beatmup.nnets.Classifier¶
- class beatmup.nnets.Classifier¶
Image classifier base class. Makes a runnable AbstractTask from a Model. Adds an image input and a vector of probabilities for output.
- __init__(*args, **kwargs)¶
Methods
__init__
(*args, **kwargs)add_connection
(self, source_op, dest_op[, ...])Adds a connection between two given ops.
add_operation
(self, op_name, new_op)Adds a new operation to the model before another operation in the execution order.
add_output
(*args, **kwargs)Overloaded function.
append
(self, new_op[, connect])Adds a new operation to the model.
connect
(*args, **kwargs)Overloaded function.
count_multiply_adds
(self)Provides an estimation of the number of multiply-adds characterizing the model complexity.
count_texel_fetches
(self)Provides an estimation of the total number of texels fetched by all the operations in the model per image.
get_first_operation
(self)Returns the first operation in the model
get_last_operation
(self)Returns the last operation in the model
get_output_data
(*args, **kwargs)Overloaded function.
get_probabilities
(self)Returns the last classification results (vector of probabilities per class).
serialize
(self)Returns serialized representation of the model as a string.
start
(self, arg0)Initiates the classification of a given image.