dlpy.applications.ResNet101_Caffe

dlpy.applications.ResNet101_Caffe(conn, model_table='RESNET101_CAFFE', n_classes=1000, n_channels=3, width=224, height=224, scale=1, batch_norm_first=False, random_flip=None, random_crop=None, offsets=103.939, 116.779, 123.68, pre_trained_weights=False, pre_trained_weights_file=None, include_top=False, random_mutation=None, reshape_after_input=None)

Generates a deep learning model with the ResNet101 architecture with convolution shortcut.

Parameters

connCAS

Specifies the CAS connection object.

model_tablestring or dict or CAS table, optional

Specifies the CAS table to store the deep learning model.

batch_norm_firstbool, optional

Specifies whether to have batch normalization layer before the convolution layer in the residual block. For a detailed discussion about this, please refer to this paper: He, Kaiming, et al. “Identity mappings in deep residual networks.” European Conference on Computer Vision. Springer International Publishing, 2016. Default: False

n_classesint, optional

Specifies the number of classes. If None is assigned, the model will automatically detect the number of classes based on the training set. Default: 1000

n_channelsint, optional

Specifies the number of the channels (i.e., depth) of the input layer. Default: 3

widthint, optional

Specifies the width of the input layer. Default: 224

heightint, optional

Specifies the height of the input layer. Default: 224

scaledouble, optional

Specifies a scaling factor to be applied to each pixel intensity values. Default: 1

random_flipstring, optional

Specifies how to flip the data in the input layer when image data is used. Approximately half of the input data is subject to flipping. Valid Values: ‘h’, ‘hv’, ‘v’, ‘none’

random_cropstring, optional

Specifies how to crop the data in the input layer when image data is used. Images are cropped to the values that are specified in the width and height parameters. Only the images with one or both dimensions that are larger than those sizes are cropped. Valid Values: ‘none’, ‘unique’, ‘randomresized’, ‘resizethencrop’

offsetsdouble or iter-of-doubles, optional

Specifies an offset for each channel in the input data. The final input data is set after applying scaling and subtracting the specified offsets. Default: (103.939, 116.779, 123.68)

pre_trained_weightsbool, optional

Specifies whether to use the pre-trained weights from ImageNet data set Default: False

pre_trained_weights_filestring, optional

Specifies the file name for the pre-trained weights. Must be a fully qualified file name of SAS-compatible file (e.g., *.caffemodel.h5) Note: Required when pre_trained_weights=True.

include_topbool, optional

Specifies whether to include pre-trained weights of the top layers, i.e. the last layer for classification. Default: False.

random_mutationstring, optional

Specifies how to apply data augmentations/mutations to the data in the input layer. Valid Values: ‘none’, ‘random’

reshape_after_inputReshape, optional

Specifies whether to add a reshape layer after the input layer.

Returns

Sequential

If pre_trained_weights is False

Model

If pre_trained_weights is True

References

https://arxiv.org/pdf/1512.03385.pdf