https://github.com/katerynazakharova/deep-learning-and-neural-networks

Examples of NN models. DL algorithms
https://github.com/katerynazakharova/deep-learning-and-neural-networks

deep-learning dl h5py matplotlib neural-network neural-networks nn numpy pli scipy

Last synced: 12 days ago
JSON representation

Examples of NN models. DL algorithms

• Host: GitHub
• URL: https://github.com/katerynazakharova/deep-learning-and-neural-networks
• Owner: KaterynaZakharova
• Created: 2020-12-27T20:26:12.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2020-12-27T21:07:00.000Z (about 4 years ago)
• Last Synced: 2023-08-02T04:31:38.678Z (over 1 year ago)
• Topics: deep-learning, dl, h5py, matplotlib, neural-network, neural-networks, nn, numpy, pli, scipy
• Language: Python
• Homepage:
• Size: 2.62 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Deep Learning and Neural Networks Example

Examples of NN models. DL algorithms

## Task description

Given test and train data contains images of cats and non-cats. Need to create the model, which defines a cat picture(1) and a non-cat picture(0).

### Outputs:

* For two-layer network:

  

  **(there is a bird picture)**

  

  ```

  y = 0. It's a non-cat picture.

  Number of training examples: 209

  Number of testing examples: 50

  

  Each image is of size: (64, 64, 3)

  train_x_orig shape: (209, 64, 64, 3)

  train_y shape: (1, 209)

  test_x_orig shape: (50, 64, 64, 3)

  test_y shape: (1, 50)

  train_x's shape: (12288, 209)

  test_x's shape: (12288, 50)

  Cost after iteration 0: 0.693049735659989

  Cost after iteration 100: 0.6464320953428849

  ...                       ...

  Cost after iteration 2400: 0.04855478562877019

  Accuracy: 0.9999999999999998

  Accuracy: 0.72```

  

* For L-layer network (4-layer):

  

  **(there is a bird picture)**

  

  ```

  y = 0. It's a non-cat picture.

  

  Number of training examples: 209

  Number of testing examples: 50

  

  Each image is of size: (64, 64, 3)

  train_x_orig shape: (209, 64, 64, 3)

  train_y shape: (1, 209)

  test_x_orig shape: (50, 64, 64, 3)

  test_y shape: (1, 50)

  train_x's shape: (12288, 209)

  test_x's shape: (12288, 50)

  

  Cost after iteration 0: 0.771749

  Cost after iteration 100: 0.672053

  ...                       ...

  Cost after iteration 2400: 0.092878

  

  Accuracy: 0.985645933014

  Accuracy: 0.8```