python (65.1k questions)

javascript (44.2k questions)

reactjs (22.7k questions)

java (20.8k questions)

c# (17.4k questions)

html (16.3k questions)

r (13.7k questions)

android (12.9k questions)

Questions - mnist

Is it possible to train a CNN for MNIST under 1 minute with CPU?

I am programming a CNN example for demonstration purposes to university students and it should classify MNIST with upwards of 80% accuracy. I use the following architecture and the training takes like...
test-img

Creed Bratton

tensorflow

keras

deep-learning

conv-neural-network

mnist

Votes: 0

Answers: 1

Latest Answer

I was able to get very fast training with the following model: model = Sequential() model.add(Conv2D(32, (3, 3), input_shape=(28,28,1))) convLayer01 = Activation('re...
test-img

marco romelli

How do i interleave a neural network to run half iterations on a variable then move to the next target class training?

I have a function which tries to make a neural network immune to adversarial training of the MNIST handwritten digits. I am trying to interleave the training by performing a number of adversarial trai...
test-img

Clive T

python

tensorflow

deep-learning

mnist

generative-adversarial-network

Votes: 0

Answers: 0

MNIST overfitting

I am currently working on the MNIST dataset. My model has overfit the training data and I want to reduce the overfitting by using weight_decay. I am currently using 0.1 as the value for weight_decay w...
test-img

Prajwal

python

neural-network

pytorch

mnist

overfitting-underfitting

Votes: 0

Answers: 1

Latest Answer

I cannot know any information. (Such as loss function, dataset size, dataset content (training and validation), results of 100 or 200 epochs, your scope of the question) However, the overfitted model ...
test-img

nambee

MNIST dataset overfitting

I am working with the MNIST dataset and I have created the following network. I want to overfit the training data and I think I am doing that here. My training loss is lower than my validation loss. T...
test-img

Prajwal

pytorch

mnist

overfitting-underfitting

Votes: 0

Answers: 1

Latest Answer

Although I won't attempt to provide a rigorous definition, the term "overfit" typically means that the training loss continues to decrease whereas the validation loss stays stagnant at a pos...
test-img

Jake Tae

Posts

Questions

Blogs

Jobs