Training
The training components provide different methods to train the data with:
Adds the ability to perform classification.
Parameters:
Epochs: sets the number of epochs to perform. One epoch corresponds to the number of iterations it takes to go through the entire dataset one time.
Batch Size: the number of samples that the algorithm should train on at a time, before updating the weights in the model.
Loss function: specifies which loss function to apply.
Optimizer: specifies which optimizer algorithm to use
Beta 1: optimizer-specific parameter. See the TensorFlow Optimizers page for optimizer-specific definitions.
Beta 2: optimizer-specific parameter. See the TensorFlow Optimizers page for optimizer-specific definitions.
Learning rate: sets the learning rate for the algorithm. The value must be between 0 and 1.
Additional Stop Condition: allows you to specify an additional condition for when to stop training. Selecting Target Accuracydisplays an edit field where you can specify a training accuracy percentage threshold, after which training will stop.
Attempts to find a line of "best fit" on a group of points in a space.
Parameters:
Epochs: sets the number of epochs to perform. One epoch corresponds to the number of iterations it takes to go through the entire dataset one time.
Batch Size: the number of samples that the algorithm should train on at a time, before updating the weights in the model.
Loss Function: specifies which loss function to apply.
Optimizer: specifies which optimizer algorithm to use.
Beta 1: optimizer-specific parameter. See the TensorFlow Optimizers pagefor optimizer-specific definitions.
Beta 2: optimizer-specific parameter. See the TensorFlow Optimizers pagefor optimizer-specific definitions.
Learning Rate: sets the learning rate for the algorithm. The value must be between 0 and 1.
Adds the ability to train a reinforcement learning algorithm.
Parameters:
Method: specifies which reinforcement learning method to use.
Optimizer: specifies which optimizer algorithm to use.
History length: specifies how many frames there should be inside each sample.
Batch size: the number of samples that the algorithm should train on at a time, before updating the weights in the model.
Learning rate: sets the learning rate for the optimizer algorithm.
Max steps: specifies how many steps the agent is allowed to take before a Donestate is enforced.
Episodes: specifies how many episodesthe algorithm will run before the training ends. An episode transitions into a new one whenever a Donestate is received and is a way of defining how long the training will run. For example, if one training session consists of 15 episodes where reinforcement learning is training on a game, then the agent will have won, lost or reached max steps 15 times before the training ends.
Adds the ability to train a Generative Adversarial Network (GAN).
Parameters:
Switch: specifies which Switch component to use. This dropdown will only be populated if one or more Switch components exist in the model workspace.
Real Data: specifies the Data component that contains the "real" data to imitate. This dropdown will only be populated if one or more Data components exist in the model workspace.
Epochs: sets the number of iterations to perform.
Optimizer: specifies which optimizer algorithm to use.
Beta 1: optimizer-specific parameter. See the TensorFlow Optimizers page for optimizer-specific definitions.
Beta 2: optimizer-specific parameter. See the TensorFlow Optimizers page for optimizer-specific definitions.
Learning Rate: sets the learning rate for the algorithm. The value must be between 0 and 1.
Batch Size: the number of samples that the algorithm should train on at a time, before updating the weights in the model.
Additional Stop Condition: allows you to specify an additional condition for when to stop training. Selecting Target Accuracy displays an edit field where you can specify a training accuracy percentage threshold, after which training will stop.
Adds a Detector (e.g., for object detection).
Parameters:
Epochs: sets the number of epochs to perform. One epoch corresponds to the number of iterations it takes to go through the entire dataset one time.
Grid Size: the size that the grid image is divided into for the Yolo V1 model.
Batch Size: the number of samples that the algorithm should train on at a time, before updating the weights in the model.
Number of Boxes: the number of predicted bounding boxes per object by the Yolo V1 model.
Threshold: the lower threshold on the probability for boundary boxes.
λclassification: the coefficient of loss corresponding to the object detection loss in the Yolo V1 model.
λnon object: the coefficient of loss corresponding to the non-object detection loss in the Yolo V1 model.
Optimizer: specifies which optimizer algorithm to use.
Beta 1: optimizer-specific parameter. See the TensorFlow Optimizers page for optimizer-specific definitions.
Beta 2: optimizer-specific parameter. See the TensorFlow Optimizers page for optimizer-specific definitions.
Learning Rate: sets the learning rate for the algorithm. The value must be between 0 and 1.
Additional Stop Condition: allows you to specify an additional condition for when to stop training. Selecting Target Accuracydisplays an edit field where you can specify a training accuracy percentage threshold, after which training will stop.
