Questions tagged [conv-neural-network]

A convolutional neural network (CNN, or ConvNet) is a class of deep, feed-forward artificial neural networks that has successfully been applied to analyzing visual imagery. It falls under the [deep-learning] tag.

0 votes
0 answers
11 views

why is tape.gradient returning None

so I am trying to create an adversarial example using this function: def create_adversarial_pattern(input_image, input_label): input_image = tf.cast(input_image, tf.float32) with tf....
user avatar
0 votes
0 answers
19 views

i have problem in accuracy when i merge 2 cnn to binary classification for 1D data

i have problem in accuracy when i merge 2 cnn to binary classification for 1D data the code history = model_combined.fit(X_train, Y_train, epochs=5, batch_size=64,verbose = 1,validation_data=(X_test,...
user avatar
0 votes
0 answers
25 views

problem while giving input to the model and saving the output to a file

I have a numpy array having the 512 data points, I want to consider this as the input to my 1d convolutional model. After training the model in unsupervised way I want to predict the same input data ...
user avatar
0 votes
0 answers
15 views

denoising 1d timeseries using deep learning

I want to train a 1d convolutional model in the unsupervised way for denoising the 1d timeseries data.In this regard I generated the 1d noisy timeseries as mentioned in inpdata and i want to denoise ...
user avatar
-1 votes
0 answers
31 views

Incorrect CNN output

I'm working with a UNet convolutional neural network architecture because I need to output an image. However, it outputs an incorrect image on two counts: The first picture on the far left is X, the ...
user avatar
  • 13
0 votes
2 answers
20 views

Printing only the first weights of a neural network

I have my model (a VGG16, but it is not important). I want to check only some parameters of my network, for example the first ones. To do this I do list(model.parameters()) and it prints all the ...
user avatar
  • 158
0 votes
0 answers
25 views

Keras model always predicting the same class

I am working on a project where I have to classify genomic sequences as either positive or negative. So basically, I have sequences that are in the form 'accccttttttgggg...' These sequences are 150 ...
user avatar
  • 1
0 votes
0 answers
19 views

How to make YOLOV7 use higher resolution for training?

The current requirements are as follows: 1.The input image is a picture taken by 1440x1080 camera 2.There are only two detection targets, which are approximately 40x40 pixels and 16x16 pixel balls on ...
user avatar
0 votes
0 answers
18 views

Input 0 of layer "model_2" is incompatible with the layer

Working on a project using the below Jupyter notebook as a reference. I am getting the following error when I try to train the model : Node: 'model_6/dense_9/Relu' Matrix size-incompatible: In[0]: [47,...
user avatar
-1 votes
1 answer
33 views

Implementing CNN from scratch with numpy only and save model

Currently, I am learning CNN by myself. I find lots of sources on the Internet. But most of them use Pytorch and Tensorflow. I want to find some examples for image classification that uses NumPy only ...
user avatar
  • 9
-2 votes
0 answers
24 views

What value of val_loss is considered good for a CNN? [closed]

I got train_loss: 0.3519 - train_accuracy: 0.8394 And val_loss: 35.0334 and val_accuracy: 0.8542. Is this a good validation loss?
user avatar
0 votes
0 answers
17 views

I have to decrease the batch size after adding a transformation

I am new to PYTORCH and AI in general. I am working on a dataset with 1080p images (6.7MB per image) where I can only train with a batch size of 1 using my GPU. I thought I will add a transformation ...
user avatar
  • 25
0 votes
0 answers
43 views

Keras and Tensorflow OS resource requirement

I keep getting F tensorflow/core/platform/default/env.cc:73] Check failed: ret == 0 (11 vs. 0)Thread tf_data_private_threadpool creation via pthread_create() failed. errors during training, although ...
user avatar
0 votes
0 answers
14 views

"input channel should be divided by the weight channel" Error when converting TF2 StyleGAN2 to CoreML Model

I'm trying to convert an unofficial Tensorflow 2 implementation of StyleGAN 2 (Specifically, just the generator portion, not the discriminator) to a CoreML model to use in an iPhone app using the ...
user avatar
-2 votes
1 answer
30 views

What do the terms filter and kernel size represent?

In relation to CNNs, what is the difference between the filters an the kernel size in keras models? For example, I have a model with the following convolution layer: layer_conv_2d(filters = 32, ...
user avatar
  • 61

15 30 50 per page
1
2 3 4 5
641