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.
754
questions
0
votes
0
answers
9
views
ML approach for quantifying building quality perception
I'm working on a project to model public perceptions of buildings in a tourism context, focusing on attributes like beauty and mystery. The data I have is a labeled dataset of building photos, each ...
- 101
0
votes
0
answers
5
views
How to handle multiple training jobs in AWS Sagemaker Pipelines?
I am trying to create a pipeline for training an image dataset via Sagemaker Pipelines. Based on the examples I understood that for all distinct stages like data preparation, model training, ...
0
votes
0
answers
19
views
Using cropped background images as background class
I’m currently working on a binary image classification problem using high resolution (up to 6000x4000 pixels) images with complex backgrounds, and CNN transfer learning.
In order to reduce Images size ...
0
votes
0
answers
42
views
Competition test set performance much lower than validation set
We are a team of 3 participating in a university competition for a deep learning course. The competition involves a binary image classification task where we have to predict leaf diseases on a (5200, ...
0
votes
0
answers
22
views
Test accuracy is very low, compare to Trian and validation accuracy for image classification for 400 class
I am working on image classification with 400 class , during training , I am getting good training and validation accuracy , but test accuracy is approximate 0-1% .My input image is 1 scale , with ...
0
votes
0
answers
8
views
Pretrained computer vision models that accept as input a segmented image and the original image
My data is a set of segmented images with extra details:
there is 30 object classes
each object is labeled with its state (very old, old-fashion, modern)
and each object is also labeled with a second ...
- 1
1
vote
1
answer
38
views
How to use additional features in image captioning?
I have the following question - is it possible to train a model based on Transformer architecture to use additional attributes to generate a caption for an image?
For example, I have a dataset with ...
0
votes
0
answers
14
views
Which image classification methods/models could suit my (product) image classification problem?
Say you are a potato chips company. The goal is to have consumers upload images of the product they are having issues with and be able to identify the product by brand/variant using machine learning. ...
0
votes
1
answer
26
views
Binary Classification of Images- CNN
I am learning ML and am working on a CNN problem where I need to classify images of CATS and DOGS.
The way I have setup the labels is that cats are 1 and dogs are 0. I have made the final output layer ...
0
votes
0
answers
51
views
Different generated patches from original image using vision transformer (ViT)
I am using ViT for image classification, I scaled images in range of [-1,1], and I also padded images. Then, I used the following code to see the original image and generated patches, but the output ...
- 1
0
votes
0
answers
31
views
My VGG16 Model's training and validation accuracy scores are stuck
Im trying to create an image classification model that classifies plants from an image dataset made up of 33 classes, the total amount of images is 41,808, the images are unbalanced but that is ...
0
votes
0
answers
39
views
3D CNN accuracy is too low, how to improve it?
I have just started learning image processing and this is my first time working on video classification. I am trying to develop a model that recognizes hand gestures using the EgoGesture dataset(more ...
- 1
0
votes
0
answers
19
views
Why does the first call to a TensorFlow function execute much slower than the second call?
I was doing an Image Classification problem using TensorFlow. I was generating the mean images for two image datasets having the same size. The dataset was generated using the tf.data API. Thereafter ...
- 77
0
votes
0
answers
30
views
How to remove augmented data from test data
I am working with this dataset https://data.mendeley.com/datasets/hxsnvwty3r/1 for object classification model like CNN. In the description of the dataset, I see in the description there are "...
- 1
0
votes
1
answer
18
views
Object Classification Dataset Creation
There is a problem I've faced recently which I'm not sure my approach is proper or not. There is bunch of field videos which I run a semi-supervised detection model to extract crops to train my ...
- 38
0
votes
0
answers
20
views
Image classification of centered objects with convolutional neural networks
Given that I have a set of images that contain multiple objects for which labels exist and the object the image label refers to is always in the center. The objects vary in size. I want to train a ...
- 1
0
votes
1
answer
93
views
Histogram of Oriented Gradients (HOG) - Why normalize 16x16 blocks and not the whole picture?
I'm trying to learn Histogram of Oriented Gradients (HOG)
I understand why we compute the gradient and the orientation and also map every gradient into a 9 binaries histogram that spans from 0 to 180.
...
- 115
0
votes
1
answer
26
views
Detector vs Classification - Detecting a netted bag for fruit/vegetables in image
The application is detecting the presence of a netted bag in an image.
The image can contain fruit and vegetables, either with or without a netted bag around them, or below them (no constraints about ...
0
votes
1
answer
25
views
How do I create an Image Dataset for a CNN?
I'm currently working on assembling a CNN for image classification with tensorflow.keras. I have all my images in a file which I already uploaded to my program. Also I have CSV-Files for training and ...
0
votes
0
answers
15
views
Is a csv file to store image path and class neccessary for image classification?
I just get my hand-on a basic deep-learning project. I am working on multi-class image classification project with e-commerce dataset. I am not sure whether by storing training images in sub-folder ...
- 1
0
votes
1
answer
86
views
Combine two separate models created via Transfer Learning?
Suppose have two 'image classification' models created by transfer learning on the same base model[1], each producing a different set of labels/classes. Trained at different times, with different ...
- 101
0
votes
0
answers
32
views
Create a TensorFlow Input pipeline from GCS Bucket?
I wish to generate a TensorFlow input pipeline (i.e. tf.data pipeline) for an image classification project. The images stored in a GCS bucket having access controls and is not publicly accessible. And ...
- 77
0
votes
0
answers
17
views
Multilabel Image Classification - problem with probability at prediction
I'm building a multilabel image classification problem usinc MIMIC CXR dataset. I'm struggling with probability at prediction as for every image in test dataset the probability of an existance of ...
