Salma Hassan

Last seen: plus de 2 ans il y a | Actif depuis 2016

Followers: 0 Following: 0

Message

Statistiques

Afficher les badges

Feeds

Question

how to prepare images dataset for autoencoder
I used this link to train 20000 2D images with size 256x256. first I have to prepare the dataset to feed it into autoencoder fuc...

plus de 4 ans il y a | 1 réponse | 0

0

réponse

Question

problem with ResNet pre-trained network for classification
I used ResNet (Matlab 2019a) for training the dataset and i saved each checkpoints during the training. I am trying to use thes...

plus de 4 ans il y a | 1 réponse | 0

0

réponse

Question

change size and format of images
I have a medical images dataset with various sizes and formats . I want to downsample all of them into 256*256 without loosing i...

plus de 4 ans il y a | 1 réponse | 0

1

réponse

Question

gathering two cells in confusion matrix
If I have a 4*4 confusion matrix array [1 1 3 2; 1 0 2 1 ; 7 4 3 1; 5 6 3 7]. how can I combining both 2*2 regions are next to ...

plus de 4 ans il y a | 1 réponse | 0

1

réponse

Réponse apportée
How to select the components that show the most variance in PCA
i still not understand i need an answer for my question------> how many eigenvector i have to use? from these figures

environ 5 ans il y a | 0

Question

How to Plot the ROC curve for the average of 10 fold cross validation using Matlab
i used 10 fold cross validation for training the convolution nural network, that each layer was trained 10 times. my question is...

plus de 5 ans il y a | 1 réponse | 0

1

réponse

Question

adding decoder layers into architecture of AlexNet
firstly the architecture of AlexNet is not an autoencoder. there is only an encoder but no decoder in AlexNet. So how can i crea...

presque 6 ans il y a | 1 réponse | 0

0

réponse

Question

how can i change the SegNet architecture to be based on AlexNet not vgg16

presque 6 ans il y a | 1 réponse | 0

1

réponse

Question

improve the performance of semantic segmentation
i used this options for training SegNet on my own data (medical image) but i got high error and looowww accuracy i reduced the...

presque 6 ans il y a | 1 réponse | 0

0

réponse

Question

semantic segmentation with different dataset
how can i use the example in this link https://www.mathworks.com/help/vision/examples/semantic-segmentation-using-deep-learning...

presque 6 ans il y a | 1 réponse | 0

1

réponse

Question

semantic segmentation with deep learning
i have a confused between pixel label and ground truth , are there similar when using for training SegNet code . if not how can...

presque 6 ans il y a | 1 réponse | 0

1

réponse

Réponse apportée
Dividing the image into blocks
i=imread('image_1_0.png'); i=imresize(i,[256 256]); a=64; b=64; %window size x=size(i,1)/a; y=size(i,2)/...

environ 6 ans il y a | 0

Question

divide image into blocks whatever the number of these blocks
i have an image with size 6000*6000 , i want to divide it into blocks the size of each block is 256*256 , what ever the number o...

plus de 6 ans il y a | 1 réponse | 0

1

réponse

Question

visualization the features in each layer for convolution neural network
i used the code in this link to visualize the feature https://www.mathworks.com/help/nnet/examples/visualize-features-of-a-co...

plus de 6 ans il y a | 1 réponse | 0

0

réponse

Question

I want to plot the Roc curve using perfcurve function i have 2 plot which code is right
the code is [Xpr,Ypr,Tpr,AUCpr] = perfcurve(targets,abs(scores(:,1)), 1, 'xCrit', 'reca', 'yCrit', 'fpr'); plot(Xpr,Ypr) ...

plus de 6 ans il y a | 1 réponse | 0

1

réponse

Réponse apportée
ROC curve AlexNet CNN
sir did you find the solution i have the same problem

presque 7 ans il y a | 0

Réponse apportée
How extract Precision, Recall and F-score values from PLOTROC () in Neural Network?
i used your lines in my code but it gives me this graph .... is that ture <</matlabcentral/answers/uploaded_files/102855/ROC...

presque 7 ans il y a | 0

Réponse apportée
how to calculate precision and recall in MATLAB?
[Xpr,Ypr,Tpr,AUCpr] =perfcurve(targets, scores, 1, 'xCrit', 'reca', 'yCrit', 'prec'); plot(Xpr,Ypr) xlabel('Recall'); ylab...

presque 7 ans il y a | 2

Réponse apportée
How can I extract the values of weights and biases after each training epoch?
this option 'CheckpointPath' in trainoptions function save the parameters value after each epoch

presque 7 ans il y a | 0

Réponse apportée
Load one Image and it will Compare with All Images in database Folder and Tell does it match with any image or Not
srcFiles = dir('D:.............\1\*.png'); image_1=length(srcFiles); srcFiles2 = dir('D:\...........\2\*.png'); ima...

presque 7 ans il y a | 0

Réponse apportée
how to turn matlab table into appropriate input for neural net package
imds=' D:\ '; imds=imageDatastore(imds,'IncludeSubfolders',true,'FileExtensions','.png','LabelSource','foldernames'); [tra...

presque 7 ans il y a | 0

Question

how does it possible in convnet, High accuracy in both of validation and test the same has 97% with error loss function 0.01
i really need an experience help . i feel misunderstand about convolution neural network i have a medical image data set and i...

presque 7 ans il y a | 1 réponse | 0

0

réponse

Question

error "Error using nnet.internal.cnn.layer.util.inferParameters>iInferSize (line 86) The output of layer 13 is incompatible with the input expected by layer 14."
where is the error in this code ..i only use googlenet as deep tuning without change any thing in it's Layers except the last 3 ...

presque 7 ans il y a | 1 réponse | 0

1

réponse

Question

Why is the learning rate for the bias usually twice as large as the the LR for the weights?
Why is the learning rate for the bias usually twice as large as the the LR for the weights?

presque 7 ans il y a | 1 réponse | 0

0

réponse

Question

deep learning convnet with matlab
i want to divide the dataset into 3 parts ( training , validation , test ) with matlab is this line true [trainingimages,...

presque 7 ans il y a | 1 réponse | 0

1

réponse

Réponse apportée
deep learning convnet with matlab
ok i found the answer Create three new datastores from the files in imds. The first datastore imds60 contains the first 60% o...

presque 7 ans il y a | 0

Question

what is causes NaN values in the validation accuracy and loss from traning convolutional neural network and how to avoid it?
I USE this line in matlab code [trainedNet,traininfo] = trainNetwork(trainMatrix,Layers,opts); so the information about vali...

presque 7 ans il y a | 3 réponses | 1

3

réponses

Réponse apportée
How to avoid NaN in the Mini-batch-loss from traning convolutional neural network?
i have this line in my code [trainedNet,traininfo] = trainNetwork(trainingimages,Layers,opts); when i opened the structure tra...

presque 7 ans il y a | 0

Réponse apportée
save image in a folder with original name
https://stackoverflow.com/questions/32430643/saving-with-original-names-in-matlab

presque 7 ans il y a | 0

Réponse apportée
How to increase the training and testing accuracy in CNN training?
hi sir did you find any solution for your problem , i have the same on

environ 7 ans il y a | 0