All Questions
Tagged with neural-network image-classification
152 questions
0
votes
1
answer
31
views
Accuracy and test_accuracy gives a result =1
I've developed a code for classifying hyperspectral images using three different convolutional neural network (CNN) architectures: 1D, 2D, and 3D. The code has two main parts:
Preprocessing and data ...
0
votes
0
answers
31
views
Converting multiple binomial logits to multinomial
I am faced with a image classification problem with 3 classes. My existing network consists of 3 'branches' each corresponding to one of the classes. Each of these branch outputs a binomial logit ...
0
votes
0
answers
8
views
Resources for writing CNN for semantic segmentation
I am intermediate/advanced in Python and new to machine learning. Most of what I know about deep learning I learned through Deep Learning with Python by François Chollet. I am trying to do image ...
2
votes
1
answer
128
views
Creating a custom loss function for an image classification model where the label matters
I have the following dataset of images, where we can see the image distribution of labels below.
I want to construct a loss function that, on the one hand, outputs probabilities for a specific class ...
- 21
1
vote
0
answers
94
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
2
votes
1
answer
18k
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:
...
- 57
0
votes
0
answers
77
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 ?
- 13
6
votes
2
answers
2k
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
1
vote
1
answer
587
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 ...
1
vote
1
answer
260
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
57
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 ...
0
votes
2
answers
3k
views
1
vote
1
answer
70
views
Advice / Good practises | CNN poor image diversity
I am currenty working on a project that involves multiple cameras fixed on the ceiling. Each time I take a picture, I check whether there is a "cart" right under the camera.
I would like to ...
- 11
2
votes
0
answers
73
views
Which model is used for document extraction (CamScanner, Microsoft Lens etc)
I want to start a small project where I'd create a model(s) that would extract document from a picture and rescale it, something like CamScanner or Microsoft Lens apps do.
I've gathered a small ...
- 21
1
vote
1
answer
156
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 ...
- 27
1
vote
0
answers
32
views
Why concatenating these layers, why applying masks over and over to partial convoluted image?
I'd like to ask some questions about a topic. In a sentence of Nvidia's article they are saying:
"The last partial convolution layer’s input will contain the
concatenation of the original input ...
- 11
3
votes
1
answer
435
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 ...
- 231
3
votes
1
answer
342
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 ...
- 133
2
votes
1
answer
85
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 ...
0
votes
2
answers
239
views
How to get >=85% accuracy on 3-class classification task
Now I am solving the problem of 3-class classification (in the task you need to understand who is in the picture - a panda, a cat or a dog). The dataset consists of 3000 images. To solve the problem, ...
- 23
1
vote
1
answer
137
views
Model that predicts probability of correctness of another model
Problem:
Given a neural network for image classification with $1000$ classes, the objective is to create another model which will output the probability of the neural network giving the correct ...
- 53
0
votes
1
answer
261
views
Image classification with CNN Python
I'm working on image classification using CNN, my dataset contains more than 50 classes (50 folders) which represent the types of car parts, and in each folder we have vehicle brands, each vehicle ...
- 41
1
vote
1
answer
28
views
Approach to labelling new data for training
Overview:
Imagine an application that identifies cats and dogs from their phone camera. User's take a photo of their pet and it tells them if it is a dog or a cat. The data is then sent to the server.
...
- 111
0
votes
0
answers
351
views
Validation Accuracy not going beyond 60% for image classification with 5 species of snake
My dataset has about 17000 images belonging to 5 classes. I am using 16000+ images for training(about 3k/class) & 500 for validation(100/class). Training accuracy is very good but validation ...
1
vote
2
answers
478
views
What are the activation functions in Convolutional Layers for?
I read a lot about CNNs but I didn't quite understand some things:
What are the activation function in CLayers for? If I understood it right, the only weights in these layers are the ones in Filters, ...
- 15
2
votes
1
answer
46
views
Nutritional image classification task
I need a model that is able to receive as input an image of a nutritional information chart and tell the level of sugar that the product has. It would be a 3-class classification problem (low if sugar ...
- 81
1
vote
0
answers
37
views
Close set and open set classification at the same time
Is it possible to use a neural network(or another approach) to classify image based on trained data and at the same time if new image classes are introduced in the test set it should classify those ...
- 13
1
vote
0
answers
65
views
Denoising Prior to Image Classification
From what I have read, Denoising during preprocessing for image classification tasks seems to be a bit controversial.
While on one hand it might improve classification accuracy, the computational ...
- 123
1
vote
0
answers
134
views
Large general-purpose model vs ensemble of many smaller models
I am reading this paper - https://arxiv.org/abs/1503.02531v1 - devoted to knowledge distillation in neural networks.
One interesting approach is mentioned in this paper in sections ...
0
votes
1
answer
2k
views
Keras model has a good validation accuracy but makes bad predictions
I have this model which takes 9000 images in a dataset containing 96 categories of traffic signs, each category has more or less the same number of images (about 50). This is the model I made but ...
