Skip to main content

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
49 views

Keras model with 3 input images giving wrong output

I have created a keras model that takes 3 images as input, passes them to individual CNN backbone(mobilenet_v2) and fuse the results from 3 individual streams. These fused outputs further goes through ...
0 votes
0 answers
7 views

Mobilenet vs resnet

Q1-Why dont we remove relu after addition of skip connection in resnet50 like we do in mobile-net v2 for better performance? Q2-And why dont we have Convolution layer in skip connection for dimention ...
0 votes
1 answer
1k views

How to correctly measure the inference time and FLOPs of a model?

For some reason, I can’t find built-in solutions (not really?) in keras and tensorflow, while on the site https://keras.io/api/applications/ they provide Time (ms) per inference step (CPU), but for ...
1 vote
1 answer
81 views

Extract segment from document scan

I need to extract some "valuable" information from document scan. For example, document's number, incoming date, organizations, persons, etc. Example document: I'm trying to extract highlighted ...
2 votes
1 answer
2k views

Backpropagation of convolutional neural network - confusion

I've already seen many articles about this topic and Backpropagation In Convolutional Neural Networks by Jefkine seems to be the best. Although, as author said, For the purposes of simplicity we ...
0 votes
1 answer
49 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? ...
2 votes
2 answers
92 views

Does high accuracy metrics with small (but equally sampled) dataset means a good model?

I have been training my CNN with 200 images per class for a classification problem. There problem is a binary classification one. And with the amount of test data ( 25 per class) I am getting good ...
1 vote
2 answers
1k views

Vanishing gradient problem even after existence of ReLu function?

Let's say I have a deep neural network with 50 hidden layers and at each neuron of hidden layer the ReLu activation function is used. My question is Is it possible for vanishing gradient problem to ...
0 votes
0 answers
31 views
+50

How specific should I be with my region of interest in image data for training a CNN model for better accuracies?

I am trying to train a 3D CNN model for classification of cancer stages on a dataset that comprises of head to neck CT image series which is split into 5 classes corresponding to the stages of cancer....
2 votes
1 answer
4k views

Getting confusion matrix with Keras flow_from_directory

For a homework I have to analyse a set of images. For this I plan to use convolutional neural network. The images are split onto specific folders : A test set with 624 photos dataset/test/normal (...
0 votes
1 answer
16 views

What is the "fast version" of ZFNet referenced in SPPNet and Faster R-CNN papers?

I'm reading old papers: SPPNet: Link Faster R-CNN: Link In both cases, the authors refer to a "fast version of Zeiler and Fergus (ZF) Net"; specifically: In SPPNet: ZF-5: this ...
4 votes
1 answer
97 views

Training Machine Learning Model - Neural Network - Islands Problem

I was working on the following leetcode problem: Given a 2d grid map of '1's (land) and '0's (water), count the number of islands. An island is surrounded by water and is formed by connecting ...
1 vote
1 answer
67 views

How to have Multiple labels in a single video?

I am building a Tennis stroke classification system using CNN. I assume each stroke contains 3 steps/classes ('Ready', 'Impact', 'Finish'). I want to train a model which will predict whether the input ...
0 votes
0 answers
7 views

Binary Cross Entropy Loss Not Learning

I am trying to implement a CNN that receives as input a 640 by 368 sized tensor where only the center 30 columns (i.e. columns 169 to 199) keep their real values and everything else is set to 0 and ...
0 votes
0 answers
14 views

Implementation of CNN-LSTM for multivaraite time series forecasting

I have recently completed the course on TimeSeries from Coursera - Deeplearning AI, and was trying to replicate the results of an open-access research paper (...
3 votes
2 answers
760 views

LeNet-5 - combining feature maps in C3 layer

Famous LeNet-5 architecture looks like this: The output of layer S2 has dimension: 10x10x6 - so basically an image with 6 convultions applied to it to derive features. If each dimension was again ...
0 votes
1 answer
53 views

Discrepancy between cross-validation and un-seen data predictions

I am facing an issue with an imbalanced dataset. The dataset contains 20% targets and 80% non-targets. I am expecting a confusion matrix below when I give un-seen data to the trained model. ...
0 votes
1 answer
58 views

CNN training accuracy flatlines

I'm training a CNN from scratch to do tagging of images. And my training is going nowhere. I was hoping someone could help me identify an obvious error. I would like to end up with a network that ...
0 votes
1 answer
211 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 ...
0 votes
1 answer
2k views

Epoch 1/5 won't stop

When i run my code with 5 epochs, code gets stuck at first epoch and run continuesly. I tried applying various parameters but couldn't make it. here is my code... ...
0 votes
1 answer
209 views

How to obtain and load a good initial data set for object localization?

I'm looking for a good data set for training a CNN based network to do object localization (i.e. a data set with class labels and bounding box data). What is a good initial data set to use? How can ...
2 votes
1 answer
52 views

Dealing with high dimensionality datasets

I have data of dimensionality (25000, 100, 500) i.e. 25000 rows each consisting of a 2 dimensional 100 X 500 matrix. Currently I am only applying CNN for ...
1 vote
1 answer
499 views

CNN can't predict images outside the dataset

I am using celeba dataset to train my CNN face landmark detection model. Here is my model ...
1 vote
1 answer
133 views

CNN 3D line angles prediction regression - results of training of phi depend on theta

I am a beginner in "deep learning". What I am trying to do, is to predict two angles of a 3D line projected on a 2D image. The toy model is that I create a line going out from the centre of 48x48 ...
1 vote
1 answer
95 views

interpret cnn structure

I am trying to interpret the CNN model from the below settings. AS I am new to deep learning and I am not able to fully comprehend the layer structure . Could someone please tell me is these two ...
1 vote
1 answer
170 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 ...
3 votes
1 answer
228 views

What ML model for regression given tabular AND image data?

