Questions tagged [cnn]

Convolutional Neural Networks (CNN, also called ConvNets) are a tool used for classification tasks and image recognition. The name giving first step is the extraction of features from the input data.

Filter by
Sorted by
Tagged with
0
votes
0answers
10 views

Can PCA help to reduce false positives in image-based classification?

I'm working on a 2-class problem where cancer cells need to be accurately identified from a mixed population containing cancer cells + white blood cells (WBCs). The model I have been using - SVM with ...
0
votes
0answers
12 views

An efficient way to encode & embed tabular data of a video into a transformer?

So a little bit of a background: I have a folder which contains video files of lets say humans doing a certain action (i.e. walking) where each .2 seconds is documented in a ...
0
votes
0answers
7 views

How to classify (supervised) a multi dimensional vector?

What kinds of machine learning tool is used to classify a vector of data which are not spatially correlated? I have a 158*158 image*15000 samples which I tried to ...
1
vote
0answers
9 views

Looking for multi output image datasets

I'm looking for image datasets that have multiple labels. So far I could only find one dataset of age, sex and ethnicity prediction but I'm looking for something a little less known than that one. ...
1
vote
1answer
18 views

Does validation_split in tf.keras.preprocessing.image_dataset_from_directory result in Data Leakage?

For a binary image classification problem (CNN using tf.keras). My image data is separated into folders (train, validation, test) each with subfolders for two balanced classes. Borrowing code from ...
0
votes
0answers
10 views

How can I reduce overfitting in CNN model for image classification, even after data augmentation?

its my first time posting here. I'm trying to build a CNN model that identifies fruits from a dataset of apples, bananas, mixed fruits, and oranges. So far, one of the things I have done to prevent ...
0
votes
0answers
15 views

Test/validation loss/accuracy fluctuation and relation to training loss/accuracy and regularization

I'm using CIFAR 10 dataset, and I'm applying CNN. I'm confused about my validation/test loss/accuracy curves and their behavior when I apply batch normalization and/or dropout. They fluctuate ...
0
votes
0answers
10 views

In a CNN architecture, is it possible to incorporate both class weights and data augmentation?

I'd like to conduct image classification using some CNN architectures, but the problem is that my classes are imbalanced, and each class has insufficient data. To solve this situation, I have a ...
0
votes
0answers
18 views

Augmentation for sound recognition of dog barks for CNNs

I am training CNNs to recognize dog barking, and for this I would like to augment the data sets I have (~30'000 10s clips with either barks, or no-barks in them). The straight forward idea was to mix ...
1
vote
1answer
18 views

spot/stain growth in image classification problems

I am working on a problem with images where we are monitoring development of spot in certain region of image. We are able to classify spot present(NOK) or not present(OK) successfully if initially ...
0
votes
0answers
5 views

Computational complexity for CNNs that accept more than 3 image channels

I have a dataset with images that have 10 channels instead of 3 RGB channels. Also the images have 16bit color depth and not 8bit as "regular" RGB images. Do these properties have an ...
1
vote
0answers
12 views

Merging Multidimensional Features in Python

I am trying to do 10-fold cross-validation on an audio dataset. The audio is clipped into small segments, so we have multiple clips from the same file. To avoid overfitting, each audio is assigned to ...
3
votes
4answers
147 views

Why are deep learning models unstable compare to machine learning models?

I would like to understand why deep learning models are so unstable. Suppose I use the same dataset to train a machine learning model multiple times (for example logistic regression) and a deep ...
1
vote
0answers
7 views

If an FCN accept rectangular image as input or has to be square?

Some say that for FCN it doesn't matter if the input image is rectangular the only thing matters that the size must be constant ...
1
vote
1answer
20 views

Question about performance of a CNN

I have a question (beginner :D) that is related to throughput and inference rate. Can the throughput and inference rate change as the model is trained or are the values for these parameters fixed? ...
1
vote
1answer
11 views

Loss is coming very high for object detection

I am using total of 3000 images for training an ssd_inception_v2_coco as the object detection model. I have set batch size as 4 because I don't have a high end GPU hence I am renting it for few hours ...
10
votes
2answers
3k views

Why should I understand AI architectures?

