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.
1,365
questions
0
votes
1
answer
115
views
Can I have 0 loss in the validation set and still have bad accuracy?
I am starting in the world of deep neural networks and doing a series of tests with a convolutional model, I have found the following case:
The accuracy in the training set is much better (around 0.85)...
- 304
1
vote
1
answer
314
views
Random Forest Classifier is giving me an array of zeroes
I used VGG16 as feature extractor on a dataset with 9 classes and trained the Random Forest Classifier on the feature vector. I tried to make prediction on the test feature vector but the prediction ...
- 23
0
votes
1
answer
48
views
How to build model if the data dont have corelation each other's
I have 2 datasets, call them dataset A and dataset B. Then I want to predict dataset A using dataset B as input using regression model.
dataset A format:
dataset A shape(15000,1)
dataset B format:
...
- 31
0
votes
0
answers
98
views
How to select best kernel_size and max_pool_size in CNN1D
I have data with shape size 1,89. setup kernel_size = 3 and pool_size = 2 on the conv1d layer. However, the model is not able to predict the peak well. i think the problem is because the kernel_size ...
- 31
0
votes
0
answers
31
views
How the low level features are combined to form high level features in CNN? What happens to combine low level feature to form higher ones in bw layers
I want to understand basics behind cnn features formation like how high level features are formed using low level features in a CNN?
1
vote
0
answers
83
views
Why is my segmentation model not returning a heat map?
I have implemented two CNN architectures to perform segmentations on medical images: the classic UNet and a modified version called the Attention UNet. I have been training the models on roughly 50,...
- 11
1
vote
1
answer
117
views
why CNN model can't learn well the peak from data
here I have two different datasets. dataset1 is force plate data and dataset2 is plantar pressure data. dataset1 has shape (2050,2) and dataset2 has shape(2050,89). before doing the training I have ...
- 31
0
votes
2
answers
124
views
In a convolutional layer, is it standard practice to modify stride and padding to get a desired output?
I'm trying to implement the CNN described in A Framework of Hierarchical Deep Q-Network for Portfolio Management (see screenshot). In the paper, the author describes the first CNN layer as having a ...
0
votes
0
answers
23
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 ...
- 1
0
votes
1
answer
35
views
Sound Anomaly Detection
What is the recommended directory structure for sound anomaly detection using Keras CNN (Unsupervised) ?
After converting the sound files into spectrograms. Code examples will be highly appreciated.
- 1
3
votes
1
answer
98
views
Solving video classification problem by taking EVA Large as backbone
I am solving a video classification problem. There are 9 classes in total. At first I took ResNet as a feature extractor, this gave me 0.74 accuracy. Then I changed ResNet to EVA (I also tried Swin), ...
- 131
0
votes
0
answers
111
views
High Recall and Low Precision for Binary CNN model
I was training a CNN model for binary classification. The training and validation accuracy seemed good. However, the precision is low and the recall is high (High false positive).
...
1
vote
1
answer
1k
views
What is the architecture of ssd_mobilenet_v2_fpnlite_640x640?
What is the architecture of ssd_mobilenet_v2_fpnlite_640x640, which is a model available on TensorFlow model zoo. If my understanding is correct, mobilenet is used for feature extraction , while SSD ...
- 13
0
votes
0
answers
100
views
How to best train a CNN with longitude/latitude output
Problem
I am new to CNNs and I'm starting off with a geolocation problem where the input is an image and the output should be a longitude value and a latitude value.
I am unsure of the best way to ...
0
votes
0
answers
41
views
Is zero centering done based on the mean of a single image or of all images?
I have a set of training images and a set of testing images.
How exactly should I do zero centering in pre-processing? I have the following questions regarding this:
Should I subtract the mean of ...
0
votes
0
answers
47
views
how to get the extracted feature vector from transfer learning models python?
I am trying to implement a classification model with ResNet50. I know, CNN or transfer learning models extract the features themselves. How can I get the extracted feature vector from the image ...
- 172
0
votes
0
answers
1k
views
Yolo confusion matrix - Background Class
I am training the yoloV5 model, where, I have two class[object = A and B].
In the dataset, the class B has more samples than class ...
0
votes
0
answers
10
views
Improving CNN Regression model: make more fit each data point
I want to predict a force plate data using smart insole data. I'm trying to implement a CNN model for Regression prediction. The following is data from the force plate and smart insole
Force Plate ...
- 31
0
votes
1
answer
52
views
Input Tensor Shape for CNN Binary Classification of Time Series Data
I want to predict whether a machine will fail based on the most recent set of measurements taken by on-board sensors. I have several dozen machines, each with a sensor that takes a measurement at ...
0
votes
1
answer
573
views
CNN for time series: Input 0 of layer "conv2d_5" is incompatible with the layer: expected min_ndim=4, found ndim=2. Full shape received: (None, 2)
I am trying to use CNN on multivariate time series instead the most common usage on images. The number of features are between 90 and 120, depending on which I need to consider and experiment. This is ...
- 61
0
votes
0
answers
20
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
198
views
CNN-BERT Text Classification good results on train and val, but bad prediction on testing
I built a Keras model to predict hoax news and true news using the CNN-BERT Text Classification algorithm with Categorical Classification, with label 1 indicating a hoax and 0 indicating true news.
...
- 1
1
vote
1
answer
392
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 ...
1
vote
1
answer
56
views
What is the best way to split small data?
I have dataset of 17-20 videos (5 minutes) each video representrepresents a different class (around 4 classes). I can'tcannot get more video because this was provided by the company. I'm planingI am ...
user142691
0
votes
0
answers
24
views
Keras Custom Layer Aware of Position in Network
I'm writing a custom Layer in TF/Keras (tf.keras.layers.Layer) for a CNN, and I need each layer to know its own depth in the model.