- 1
2
votes
1
answer
678
views
Input dimensions for the EfficientNetV2 family of models
I have a question regarding the EfficientNetV2 family of models. If my understanding is correct there are 6 models under this family - B0 to B1 & S are the comparatively smaller models while M &...
- 23
0
votes
0
answers
12
views
TensorFlow lite classification model;{1,1,1,3}
How can I initialize and insert images into this classification model; what is meant by {1,1,1,3} according to my parameters it should be {1,size,size,3} please help
try {
Firstclass model = ...
0
votes
0
answers
22
views
Overfitting on implemented Dense-Net architecture
I have been playing with different architectures and see how they would perform on the quick draw dataset. Even though the accuracy is significantly higher, I can't reduce overfitting no matter what I ...
- 1
0
votes
0
answers
61
views
Object detection on largest number of classes
Does anyone know any pretrained object detection models to run with python with highest number of objects to be recognised? Yolo finds 80 objects, it is good if I can find a larger number. It would be ...
- 37
0
votes
0
answers
29
views
How do I test with custom images for a model that was trained on quick draw npy dataset
I have been trying to test my CNN model on a custom doodle of an apple that I drew. But even when I preprocess the image to have the same shape with the training data, the model gives wrong prediction ...
- 1
1
vote
1
answer
33
views
Different validation sets give very different results. What can be the reason?
I have ~78k microscopy images of single cells, where the task is to classify for cancer (binary classifier). The images are labeled according to which patient the data came from. I do the train-val ...
0
votes
0
answers
13
views
Validation Loss not decreasing for RESNet model
I have been trying to train a Resnet model to classify Diabetic Retinopathy images into binary classes. The dataset consists of around 35k images. The val loss and accuracy does seem to behave weirdly ...
0
votes
0
answers
52
views
Why does my validation loss go so high after few epochs?
I am facing an issue with my pretrained mobilenetv3 model, it is quite strange how the validation loss is behaving, it starts low but then goes up ridiculously high. I have normalized my images as ...
- 47
0
votes
0
answers
54
views
How can I prevent mobilenetv3 from overfitting with less data?
So I have around 462 images and I can't really get more images. I am using a pretrained model of MobileNetV3 with the respective weights. I am facing a huge problem of overfitting and no real solution ...
- 47
1
vote
0
answers
61
views
MobileNet validation loss not decreasing over time
I am trying to train a MobileNetV2 on a custom dataset, to image Classification task.
Cardinality is 864 images, split in 70%/20%/10%, balanced between the 3 different classes.
Weights are pre-loaded ...
- 11
0
votes
1
answer
40
views
Improve image classification model with trained generator
Is it possible to improve an image classification model with a generator (trained class conditionally). (so this is same source/target distribution and same source/target task, so not domain ...
0
votes
2
answers
196
views
which Keras accuracy metric for multiclass classification
I am training a CNN for multiclass image classification into 4 images , what accuracy metric should i use from Keras. My labels are not one hot encoded as I am trying to predict probability of ...
0
votes
0
answers
10
views
Image classification approach for float outputs
I have an image input and the model should be able to predict its 15 feature values as output. I am being told that i should use an image classification model to solve this. can somebody suggest me a ...
- 1
0
votes
0
answers
15
views
Image based ML paradigms where input vector integrates pixel intensity with pixel coordinates
Are there image based machine learning formulations where the input is not just the plain 2D image grid but one where pixel intensity $I(x,y)$, at position $(x,y)$ is coupled with the actual position ...
- 101
0
votes
1
answer
179
views
Does Rotation and Translation range in augmentation? (image data)
I am building a classification model. I want to use augmentation (less images + but no class imbalance)
I want to use rotation and translation. Does it matter what range I use and how big the range is?...
- 482
0
votes
0
answers
49
views
This model is too slow. I'm looking for a good, fast-enough, out-of-the-box, pre-trained image classifier. Any tip?
I have been using this on a laptop without a GPU: https://github.com/pharmapsychotic/clip-interrogator
Currently it takes about 10s to classify a single image on my own computer.
I use ...
- 101
0
votes
0
answers
10
views
Image Captioning problem where we expect a specifc type of answer depending on the objects in the image
I'm working on an ML problem where I'm trying to generate captions for the images, but depending on the category of the image, the caption should contain specific information. For example, if the ...
1
vote
1
answer
43
views
Can we create tensorflow or tflite model for object detection without uploading our dataset images to cloud?
I need to create a custom Tensor flow lite model for object detection to integrate in an android app. But I have a constraint that the dataset images to be used is confidential and cant be uploaded ...
0
votes
0
answers
24
views
AutoKeras create model from specific trial_id
I have trained ImageClassifier of 128 trials, I found best console result on trial 99. How can I load that structure at 99 trial as a model? I want to fit it and save it as well.
0
votes
0
answers
27
views
YoloV5 results rendered lead to different picture
I basically trained a custom model to detect peg-solitaire games.
In my example I use the results of the detection to render a board with matplotlib
...
- 157
0
votes
0
answers
22
views
Facing Problems in Dilation and Erosion of Segmented Images of Knee X-Rays
I am working on a project to grade the severity of Knee Osteoarthritis using X-Ray Images. Before feeding the images into the machine learning model and enhancing the features of Knee osteoarthritis i....
0
votes
0
answers
17
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
36
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 ...
- 229
1
vote
2
answers
29
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
82
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
457
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 ...
1
vote
1
answer
10k
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:
...
- 37