2022 Developer Survey is open! Take survey.

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
1 answer
8 views

AttributeError: 'Functional' object has no attribute 'predict_classes''

I am trying to use run a GoogLeNet code using FERET datasets. When I run the code, I get the following error message: ...
user avatar
  • 1
0 votes
0 answers
11 views

Using large CNNs (e.g., ResNet) in convolutional autoencoders for image representation learning

I am confused about which CNNs are generally used inside autoencoder architectures for learning image representations. Is it more common to use a large existing network like ResNet or VGG, or do most ...
user avatar
0 votes
3 answers
47 views
+50

How to verify if the behavior of CNN model is correct?

I am exploring using CNNs for multi-class classification. My model details are: and the training/testing accuracy/loss: As you can see from the image, the accuracy jumped from 0.08 to 0.39 to 0.77 ...
user avatar
  • 51
0 votes
0 answers
17 views

Keras/Tensorflow Error: Specified a list with shape [3,1] from a tensor with shape [32,1]

I have been experimenting with keras/tensorflow to build up my confidence and am currently trying to build a LSTM model that forecast the price of a stock based on the price of the stock in the ...
user avatar
0 votes
0 answers
19 views
+50

Accuracy drops when adding a fully connected layer for dimensionality reduction to a ResNet50

I'm training a ResNet50 for image classification and I'm interested in decreasing the dimensionality of the embedded layer, in order to apply some clustering techniques. The suggested dimension is ...
user avatar
  • 51
0 votes
1 answer
15 views

In what ways are transformers better for Vision than CNNs? [closed]

I am looking at getting an intuition about how transformers can be better in vision tasks such as recognition and also for Adversarial examples is it better.
user avatar
0 votes
0 answers
8 views

What should be the loss and accuracy value while training the input and output data in deep learning using jupyter notebook? [closed]

I am working on fault detection and fault classification in power system using deep learning, when I am training the input data (fault coefficients m, n, p, q) and output data (fault type A-G, B-G, C-...
user avatar
0 votes
0 answers
6 views

What would be the best method for uncertainty analysis for a CNN-based regression model?

I am trying to establish a relationship between a dependent variable and 18 independent variables using a CNN-based regression model. What would be the best method for uncertainty analysis? Thanks.
user avatar
  • 1
0 votes
0 answers
8 views

What is the best method to determine variable importance in a CNN-based regression model?

I am trying to establish a relationship between a dependent variable and 18 independent variables using a CNN-based regression model. What would be the best method to determine variable importance in ...
user avatar
  • 1
0 votes
0 answers
6 views

I am trying to establish a relationship b/n hcanopy & 18 predictors (vv_name & vh_name) using CNN but my model isn't learning. How can I resolve it?

Before building and running the model, I have rescaled and normalized the data. Here is my model - ...
user avatar
  • 1
0 votes
0 answers
14 views

Time series classification using multiples multivariate multi-length timeseries

0 I would like to develop a time series classification algorithm to classify use a of parachute. My data consist of multiple recording files (around 5min at 100hz, length of the recording vary) with a ...
user avatar
0 votes
0 answers
11 views

When using a model like VGG16 as a classifier within Faster RCNN, does Faster RCNN then use 2 CNNs in total?

Im currently doing a project about CNN's but im quite confused because they can be used to classify and to extract features. According to the Faster RCNN paper, it uses a ResNet backbone. I have also ...
user avatar
0 votes
0 answers
9 views

Erratic changes in validation accuracy

I am training the binary classification CNN model. It is part of the self-supervised pipeline and I use it to predict whether the transformation has been applied to an image. However, I am getting ...
user avatar
0 votes
1 answer
15 views

Using CNNs to detect incorrect label images in dataset

What I want to do is to train a model to identify the images that are incorrectly labeled in my dataset, for example, in a class of dogs, I can find cats images and I want a model that detects all ...
user avatar
0 votes
0 answers
15 views

Is it possible to justify why one CNN architecture outperforms other models?

I am using several pre-trained models to solve my problem. These models are VGG-16, Resnet-101, Inception-ResNet-v2, Densenet-201, and Xception. Xception has outperformed all of these models; is it ...
user avatar
0 votes
0 answers
10 views

Does eval loss decreasing slower than train loss indicate overfitting?

