New answers tagged convolutional-neural-network
0
votes
Applying dropout effectively in CNN
Firstly, why do we use dropout in the first place? Dropout is a regularization technique designed to improve generalization and prevent overfitting.
With this in mind, you should not necessarily ...
0
votes
Accepted
Asynchronous Training of Deep Learning Models
By default, CUDA computations (i.e. kernels) are asynchronous (see the CUDA docs and the Pytorch docs). Therefore, what you suggested is already happening under the hoods.
1
vote
why validation accuracy is stuck at 75%?
My first inclination is that your dataset size is relatively small, and you have many hidden layers, which increases the likelihood of your model overgeneralizing on the training data, leading to ...
Top 50 recent answers are included
Related Tags
convolutional-neural-network × 733deep-learning × 282
neural-network × 253
keras × 162
machine-learning × 157
cnn × 122
tensorflow × 114
python × 82
image-classification × 76
computer-vision × 73
convolution × 58
pytorch × 43
classification × 34
training × 25
backpropagation × 20
image-recognition × 18
autoencoder × 17
lstm × 16
rnn × 16
overfitting × 16
transfer-learning × 15
loss-function × 14
time-series × 13
nlp × 12
dataset × 12