https://github.com/ltfschoen/aind2-cnn

https://github.com/ltfschoen/aind2-cnn

classification convolutional-neural-networks deep-neural-networks global-average-pooling image-augmentation image-recognition keras loss-functions mlp model-architecture multi-layer-architecture multi-layer-perceptron one-hot-encode optimiser tensorflow testing training validation

Last synced: about 2 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/ltfschoen/aind2-cnn
• Owner: ltfschoen
• Created: 2017-06-20T03:26:15.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2017-06-22T02:06:57.000Z (over 7 years ago)
• Last Synced: 2024-10-19T16:02:25.881Z (3 months ago)
• Topics: classification, convolutional-neural-networks, deep-neural-networks, global-average-pooling, image-augmentation, image-recognition, keras, loss-functions, mlp, model-architecture, multi-layer-architecture, multi-layer-perceptron, one-hot-encode, optimiser, tensorflow, testing, training, validation
• Language: Jupyter Notebook
• Size: 50.2 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# aind2-cnn

### Instructions

1. Clone the repository and navigate to the downloaded folder.

	

	```	

		git clone https://github.com/udacity/aind2-cnn.git

		cd aind2-cnn

	```

2. Obtain the necessary Python packages, and switch Keras backend to Tensorflow.  	

	For __Mac/OSX__:

	```

		conda env create -f requirements/aind-dog-mac.yml

		source activate aind-dog

		KERAS_BACKEND=tensorflow python -c "from keras import backend"

	```

	For __Linux__:

	```

		conda env create -f requirements/aind-dog-linux.yml

		source activate aind-dog

		KERAS_BACKEND=tensorflow python -c "from keras import backend"

	```

	For __Windows__:

	```

		conda env create -f requirements/aind-dog-windows.yml

		activate aind-dog

		set KERAS_BACKEND=tensorflow

		python -c "from keras import backend"

	```

	

3. Run `cd mnist-mlp; jupyter notebook mnist_mlp.ipynb`