|
gptkbp:instanceOf
|
gptkb:deep_convolutional_neural_network
|
|
gptkbp:activatedBy
|
gptkb:ReLU
|
|
gptkbp:architecture
|
residual network
|
|
gptkbp:author
|
gptkb:Shaoqing_Ren
gptkb:Xiangyu_Zhang
gptkb:Jian_Sun
gptkb:Kaiming_He
|
|
gptkbp:bench
|
gptkb:ImageNet
|
|
gptkbp:citation
|
over 100,000
|
|
gptkbp:contains
|
batch normalization
fully connected layer
convolutional layers
global average pooling
|
|
gptkbp:developedBy
|
gptkb:Microsoft_Research
|
|
gptkbp:digestSize
|
224x224
|
|
gptkbp:improves
|
gptkb:VGG-19
|
|
gptkbp:introduced
|
gptkb:Deep_Residual_Learning_for_Image_Recognition
|
|
gptkbp:introducedIn
|
2015
|
|
gptkbp:level
|
34
|
|
gptkbp:notableFeature
|
enables training of deeper networks
solves vanishing gradient problem
|
|
gptkbp:openSource
|
yes
|
|
gptkbp:outputClasses
|
1000
|
|
gptkbp:platform
|
gptkb:TensorFlow
gptkb:Keras
gptkb:PyTorch
|
|
gptkbp:pretrainedWeightsAvailable
|
yes
|
|
gptkbp:relatedTo
|
gptkb:ResNet-101
gptkb:ResNet-152
gptkb:ResNet-18
gptkb:ResNet-50
|
|
gptkbp:usedFor
|
feature extraction
image classification
object detection
|
|
gptkbp:uses
|
residual connections
|
|
gptkbp:bfsParent
|
gptkb:Residual_Network
|
|
gptkbp:bfsLayer
|
8
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
ResNet-34
|