Why should I understand what is happening deep down in some AI architecture? For example LSTM-BERT- Partial Conv... Architectures like this. Why should I understand what is going on while I can find ...
0
votes
0answers
8 views

Filters in subsequent layers

So I recently started learning about CNNs, and one question struck out to menthe filters used in the second layer are a combination of the filters used in the first layer, right? Lets say I make use ...
0
votes
0answers
24 views

Why do we use multiple convolutional layers, instead of a single layer

My intuition is that, when we have the raw pixels from the image, suppose we want to extract an eye, why don't we just try to use an eye detector to extract the eye feature from the image, why do we ...
-1
votes
1answer
82 views

ValueError:Input 0 of layer sequential is incompatible with the layer

i represented each row in my dateset as a 15552 cell which is spectrogram colored image(72723), that is represent the audio features, 72*72 is the size of spectrogram image and 3 referred to the 3 ...
0
votes
0answers
11 views

U-net cannot detect midline of large object

I am training a three-dimensional U-net to detect tube-shaped objects, such as blood vessels, in medical image data. I am using simulated images during training, which contain tubes of varying size, ...
3
votes
0answers
78 views

ResNet50 + Transformer

In many papers people extract features from image using ResNet and than pass them through transformer. I want to implement the same. I want to get features and than classify them using transformer. ...
1
vote
0answers
25 views

Get GradCAM image for Mel-Spectrogram from CNN saved model in Python

Please note I have also asked this question in stack exchange 2 days ago, but have not received any answers to date: After extracting the MFCCs via this code: ...
1
vote
1answer
15 views

ResNet output dimensions of initial convolution don’t yield in an integer

I am trying to understand the ResNet dimensions, but got stuck at the first layer. We are passing a [224x224x3] image into 64 filters with kernel size 7x7 and stride=2. According to the ResNet source ...
0
votes
1answer
20 views

Understanding Max Pooling

I understand max pooling in CNNs can help decrease the computational load due to downsampling. Another thing mentioned is that max pooling can help provide a sort of "spatial invariance" for ...
1
vote
1answer
43 views

Should rescaling be used on test images in keras?

I am kind of confused regarding the topic. I have built a CNN architecture for the cat-dog image classification around 6000 images of cat and 6000 images of dog and I am predicting on test images. I ...
1
vote
0answers
21 views

Does time-series dependence penalize prediction with CNNs?

I'm trying to use CNNs on time series data (EEG), measured on different people. Each person has 10-20 recorded signals of different lengths and every subject has one global class assigned. Example: ...
1
vote
1answer
22 views

How to load a dataset with a specific structure in tfds library?

I have a dataset that it's classes arranged in the following way: /dataset/train/images/class1/ /dataset/train/images/class2/ . . . /dataset/train/images/classN/ ...
0
votes
1answer
30 views

Improving the performance of neural networks

I have 3 questions in mind about the neural network For the best model performance, is it better to train a model only on high resolution images or does it not matter whether the training data ...
0
votes
1answer
20 views

Keras ImageDataGenerator unable to find images

I'm trying to add image data to a Kaggle notebook so I can run a convolutional neural network but I'm having trouble doing this via ImageDataGenerator. This is the ...
0
votes
1answer
24 views

Improving validation losses and accuracy for 3D CNN

I have used a 3D CNN architecture, for detecting the presence of a particular promoter (MGMT), by using FLAIR brain scans. (64 slices per patient). The output is supposed to be binary (0/1). I have ...
1
vote
0answers
16 views

Q: Training a CNN-LSTM on video inputs

Hello everyone! I implemented the following model, for action classification from videos, where each frame is 224x224x3, a video consists of ...
0
votes
0answers
12 views

How many layers/ convolutions does DensNet-169 have?

