|
gptkbp:instance_of
|
gptkb:television_channel
|
|
gptkbp:bfsLayer
|
8
|
|
gptkbp:bfsParent
|
gptkb:Cresnet_50
|
|
gptkbp:application
|
Image Classification
|
|
gptkbp:architectural_style
|
gptkb:Residual_Network
|
|
gptkbp:coat_of_arms
|
164
|
|
gptkbp:developed_by
|
gptkb:Microsoft_Research
|
|
gptkbp:established
|
Re LU
|
|
gptkbp:features
|
Skip Connections
|
|
gptkbp:field_of_study
|
gptkb:viewpoint
gptkb:Deep_Learning
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Cresnet 164
|
|
gptkbp:input_output
|
224x224
|
|
gptkbp:is_a_framework_for
|
gptkb:Graphics_Processing_Unit
gptkb:Py_Torch
|
|
gptkbp:is_optimized_for
|
Stochastic Gradient Descent
|
|
gptkbp:losses
|
Cross-Entropy Loss
|
|
gptkbp:notable_feature
|
gptkb:Deep_Residual_Learning
gptkb:Batch_Normalization
Global Average Pooling
|
|
gptkbp:performance
|
Top-5 Accuracy
|
|
gptkbp:predecessor
|
gptkb:Cresnet_152
|
|
gptkbp:provides_information_on
|
gptkb:Image_Net
|
|
gptkbp:related_to
|
gptkb:streaming_service
gptkb:microprocessor
gptkb:AI_Ethics
gptkb:API
gptkb:software
gptkb:Dropout
gptkb:engine
gptkb:Image_Net_Challenge
Backpropagation
Convolutional Layers
Data Augmentation
Fully Connected Layers
Pooling Layers
Overfitting
Underfitting
Feature Extraction
Neural Network Training
Regularization
Model Evaluation
Bias in AI
Gradient Descent
Ensemble Learning
AI Governance
Model Interpretability
Fine-tuning
Model Compression
AI Fairness
AI Policy
AI Regulation
Learning Rate Scheduling
Activation Layers
|
|
gptkbp:resolution
|
1000 classes
|
|
gptkbp:successor
|
Cresnet 200
|
|
gptkbp:training
|
varies
|
|
gptkbp:year_created
|
gptkb:2017
|