Convolutional Neural Networks¶

Classes for deploying ConvNets.

AlexNet¶

class perception.AlexNet(config, model_dir=None, use_default_weights=False, dynamic_load=True)¶

Bases: object

Wrapper for tensorflow AlexNet. Note: training not yet supported.

Parameters:	config (`autolab_core.YamlConfig`) – specifies the parameters of the network

Notes

Required configuration paramters are specified in Other Parameters

Other Parameters:

batch_size (int) – size of batches, less than largest possible prediction to save memory
im_height (int) – height of input images
im_width (int) – width of input images
channels (int) – number of channels of input image (should be 3)
output_layer (str) – name of output layer for classification
feature_layer (:obj`str`) – name of layer to use for feature extraction (e.g. conv5)

close_session()¶: Close tensorflow session. Exposes for memory management.

predict(image_arr, featurize=False)¶

Predict a set of images in batches.

Parameters:	image_arr (NxHxWxC `numpy.ndarray`) – input set of images in a num_images x image height x image width x image channels array (must match parameters of network) featurize (bool) – whether or not to use the featurization layer or classification output layer
Returns:	num_images x feature_dim containing the output values for each input image
Return type:	`numpy.ndarray`

featurize(image_arr)¶

Featurize a set of images in batches.

Parameters:	image_arr (NxHxWxC `numpy.ndarray`) – input set of images in a num_images x image height x image width x image channels array (must match parameters of network)
Returns:	num_images x feature_dim containing the output values for each input image
Return type:	`numpy.ndarray`

build_alexnet(weights, output_layer=None)¶: Connects graph of alexnet from weights