I am a little confused by the numbers. From the Digram in the paper I count 312 convolutions without the transition layers. Can anybody help understand how the 169 in the name is calculated?
0
votes
2answers
61 views

High accuracy in mode.fit but low precision and recall. Overfit? Unbalanced? Error?

Hello ive been training a CNN with keras. A binnary clasificator where it says if a depth image has a manhole or not. Ive labeled manually the datasets with 0 (no manhole) and 1(it has a manhole). I ...
0
votes
1answer
13 views

How many layers of a pretrained model shoud be frozen?

I'm following an example of transfer learning where the blogger has frozen the first 20 layers of MobileNet. My question is , that is there any rule of thumb for how many layers should be frozen? ...
0
votes
0answers
22 views

How to determine a good architecture for multilabel classification

I am working on an university project that requests us to classify Wikipedia abstracts about people by their professions. The output shall be a JSON file that assigns each Wikipedia abstract to a set ...
0
votes
0answers
15 views

Differentiation of Learning Capabilities of Different Networks

I have a conceptual problem regarding the overall learning capability of a neural network differentiated by the different types of input that we can give to the network. Suppose that we have a ...
1
vote
3answers
47 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....
0
votes
0answers
9 views

How does 1 x 1 convolution operation help in finding cross channel patterns?

1 x 1 convolutions are very popular and I see that they are mostly used as bottlenecks. They help in dimensionality reduction which is why architectures like GoogLeNet use it. Xception net uses it for ...
0
votes
1answer
34 views

after overcoming the overfitting, how to increase training accuracy?

I am building a CNN using keras for a classification task. I started with a simple model as a starting point and as almost all ML problems go, especially if the dataset is not very big, I faced an ...
0
votes
0answers
10 views

Loss & accuracy curves from learning rate range test interpretation

I am working on a project doing experiments with the Learning Rate Range Test (See "A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and ...
1
vote
0answers
18 views

Identify areas within a shape/polygon with Vision / ML

Given a shape, in the format of a binary image, I would like to detect and subdivide it to new areas. Below is an attached example of such a shape and the expected outcome where each new area is ...
0
votes
0answers
25 views

Improving accuracy of 2D CNN with time series classification

After somewhat extensive optimization of hyperparameters, my test accuracy remains at around 70 %. I have tried techniques to augment time series but they only make things worse. Unlike image ...
0
votes
1answer
20 views

What does Keras image generators do with input images samplewise_std_normalization= True?

I have trained a a convolutional network samplewise_std_normalization=True. Now I want to check my model in real-time using Opencv. Therefore I would like to perform the same preprocessing on the ...
0
votes
0answers
6 views

Sequential batch processing vs parallel batch processing?

In deep learning based model training, in general batch of inputs are passed. For example for training a deep learning model with [512] dimensional input feature vector, say for batch size= 4, we ...
0
votes
1answer
42 views

Reducing Validation loss for Triplet Loss Embeddings

I'm trying to create a facial recognition detector using triplet loss followed by a kNN algorithm. I have roughly 10000 input images with 3 different classes, input size is 80x80. Model structure uses ...
0
votes
0answers
130 views

ValueError: `validation_split` is only supported for Tensors or NumPy arrays, found following input: RaggedTensor

I have following inputs to be trained on a CNN: x = np.array(Images) y = [ [[0]], [[76., 5., 9., 1., 0., 0.], [54., 4., 10., 51.]] ] Since the ...
0
votes
1answer
20 views

Tensorflow parameters for CNN

I created the below simple model (taken from a Coursera course). It has a total of five convolutions. ...
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

Multi site/source and Multivariate time series data (with multi time step) input in LSTM for forecasting

I am trying to make a multisite multivariate LSTM forecasting model with Keras. I have a simple Multivariate data structure like 3 X variables and 1 target variable with time-step 10, so my input ...

1
2 3 4 5
25