Is there any way I can do this, ...
- 53
0
votes
1
answer
410
views
image_dataset_from_directory using a subset of sub-directories
I have downloaded the MINC dataset for material classification which consists of 23 cateogories. However, I am only interested in a subset of the categories (e.g. [wood, foliage, glass, hair])
Is it ...
- 1
1
vote
0
answers
20
views
How to design and use CNNs for sentence classification?
I'm playing around with using CNNs for sentence classification. Basically all models I found implement the same model proposed in Convolutional Neural Networks for Sentence Classification (Kim, 2014), ...
- 171
0
votes
1
answer
259
views
Why VGG16 Outperforms VGG19?
I built VGG16 and VGG19 models using transfer learning. As far as I know, VGG19 has more convolutional layers and it is more complex, VGG16 performs better in terms of accuracy and loss. I can't ...
0
votes
1
answer
30
views
I am concatenating two different CNN model trained on two completely different dataset
My model is going in the infinite loop while predicting( full_model.predict(inputgenerator)). I think there is some issue with the datagenerator code that I have written(especially with while loop)....
1
vote
1
answer
267
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
30
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
1
vote
1
answer
35
views
How are OCR training datasets constructed?
For the sake of concreteness: let's suppose that the word "OCR" refers to any OCR system build on an R-CNN architecture. Similarly, in aims of simplicity, let's declare that we are ...
- 123
0
votes
1
answer
36
views
Xception model input_shape size
When I set Xception input_shape=None, use the (299,299) dataset for training, and use the (149,149) image when doing the test. Will the (149,149) image be upsampled when it is input to the network?
...
- 1
0
votes
1
answer
24
views
Why when i convert my MRI images to L they dont turn gray?
I have mri images when I checked the mode it show that they are RGB but they look like grayscale images so when I converted them to L[![enter image description here][1]][1] they turn mix of green and ...
0
votes
1
answer
75
views
Should the dataset be divided into train, test, and validation?
I am implementing the CNN classification model. I've seen several instances where a dataset is split into test, train, and validation. I've also seen instances where a dataset is split into train and ...
- 172
0
votes
1
answer
86
views
How to make a pipeline for Videos Dataset for TensorFlow [Sequence Matters] & train Model Effectively with Low Memory System
I am working on a Deep Learning project and I am facing an issue with the size of the dataset. I want to make a pipeline for video dataset [Sequence Matters]. Because if I try the load the whole ...
- 21
0
votes
1
answer
57
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
52
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
1
vote
0
answers
35
views
What data can I obtain from this H5 file?
I created a CNN model and it is saved in h5 format.
I used the Netron app, where I obtained the model architecture, however batchnormalization was not present.
Is ...
- 172
0
votes
1
answer
41
views
Reusing a model, pretrained on 19 classes, for just one of those classes
I have a pretrained net for semantic segmentation, which has been trained on the cityscapes dataset and its 19 classes (Person, car, traffic sign, …). One of those is "Person". I am only ...
- 1
1
vote
0
answers
94
views
how to reduce the loss and improve the gradient flow - CNN
I am trying to improve this situation, in image classification[3 classes, softmax in the last layer], I constructed the neural network having 7[conv2d+Batchnormalization] layers + 1 linear layer,
...
- 21
0
votes
0
answers
33
views
Different results between training and evaluation phase on the same data
I have trained a CNN and in the training phase I obtained an accuracy of 36.5%.
If I call model.predict() on the same test data of the training phase I only obtain ...
1
vote
0
answers
34
views
Regression for arrays rather than numerical values
I have a dataset with a small amount of points (~500) and 10 features. The points are related to eachother, so that information about point 1 should help predict information about point 2 etc etc.
...
- 11
0
votes
0
answers
109
views
Increase and decrease in depth of CNN blocks
Please see the image below as an example. To my understanding, the 1nn image is converted to 500*n~ * n~ with the help of 500 kernels applied on the same image. What I am confused about is how in the ...
- 21
0
votes
2
answers
39
views
Difficulty loading data/running model on custom dataset derrived from DNA sequence data - TypeError when attempting to run model
I am a student who has some limited experience with keras, and for a new project recently decided to learn how to use pytorch to implement my models. I'm a beginner with both, so apologies in advance ...
0
votes
0
answers
245
views
How ca I reshape y_train , y_validation from train_generator?
I retrained ResNet-50 for iris flower classification in tensorflow using the following code:
...
- 125
0
votes
0
answers
318
views
Classification report for binary class problem
I am building a binary CNN using single neuron in the last dense layer and "binary_crossentropy" as the loss function while compiling to predict either class1 or class2. I am having problem ...
- 31
0
votes
1
answer
110
views
How to use strong labels in image classification?
I have a dataset where I have localized pixel-level annotations of a dataset of cancer vs non-cancer.
Which deep learning methods can I use to optimize the model to focus on the localized regions of ...
- 33
1
vote
1
answer
335
views
How is ResNet different from FPN?
I'm learning more about different variations of deep CNNs. Based from my understanding, ResNet makes use of skip connections that's also somehow shaped like a pyramid or triangle? How is this ...
- 11
0
votes
1
answer
449
views
Colab Pro+ CNN GPU memory saturation
I have a problem when executing jupyter notebook for CNN in colab pro+, to train a model with a size of 560664x48x48x1.
normally the data is composed of images with a size of 48x48.
I used 10 fold ...
- 101