I am training a binary classifier using an efficientnetv2 model with a 1M image dataset where I do a 60/20/20 split. Does this graph mean that the model is over-fitting? I can see that the train loss ...
user avatar
  • 1
-1 votes
0 answers
10 views

Problem with root error

I currently built a model for classify age with Keras function API for studying then i'm stuck in this error for a long time. Don't know how to fix it, please help me solve this problem. Here is my ...
user avatar
0 votes
0 answers
11 views

Predicting value using LSTM

I'm currently learning about LSTM and want to make a prediction using an array as an input and have an output as a single value. I currently trying to do that by using this model: ...
user avatar
0 votes
0 answers
8 views

Data Augmentation Keras length of data

I'm confused when I add data augmentation should I get more data or the same data I tested my x_train length to confirm but I got the same length before augmentation and after augmentation is that ...
user avatar
  • 1
0 votes
0 answers
11 views

Dimensionality of CNN and a linear function

Hi I need help understanding how the nn.linear can be implemented in a neural network without problems dimensionality. EDIT I think my problem relates to understanding the relationship between in and ...
user avatar
0 votes
1 answer
31 views

Overfitting CNN model - any relation to input image size?

If my CNN model is over-fitting despite trying all possible hyper parameter tuning, does it mean I must decrease/increase my input image size in the Imagadatagenarator?
user avatar
  • 11
0 votes
0 answers
14 views

ValueError: Shapes (1,) and (1, 70, 70, 1) are incompatible

I was trying to train my CNN model on some pics to identify them from a label vector and these are the shape of my Data (my data is contains 10 pics each 5 belongs to jeff bezos and bill gates and for ...
user avatar
  • 31
0 votes
1 answer
21 views

Is it feasible to integrate convolutionnal layers as Reinforcement Learning input to learn video game?

Let's say, you want to apply reinforcement learning on a simple 2D game. (ex : super mario) The easy way is of course to retrieve an abstraction of the environnment, per example using gym and/or an ...
user avatar
0 votes
0 answers
10 views

Group multiple ImageNet labels into a more general label

I'm a beginner in the world of machine learning, and my goal is to produce a mobile app that can recognize, label and group your gallery picture to make it more organized. I started by digging into ...
user avatar
0 votes
0 answers
16 views

Defects classification

my task is to classify the defects type present in some images coming from optical inspection tools. Often the defects appear on a uniform colored background while some other times they appear on top ...
user avatar
0 votes
0 answers
27 views

YOLOv5 can't detect object on custom dataset

Context: I'm trying to utilize an object detection model (YOLOv5) to detect damage/defects on cars (dents, scratches, cracks). Right now the goal is to make a minimum viable prototype, a model able to ...
user avatar
  • 35
0 votes
1 answer
31 views

What does it mean if the validation accuracy is equal to the testing accuracy?

I am training a CNN model for my specific problem. I have divided the dataset into 70% training set, 20% validation set, and 10% test set. The validation accuracy achieved was 95% and the test ...
user avatar
  • 13
0 votes
1 answer
22 views

How to compute the mean of weights of multiple models?

Hi i'm a student and i'm working on a Federated Learning problem, but before doing that with the proper tools like OpenFL or Flower, I started a little experiment to try in local to train using this ...
user avatar
0 votes
0 answers
13 views

How many model parameters do R-CNN, Fast R-CNN and Faster R-CNN have respectively?

I am making research on object detection and I would like to know the number of parameters these three models obtain.
user avatar
0 votes
1 answer
48 views

My validation loss is too much higher than the training loss is that overfitting?

I am new to data deep learning. I am educating myself but I don't understand this situation. Where Validation loss is much much higher than the training loss. Can someone please interpret this? ...
user avatar
0 votes
0 answers
7 views

Post processing in medical segmentation with attemtion unet

I am doing a lesion segmentation for multiple sclerosis (MS), and at the moment I am using a attention unet for my thesis. The best validation dice score I have recieved is 0.771 and train 0.84. I am ...
user avatar
  • 1
0 votes
0 answers
14 views

Is RoI Pooling appropriate to retrieve fine details from objects of varying sizes?

I’m using a RoI Pooling after a CNN that extract features from images of varying sizes, containing defects I want to classify. The images and defects sizes range from a couple of pixels to ~100 pixels....
user avatar
0 votes
0 answers
9 views

Getting Input Dimension from Tensorflow

I have this code: ...
user avatar
  • 171
0 votes
0 answers
14 views

Value Error: Shapes (None,128,128) and (None, 4) are incompatible

I am trying to perform CNN on my dataset. I came across the below error ValueError: Shapes (None, 128, 128) and (None, 4) are incompatible The shape of my xTrain ...
user avatar
0 votes
0 answers
8 views

Can I use low dimensional node features in graph convolutional networks?