I'd like to predict the power production of a windfarm given the wind speed, its direction and other variables related to the specific wind turbines. However, due to wake effects (wind speed decreases ...
0 votes
0 answers
15 views

What are good configs for running UNet3DConditionModel on 8 GB VRAM? (64x64x64 inputs)

What are good configs for running UNet3DConditionModel on 8 GB VRAM? (64x64x64 inputs) More specifically for this project I'm looking to use HuggingFace's UNet3DConditionModel on my home PC on a RTX ...
0 votes
2 answers
52 views

CNN application assessment

I would be glad if someone could give me some hints and assessment for the following project. (I'm relatively new to ML and DL and having only a little theoretical knowledge) My goal is to build a ...
0 votes
1 answer
476 views

How to copy and crop feature map in Unet?

I am confused about the principle of copy and crop in U-net, like the grey line shown above. For example, the first grey line, how to convert a (64, 568, 568)(C,W,H) to a (128, 392, 392), did the ...
1 vote
1 answer
853 views

What are the possible values of a filter in a CNN?

I am a trying to write a CNN from scratch in python but I am bit new to CNNs specifically the convolution layers as I am comfortable with the dense layers. I was reading Do filters have different ...
1 vote
0 answers
37 views

Downsampling an image in the right way

I was not shure where to ask this question, but SE Data Science seems to be the best place for it. So I tried to build a CNN based super resolution model. Unfortunately I have only high-res images but ...
0 votes
1 answer
54 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 ...
2 votes
1 answer
2k views

To freeze or not, batch normalisation in ResNet when transfer learning

I'm using a ResNet50 model pretrained on ImageNet, to do transfer learning, fitting an image classification task. The easy way of doing this is simply freezing the conv layers (or really all layers ...
0 votes
1 answer
69 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
30 views

Validation accuracy can't increase above 70%

I am building a classifying model to predict images over 3 classes. The data is balanced, with 10.5k images for train ( 3.5k for each ), 3k validation images ( 1k each ). I increased my ...
0 votes
1 answer
87 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 ...
0 votes
0 answers
35 views

Invalid Input shape for input tensor on Multimodal CNN

Im trying to build an image classification model with multimodality, it takes SAR and optical images, both types of images have FITS format. The optical images have shape (None, 512, 512, 3), while ...
0 votes
0 answers
7 views

How to work with SAR and optical images? Trying to do a Multimodal CNN

I´ve been trying to come up with a image classification algorithm that uses SAR and optical images, but I havent been able to write a code that works, where could I look for guides about multimodal ...
1 vote
1 answer
791 views

Error on custom RNN/LSTM with multiple inputs

I want to implement a custom RNN/LSTM model similar to this. The model should take two separate vectors as input and process them. I was following keras tutorial to implement a custom keras layer and ...
0 votes
1 answer
156 views

Number of capsules in the Primary Capsule Layer of Capsule networks

What is the Number of capsules in the Primary Capsule Layer of Capsule networks? In many articles, it is written that the number of Capsules is 32 but in the paper, by Hinton - Dynamic Routing ...
0 votes
0 answers
12 views

Reinforcement learning give reward after finishing the data classification instead of acting one by one and CNN based reinforcement learning

I am trying to write an reinforcement based based trading system and while trying to do that, the only way that I can do and I found is rewarding the model for each action but it actually performs bad ...
1 vote
1 answer
199 views

Trained CNN individually on multiple images to classify them, how can I now classify a related "set" of these images that correspond to one object?

I have a N object classification examples, each example consisting of a set M individual images of the object at different angles. I've trained M CNNs with the dataset of one particular image angle ...
0 votes
1 answer
346 views

Trying to use different image size to test my trained model

I have built my model using images which are all 512x384, I then exported the model through .pkl and am hosting it on Render, the UI is built on React App where the user will input their chosen image ...
1 vote
1 answer
1k views

Transfer learning: Poor performance with last layer replaced

I am using a transfer learning approach. For this I followed the tensorflow for poets tutorial. I use a pre-trained InceptionV3 architecture trained on the Imagenet dataset. The last layer and the ...
1 vote
0 answers
27 views

Validation accuracy stuck in tf keras

So I have a model to classify images into 3 classes. I have 10.5k train images ( 3.5 per each category ) and 3k ( 1k per each category ) validation images but I can't increase my val_acc no matter ...
2 votes
1 answer
112 views

Model for classifying time-series data with distinct features?

I've heard about time-series classification being done with TCN's and CNN's combined with LSTM's very often, citing that CNN's would provide insight both forward and in the past since you already have ...
0 votes
1 answer
367 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-...
1 vote
1 answer
169 views

I have created a CNN model and now i want to draw its architecture diagram can anyone help me with that

following is my architecture: ...
0 votes
1 answer
253 views

How can I fixed the filter and Kernel Size of a CNN?

I have created 4 x 4 2d images from a signal. Now, I want to feed this data to a Convolutional neural Network. How I can choose the nubmber of ...

1
2 3 4 5
28