All Questions
11 questions
0
votes
1
answer
502
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
0
votes
1
answer
2k
views
How to save the history epochs and plots in files from keras models
I have a question, that maybe is very simple, but I can't do it: I have 3 neural networks which are trained with 100 epochs, and I need to save all the history's train displayed at the end in a .txt ...
- 13
0
votes
1
answer
623
views
Keras: Very high loss for Autoencoder
I am trying to implement an autoencoder for prediction of multiple labels using Keras. This is a snippet:
...
- 101
0
votes
1
answer
972
views
How many images can be trained in Google Colab? [closed]
I am using the ResNet50 pretrained model to train my images using TensorFlow. I have 70k images and upgraded to Google Colab Pro, but still I am facing a memory error. So how many images I can train ...
- 391
1
vote
0
answers
1k
views
setting class weights for imbalanced dataset in tensorflow [closed]
I have 24 classes in my dataset and I am trying to set class weights in the following way:
...
- 111
1
vote
1
answer
447
views
ValueError: Error when checking input: expected conv2d_25_input to have shape (144, 256, 3) but got array with shape (256, 144, 3)
I have built a CNN with images of size 720 (height) and 1280 (width). I attempt to re scale images to 144x256. However, I receive this error:
...
- 451
0
votes
0
answers
666
views
why evaluate_generator accuracy too much by using flow_from_directory with shuffle true?
i am using tensorflow and keras on colab i train with shuffled data but i met this strange accuracy with evaluate_generator with my training set that has 95% acc
if i did not shuffle my data with ...
1
vote
1
answer
135
views
How reproducible should CNN models be? [closed]
I want to train several CNN architectures with Google Colab (GPU), Keras and Tensorflow.
Since the trained models are not reproducible due to GPU support, I would like to train the models several ...
- 45
1
vote
1
answer
4k
views
keras UserWarning: The input 1303 could not be retrieved. It could be because a worker has died
I am trying to train an autoencoder CNN on Google Colab using keras. I have mounted my Google Drive which contains all training data. The training uses six workers and the data is loaded by the ...
- 113
0
votes
2
answers
86
views
I am getting different mean_absolute_error when i retrain my model everything same
I have set my numpy random seed to 0.
I am training on colab and using keras.
I didn't change anything.
I just re-ran my cell and the val_absolute_error changed.
Code:
...
5
votes
3
answers
4k
views
Very Fast Training After First Epoch
I trained an InceptionV3 model using plant images. I used Keras library. When training was started, first epoch took 29s per step and then other steps took approximately 530ms per step. So that made ...
- 452