Toĭisable all extensions including those that are placedĪt the default location, pass an empty string. disable_gfusing Turns off fusing of grouped convolutionsĭirectory or list of directories with extensions. disable_fusing Turns off fusing of linear operations to Convolution Scale values to be used for the input image per Value for a GREEN channel, value for a BLUE channel) Values is the following: (value for a RED channel, Mean values to be used for the input image perĬhannel. mean_values MEAN_VALUES, -ms MEAN_VALUES output OUTPUT The name of the output operation of the model. ![]() ![]() Usually this is a name of the input placeholder of the input INPUT The name of the input operation of the given model. Switches the input channels order from RGB to BGR.Īpplied to original inputs of the model when and only Not applied for any input that does not match with the Is overridden by the -input parameter, this scale is ![]() The shape should not contain undefinedĭimensions (? or -1) and should fit the dimensionsĭefined in the input operation of the graph.Īll input values coming from original network inputs Of brackets are allowed to enclose the dimensions: The layout acceptable by Inference Engine. Performs necessary transforms to convert the shape to '' format, where the order of dimensionsĭepends on the framework input layout of the model.įor example, is used for Caffe* models and Input shape that should be fed to an input node of the Is the directory from where the Model Optimizer is xml/.bin files.ĭirectory that stores the generated IR. This parameter is used to name a network inĪ generated IR and output. Model_name parameter passed to the final create_ir Tensorflow*: a file with a pre-trained model (binary input_model INPUT_MODEL, -w INPUT_MODEL, -m INPUT_MODEL Name of the framework used to train the input model. h, -help Shows this help message and exit The MXNet-specific list is further down in this document. The following list provides the framework agnostic parameters. Using Framework-Agnostic Conversion Parameters
0 Comments
Leave a Reply. |