- 461
0
votes
1
answer
318
views
How do I deal with the fact that I have images which are not consistent with the class they belong in an image classification problem with CNN?
I am really new to Neural Networks and to Machine Learning in general, and I have been given a dataset composed by images for performing multi-class image classification with a CNN.
The images were ...
- 921
1
vote
1
answer
133
views
How to deal with a binary classification problem, where the instances in the negative class are very similar? [duplicate]
Let's say, one wants to detect, whether a picture of a fixed size contains a cat or not. But as a dataset, you have 10000 pictures of cats, and 30000 pictures which don't contain a cat, but are very ...
- 13
0
votes
1
answer
38
views
Creating a image classification model [closed]
I am working on a dataset to classify facial expressions.
Dataset has 7 classes, training images 28000 and test images 7000. I created 2 models
Model1:
this model has 11 layers. Initially model was ...
- 13
0
votes
0
answers
75
views
What are the best models developed for image classification
For inventory detection problem, when you cut single product images from the shelf, the next step you have to do is that you should label the product and identify which category this product belongs ...
- 111
1
vote
0
answers
12
views
Generalise a CNN model for Question vs Spam . Techniques to generalise the model apart from more data
For my problem, every image which is not a picture of a question on a paper (either from text book or handwritten), is a spam. It means that each and every image in this world is a spam for my case ...
- 323
-1
votes
1
answer
38
views
Suitable neural network type to classify text in images
I have images that contain text and I am not sure what is the type of NN that can do the job for me. Basically, it will have to read the images and understand the text in order to be able to classify ...
- 141
1
vote
2
answers
274
views
Positive/negative training sample imbalance in multi-label image classifiers
I'm trying to train VGG-16 on the Pascal VOC 2012 dataset, which has images with 20 labels (and a given image can have multiple classes present). The examples are highly imbalanced, so I've "...
- 31
1
vote
1
answer
111
views
Training set of a NN that classify Cat or Not Cat
Is it possible to build a Convolutional Neural Network (using Keras, Tensorflow) that can give output as 1 for an image of a Cat and 0 for everything else?
How would the training set look like?
I mean,...
- 125
1
vote
1
answer
89
views
Retraining of object detection models
I came across the concept of retraining of models a few days back.
So tensorflow recommends to retrain an already trained model instead of making a new one from scratch so that the whole process takes ...
- 13
1
vote
1
answer
29
views
Image classification using cnn [closed]
I did image classification using CNN and it successfully classified the images but How to save predicted images to separate folder for example i have two classes cat and dog after prediction how to ...
4
votes
2
answers
9k
views
Training accuracy is ~97% but validation accuracy is stuck at ~40%
I am trying to classify images into 27 classes using a Conv2D network. The training accuracy rises through epochs as expected but the val_accuracy and val_loss values fluctuate severely and are not ...
- 41
1
vote
2
answers
2k
views
Image Classification low accuracy
I have a dataset that has two folders for training and testing. I am trying to determine whether a patient has an eye disease or not. However, the images I have are hard to work with. I've ran this ...
- 33
0
votes
1
answer
112
views
Error using image: Error when checking input: expected dense_56_input to have 2 dimensions, but got array with shape
I am trying to train a Sequential model using simple flow_from_directory() but i am getting this error , I have tried using lesser layers but the error dose not go away.
...
- 157
1
vote
1
answer
34
views
Label A records B times or label A*B records
This question concerns pre-training data sourcing.
Suppose you have a human workforce of B individuals and a potentially unlimited source of data.
The task is ...
- 11
0
votes
1
answer
36
views
Predictions of a Deep Learning Model
I’ve built a model that classifies digits from 0-9. My dataset is tf.keras.datasets.mnist. I use softmax as the activation function for the output layer.
Q1:
The output layer should consist of 10 ...
0
votes
1
answer
240
views
the size of training data set in the context of computer vision
Generally speaking, for training a machine learning model, the size of training data set should be bigger than the number of predictors. For a neural network, or even a deep learning model, the number ...
- 157
0
votes
3
answers
1k
views
How to train a Model which can check whether image is from existing classes or not
I have given an image dataset of 1000 classes, each class has 100 images. Now My requirement is to train a model which will take an image as input, and it should answer whether the image is present or ...
- 3
3
votes
1
answer
581
views
Convolutional neural network block notation
The paper by He et al. "Deep Residual Learning for Image Recognition" illustrates their residual network in Figure 3 as follows:
I am not a neural network expert, so could somebody please explain to ...
- 133
0
votes
1
answer
84
views
Feature-to-parameter mapping in neural networks
For neural networks, can we tell which parameters are responsible for which features?
For example, in an image classification task, each pixel of an image is a feature.
Can I somehow find out which ...
- 113
1
vote
0
answers
83
views
How can I make my own Neural Network model for Object Detection?
I'm using the ImageAI module in Python3 to do some object detection on some images I scraped from a video game. In testing, I am able to successfully detect normal world objects from a test photo of a ...
- 213