nnc-challenge_Dual-Input_CNN
Posted by wowry
Copy the project to Neural Network Console Cloud
2-input CNN model by wowry @NNC-Challenge
Network Architecture : Main
| Type | Value |
|---|---|
| Output | 609,699 |
| CostParameter | 43,088,320 |
| CostAdd | 10,909,442 |
| CostMultiply | 2,219,536 |
| CostMultiplyAdd | 6,052,275,200 |
| CostDivision | 4,364,417 |
| CostExp | 4,364,417 |
| CostIf | 2,131,968 |
Network Architecture : Conv2D
| Type | Value |
|---|---|
| Output | 132,496 |
| CostParameter | 26,592 |
| CostAdd | 125,440 |
| CostMultiply | 25,088 |
| CostMultiplyAdd | 20,697,600 |
| CostDivision | 50,176 |
| CostExp | 50,176 |
| CostIf | 25,088 |
Network Architecture : FC
| Type | Value |
|---|---|
| Output | 1,168 |
| CostParameter | 100,480 |
| CostAdd | 256 |
| CostMultiply | 128 |
| CostMultiplyAdd | 100,352 |
| CostDivision | 128 |
| CostExp | 128 |
| CostIf | 0 |
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 “Test” dataset.
- The calculation is executed 10 times for each data.
- The average value is used as a final output.
Variable : y
- Accuracy : 0.7090069284064665
- Avg.Precision : 0.5032193732193733
- Avg.Recall : 0.5075283144570286
- Avg.F-Measures : 0.4809931506849315
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
- Swish – Prajit Ramachandran, Barret Zoph, and Quoc V. Le, SEARCHING FOR ACTIVATION FUNCTIONS. https://arxiv.org/abs/1710.05941
- BatchNormalization – Ioffe and Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. https://arxiv.org/abs/1502.03167
- Adam – Kingma and Ba, Adam: A Method for Stochastic Optimization. https://arxiv.org/abs/1412.6980