|
gptkbp:instanceOf
|
gptkb:model
gptkb:convolutional_neural_network
|
|
gptkbp:architecture
|
gptkb:feedforward_neural_network
|
|
gptkbp:citation
|
high
|
|
gptkbp:contains
|
fully connected layer
convolutional layers
ReLU activation functions
batch normalization layers
global average pooling layer
|
|
gptkbp:developedBy
|
gptkb:Shaoqing_Ren
gptkb:Xiangyu_Zhang
gptkb:Jian_Sun
gptkb:Kaiming_He
|
|
gptkbp:digestSize
|
224x224 pixels
|
|
gptkbp:frameworkAvailableIn
|
gptkb:TensorFlow
gptkb:Keras
gptkb:PyTorch
|
|
gptkbp:hasVariant
|
gptkb:ResNet-101
gptkb:ResNet-152
gptkb:ResNet-34
gptkb:ResNet-50
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
ResNet-18
|
|
gptkbp:introduced
|
gptkb:Deep_Residual_Learning_for_Image_Recognition
|
|
gptkbp:introducedIn
|
2015
|
|
gptkbp:level
|
18
|
|
gptkbp:notableFor
|
enabling very deep networks
solving vanishing gradient problem
|
|
gptkbp:openSource
|
available
|
|
gptkbp:parameter
|
~11.7 million
|
|
gptkbp:trainer
|
gptkb:ImageNet
|
|
gptkbp:usedFor
|
feature extraction
transfer learning
image classification
|
|
gptkbp:uses
|
residual connections
|
|
gptkbp:bfsParent
|
gptkb:Residual_Network
|
|
gptkbp:bfsLayer
|
7
|