n3 0.1.3

Nerual Network Notation

N3: Neural Network Notation

This project is in construction. Please be aware of using it.

node LeNet5:
    let K: kernel size = int 5

    let C: input channels = dim
    let W: width = dim
    let H: height = dim

    with Conv2D:
        set kernel size = K
        set padding = K / 2
        set stride = 2

    node MyConv:
        1. Conv2D
        2. Relu

    0. Input                    =  C, W  , H
    1. MyConv                   = 32, W/2, H/2
    2. MyConv                   = 64, W/4, H/4
    3. Transform                = 64* W/4* H/4
    4. Linear + Relu + Dropout  = 1024
    5. Linear                   = 10

Usage

• Training

  $ n3 train image-classification --model LeNet5 --data Mnist --devices cuda:0 cpu
  

• Evaluating

  $ n3 eval image-classification --model LeNet5 --data Mnist --devices cuda:0 cpu
  

• Publish

  $ n3 publish image-classification --model LeNet5 --data Mnist --target android:java
  

  • android: java, flutter
  • ios: flutter
  • universal: c++, python
• Monitoring using Tensorboard

  $ n3 run tensorboard  # and, browse http://localhost::xxxx/
  

• Clustering with n3-clu

  $ n3 eval image-classification --model LeNet5 --data Mnist --devices w:180:cuda:0 w:192.168.0.181 cpu
  

  • "w:180:cuda:0": the "cuda:0" device in "xxx.xxx.xxx.180" (local)
  • "w:192.168.0.181": automatically choose devices in "192.168.0.181"
  • These can be defined as environment variables (N3_DEVICES)