GoogLeNet

E472885

convolutional neural network architecture deep learning model image classification model

GoogLeNet is a deep convolutional neural network developed by Google that popularized the Inception architecture and achieved state-of-the-art performance in image recognition tasks.

Try in SPARQL Jump to: Statements Referenced by

Statements (49)

Predicate	Object
instanceOf	convolutional neural network architecture ⓘ deep learning model ⓘ image classification model ⓘ
achieved	state-of-the-art performance on ImageNet ⓘ
alsoKnownAs	Inception v1 NERFINISHED ⓘ
architectureType	multi-branch convolutional network ⓘ
award	winner of ILSVRC 2014 classification challenge ⓘ
basedOn	Inception architecture ⓘ
competition	ILSVRC 2014 NERFINISHED ⓘ
dataset	ImageNet NERFINISHED ⓘ
designGoal	improve computational efficiency ⓘ increase depth and width without large parameter growth ⓘ
developer	Google ⓘ Google Research NERFINISHED ⓘ
domain	large-scale visual recognition ⓘ
field	computer vision ⓘ deep learning ⓘ
framework	Caffe NERFINISHED ⓘ PyTorch NERFINISHED ⓘ TensorFlow NERFINISHED ⓘ
influencedBy	Network-in-Network architecture NERFINISHED ⓘ
inputResolution	224x224 pixels ⓘ
inspired	Inception v2 NERFINISHED ⓘ Inception v3 NERFINISHED ⓘ Inception v4 NERFINISHED ⓘ Inception-ResNet NERFINISHED ⓘ later Inception variants ⓘ
introducedInPaper	Going Deeper with Convolutions NERFINISHED ⓘ
numberOfLayers	22 ⓘ
numberOfParameters	about 5 million ⓘ
optimizationMethod	stochastic gradient descent ⓘ
paperTitle	Going Deeper with Convolutions NERFINISHED ⓘ
paperVenue	CVPR 2015 NERFINISHED ⓘ
regularization	data augmentation ⓘ dropout ⓘ
task	image classification ⓘ image recognition ⓘ object recognition ⓘ
top5ErrorRate	6.67% ⓘ
uses	1x1 convolutions ⓘ 3x3 convolutions ⓘ 5x5 convolutions ⓘ Inception modules NERFINISHED ⓘ ReLU activation functions ⓘ auxiliary classifiers ⓘ average pooling ⓘ global average pooling before final layer ⓘ max pooling ⓘ
yearIntroduced	2014 ⓘ

Referenced by (2)

Full triples — surface form annotated when it differs from this entity's canonical label.

Inception architecture → introducedIn → GoogLeNet ⓘ

ImageNet → influenced → GoogLeNet ⓘ