nnc-challenge_FaceEmotionClassification
Posted by aka
Copy the project to Neural Network Console Cloud
Network Architecture : Main
Type | Value |
---|---|
Output | 262,148 |
CostParameter | 370,963 |
CostAdd | 7,882,243 |
CostMultiply | 4,390,915 |
CostMultiplyAdd | 878,100,480 |
CostDivision | 3 |
CostExp | 3 |
CostIf | 3,948,544 |
Network Architecture : CNN
Type | Value |
---|---|
Output | 63,504 |
CostParameter | 2,608 |
CostAdd | 50,176 |
CostMultiply | 25,088 |
CostMultiplyAdd | 1,919,232 |
CostDivision | 0 |
CostExp | 0 |
CostIf | 12,544 |
Network Architecture : Share
Type | Value |
---|---|
Output | 2,949,120 |
CostParameter | 72,976 |
CostAdd | 7,340,032 |
CostMultiply | 4,128,768 |
CostMultiplyAdd | 632,291,328 |
CostDivision | 0 |
CostExp | 0 |
CostIf | 3,670,016 |
Network Architecture : Face
Type | Value |
---|---|
Output | 1,474,560 |
CostParameter | 36,994 |
CostAdd | 1,179,648 |
CostMultiply | 458,752 |
CostMultiplyAdd | 94,371,840 |
CostDivision | 131,072 |
CostExp | 131,072 |
CostIf | 229,376 |
Network Architecture : Emotion
Type | Value |
---|---|
Output | 262,921 |
CostParameter | 297,987 |
CostAdd | 542,211 |
CostMultiply | 262,147 |
CostMultiplyAdd | 245,809,152 |
CostDivision | 3 |
CostExp | 3 |
CostIf | 278,528 |
Training Procedure : Optimizer
Optimize network “Main” using “Training” dataset.
- Batch size : 64
- Solver : Adam
- Learning rate(Alpha) : 0.001
- Beta1 : 0.9
- Beta2 : 0.999
- Epsilon : 1e-08
- Weight decay is not applied.
Experimental Result : Learning Curve
Experimental Result : Evaluation
Evaluate network “MainRuntime” using “Validation” dataset.
Variable : y
- Accuracy : 0.794
- Avg.Precision : 0.7855602437880919
- Avg.Recall : 0.6332162156290059
- Avg.F-Measures : 0.6762515587289175
References
- Sony Corporation. Neural Network Console : Not just train and evaluate. You can design neural networks with fast and intuitive GUI. https://dl.sony.com/
- Sony Corporation. Neural Network Libraries : An open source software to make research, development and implementation of neural network more efficient. https://nnabla.org/
- Convolution – Chen et al., DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. https://arxiv.org/abs/1606.00915, Yu et al., Multi-Scale Context Aggregation by Dilated Convolutions. https://arxiv.org/abs/1511.07122
- BatchNormalization – Ioffe and Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. https://arxiv.org/abs/1502.03167
- ReLU – Vinod Nair, Geoffrey E. Hinton. Rectified Linear Units Improve Restricted Boltzmann Machines. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.165.6419&rep=rep1&type=pdf
- Adam – Kingma and Ba, Adam: A Method for Stochastic Optimization. https://arxiv.org/abs/1412.6980