|
gptkbp:instanceOf
|
gptkb:convolutional_neural_network
|
|
gptkbp:accuracyTop1
|
83.6% (ImageNet)
|
|
gptkbp:accuracyTop5
|
96.7% (ImageNet)
|
|
gptkbp:activatedBy
|
gptkb:Swish
|
|
gptkbp:architecture
|
gptkb:CNN
|
|
gptkbp:author
|
gptkb:Mingxing_Tan
gptkb:Quoc_V._Le
|
|
gptkbp:availableOn
|
gptkb:TensorFlow
gptkb:PyTorch
|
|
gptkbp:basedOn
|
gptkb:EfficientNet-B0
|
|
gptkbp:developedBy
|
gptkb:Google_AI
|
|
gptkbp:hasPretrainedWeights
|
yes
|
|
gptkbp:hasVariant
|
gptkb:EfficientNet-B0
gptkb:EfficientNet-B1
gptkb:EfficientNet-B2
gptkb:EfficientNet-B3
gptkb:EfficientNet-B4
gptkb:EfficientNet-B6
gptkb:EfficientNet-B7
|
|
gptkbp:improves
|
gptkb:DenseNet-201
gptkb:Inception-v4
gptkb:ResNet-152
|
|
gptkbp:introducedIn
|
2019
|
|
gptkbp:license
|
Apache 2.0
|
|
gptkbp:notablePublication
|
gptkb:EfficientNet:_Rethinking_Model_Scaling_for_Convolutional_Neural_Networks
|
|
gptkbp:parameter
|
30 million
|
|
gptkbp:partOf
|
EfficientNet family
|
|
gptkbp:publishedIn
|
gptkb:ICML_2019
|
|
gptkbp:resolution
|
456x456
|
|
gptkbp:scalingMethod
|
compound scaling
|
|
gptkbp:trainer
|
gptkb:ImageNet
|
|
gptkbp:usedFor
|
image classification
|
|
gptkbp:usedIn
|
feature extraction
transfer learning
fine-tuning
|
|
gptkbp:uses
|
depthwise separable convolutions
MBConv blocks
Squeeze-and-Excitation optimization
|
|
gptkbp:bfsParent
|
gptkb:EfficientNet
|
|
gptkbp:bfsLayer
|
8
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
EfficientNet-B5
|