
Determining the information loss due to undersampling
I have an image dataset that I need to segment into directories (train, validation and test) using ImageDataGenerator in TensorFlow/Keras. The dataset is highly imbalanced:
For this I have decided to ...
- 35
1
vote
0
answers
164
views
Proper way to reshape a image for training using CNN
I am new to Keras and facing some problems figuring out how to reshape the input image data properly. I have $16 x 16$ images, each with three layers, i.e., R, G, and B. The image data is in the form ...
0
votes
0
answers
9
views
Choice of proper machine learning model for signal processing applications
I have a data set that will be consist of 1D data that comes from the Fourier Transform (FFT) of time domain samples (x-axis is frequency, y-axis is magnitude). In order to classify $N$ different ...
0
votes
1
answer
76
views
Model does not learn when using Keras 'flow_from_directory', but learns fine with 'image_dataset_from_directory'?
When classifying images with Keras, I am able to achieve a validation accuracy around 90-95%, however, I am trying to improve with the use of augmentation so have switched from ...
- 1
0
votes
0
answers
14
views
How to use Image Annotation for Image Classification?
I have been working on Crop disease identification, but with the given data i failed to get the desired accuracy using random forest classifier. I was suggested to use image annotation and I did using ...
0
votes
0
answers
12
views
Would Stacking improve accruacy if base model accruacy is not good?
Problem: I would like to improve accuracy of stock price prediction image classification model using candlestick charts.
Base model: VGG16 and EfficientNet.
Base model input: Two models independently ...
0
votes
0
answers
990
views
How to automatically save images from colab to gdrive in seperate folders whose name are as same as the labels of the respective images?
I have a total of 30k images. They are distributed among 32 classes. I want to save these images from google colab to my drive with folder names as their label name. Can it be possible by python code? ...
- 121
1
vote
1
answer
139
views
CNN good results on train and test, bad results on real world data
I'm trying to build a neural network for an age detection task.
Here some details :
Dataset: I am using the "facial age" Kaggle dataset and the "UTKFace" dataset for a total of ...
0
votes
1
answer
15
views
How to train the machine to read xray image in correct position?
I have trained a model to classify Xray of various body parts using CNN.
Now I want the model to read a Xray image in correct position even if input image is given in wrong position(rotated).
I think ...
- 1
0
votes
0
answers
11
views
how to classify abnormal and normal xray using deep learning?
I have classified Xray of various body parts using CNN in python.
1)I want to check whether the input Xray image is straight or upside down( I think letter "R" in the Xray can be used for ...
- 1
0
votes
0
answers
14
views
How to choose the threshold for recurrence plot?
Context: I'm doing the final project for my bachelors and it's about identifying apnea in eeg signals with a CNN. I'm dividing the signal in equally sized segments and then generating images for each ...
0
votes
0
answers
18
views
Getting low accuracy on base ViT while pretraining on Imagenet-1k
Has anyone successfully pretrained ViT-B on imagenet-1k and got reasonable image classification accuracy?
I'm trying to do a simple pretrain of ViT-base on imagenet-1k dataset from scratch, but the ...
0
votes
0
answers
41
views
Best Image Embeddings technique for video similarity
The problem description:
Given a large dataset of video (and growing rapidly) we are embedding every frame of every video and comparing frames to each other to find identical and near identical frames....
- 101
0
votes
1
answer
32
views
Increasing/Decreasing importance of feature/thing in ML/DL
I have 3 cases:
I have a classification model that will be used to classify cats and dogs. On my train data dog pictures has a watermark on them, but cat pictures don't. The problem is: Whenever I ...
- 91
0
votes
0
answers
31
views
Are there applications where you don’t need positional embeddings for transformers?
Are there applications where you don’t need positional embeddings for transformers?
Applications using positional embeddings with transformers: machine translation, image classification, etc.
0
votes
1
answer
41
views
CNN resize images
Reducing images size will cause a loss of information for sure.
If a have a model that perform better on resized images (50x50) than on original size images (224x224), what can I deduce ?
There is a ...
1
vote
1
answer
38
views
Improve CNN classification accuracy
I am training a CNN model with about 20.000 images with two classes each 10.000 images. The size of the images vary between 50*50 pixel and 1000x500 pixels. I am resizing all images to the average ...
- 113
0
votes
1
answer
28
views
About improving the classifier when using a pre-trained model
I have tried adding a layer in the Resnet Model as shown:
...
- 181
0
votes
0
answers
18
views
Classification task in Adaface
I have a closed dataset with 15-20 people (10 images per person) and I use Adaface to extract feature embeddings. I was wondering what is the best classifier? Is SVM (linear Kernel) a good one? What ...
- 1
0
votes
0
answers
49
views
CNN age classification --- low accuracy
I have a dataset of 34k (200x200) images and I want to build an 8 class age detector.
I've tried a lot of different networks design, regularizations, dropout layers, grayscale images, data ...
0
votes
0
answers
19
views
Using SSL to label unlabeled images [ImageNet]?
Let's say I have a bunch of images from ImageNet and their corresponding labels, I also have a set of labels that aren't labeled and I'd like to label them, what are some semi-supervised methods/...
- 101
2
votes
2
answers
466
views
SGD performing better than Adam in Random minority oversampling, I don't know what is the reason. Help
So my dataset image before and after balancing looks like this:
But when I train with Adam(0.0001) and SGD(0.0001), the results are very different. Why? What is going on under the hood?
This is ...
- 21
0
votes
0
answers
8
views
image classifcation model's depth and width
I wonder how deep and wide deep learning model should be. Where can I possess some information/rules how many layers and how wide they ought to be?
I created basic image classification model with ...
- 1
10
votes
2
answers
4k
views
Have 100% images from ImageNet been proven to belong to the class annotated?
Is it proven that all 15M images were manually classified correctly and there are no mistakes or randomly selected responses collected?
- 200
1
vote
1
answer
70
views
Recognize chatbox on game screenshots
I have videos from a computer game. In this computer game, during the rounds, there is a chat box where players can write messages. I want to read the content of this chatbox.
Difficulties are here:
...
- 13
0
votes
1
answer
30
views
ML/DL model needed to perform binary classification on binary input image dataset
I desperately need help regarding ML/NN models that would be appropriate for binary input data..
So, I have an image dataset in which [R,G,B] values can only take ...