I am trying to understand how GCNs work. For example, the well known GraphSAGE algorithm considers a graph $G$ with node features $x_i$ of dimension $n$. Then it propagates the node features over the ...
user avatar
0 votes
0 answers
18 views

MTCNN for face detection different result

I have a question concerning MTCNN for face detection. There are two ways to use MTCNN that I have discovered: Load a local model from their repository (...
user avatar
1 vote
1 answer
10 views

Creating a map between N images and N labels using CNN

I have seen classification CNNs that train with numerous images for a subset of labels (i.e. Number of images >> Number of labels), however, is it still possible to use CNNs when the number of ...
user avatar
  • 11
0 votes
0 answers
38 views

Should we use 2D or 3D data when training LSTM and CNN

My question is simple and it has 2 parts, so basically Should we train a CNN with Conv1D layers, with 2D or 3D data, or both are possible? Should we train a LSTM model with 2D or 3D data, or both are ...
user avatar
0 votes
0 answers
7 views

Is my exploration scheme in reinforcement learning done correctly?

so, I am training a deterministic policy, represented by basically a convolutional networks. I have an action space which is basically a vector of weights / probabilities, output by the network. The ...
user avatar
0 votes
1 answer
21 views

How to measure the similarity between two medical images of different imaging modalities according to similar objects in both of them?

I have two series of medical images each one from different imaging modalities. According to that, I have been segmented the Region of interest (the object which appears in both modalities )using U-...
user avatar
  • 1
0 votes
0 answers
18 views

How should I improve my CNN binary classification model from overfitting and underfitting [duplicate]

I am trying to do the cats & dogs classification problem, the problem is that my model is overfitting and I have tried all the techniques I know in order to solve but nothing is working such as ...
user avatar
0 votes
0 answers
20 views

pytorch convolution neural network tune class weights

I have a neural network as below for binary prediction. My classes are heavily imbalanced and class 1 occurs only 2% of times. Showing last few layers only ...
user avatar
0 votes
0 answers
16 views

Testing the accuracy of new data

I have a pre trained deep learning model. The author has tested it with some data and gave more than 90 % accuracy. I want to fine the accuracy given by that model for my data. How should I do it ?
user avatar
0 votes
0 answers
53 views

Input 0 of layer max_pooling1d_3 is incompatible with the layer Error

Ok, so basically, i have some Tf-Idf features and some additional features like wordcount, sentiment on my data. Now, according to my knowledge, when we use Convolutional layer, the data needs to be ...
user avatar
1 vote
0 answers
7 views

Hardware datapaths for weights and operands

A paper, Survey and Benchmarking of Machine Learning Accelerators, mentions Conversely, pooling, dropout, softmax, and recurrent/skip connection layers are not computationally intensive since these ...
user avatar
  • 143
0 votes
0 answers
6 views

CIFAR10 validation accuracy benchmark training from scratch

I am aware that training a deep neural network depends on many factors like the backbone, hyperparameters, batch size, and so on and so forth; But, I was curious to know a rough estimate of what we ...
user avatar
0 votes
1 answer
35 views

Am I over-complicating stuff?

I'm trying to classify some 1-D time series data, so I used a simple 1D CNN and fine-tuned the model via Bayesian Optimization (nothing fancy, just used the Keras tuner). And I got very good results (...
user avatar
0 votes
0 answers
11 views

How to approach a spatio-temporal forecasting?

I am dealing with a Spatio-temporal forecasting problem similar to the one dealing with the NYC Taxi Demand Prediction. This case is a good example since it has been already covered in different ...
user avatar
1 vote
0 answers
19 views

Trainning CNN Metric Learning gradient is constantly 1

I'm training a CNN with shirts and bodycon photos. I have these two classes and about 15k photos. I'am trying to do Metric Learning with a Contrastive Loss, but my CNN is not learning because ...
user avatar
0 votes
0 answers
12 views

Concatenate different image bands in same input channel

Take a multispectral image with many bands (pixel matrices values). I am thinking about concatenating the pixels values in the following way to be inputted into a CNN: 1st Channel: Red, Green and ...
user avatar

1
2 3 4 5
26