accelbrainbase.samplabledata.policysampler._mxnet package

Submodules

accelbrainbase.samplabledata.policysampler._mxnet.labeled_similar_image_policy module

class accelbrainbase.samplabledata.policysampler._mxnet.labeled_similar_image_policy.LabeledSimilarImagePolicy

Bases: accelbrainbase.samplabledata.policy_sampler.PolicySampler

Policy sampler for the Deep Q-learning to evaluate the value of the “action” of selecting the image with the highest similarity based on the “state” of observing an image.

The state-action value is proportional to the similarity between the previously observed image and the currently selected image.

This class calculates the image similarity by cross entorpy of labels (metadata).

check_the_end_flag(state_arr, meta_data_arr=None)

Check the end flag.

If this return value is True, the learning is end.

As a rule, the learning can not be stopped. This method should be overrided for concreate usecases.

Parameters:

• state_arr – state in self.t.
• meta_data_arr – meta data of the state.

Returns:

bool

draw()

Draw samples from distribtions.

Returns:Tuple of `mx.nd.array`s.

get_labeled_image_iterator()

getter for LabeledImageIterator.

labeled_image_iterator

getter for LabeledImageIterator.

observe_reward_value(state_arr, action_arr, meta_data_arr=None)

Compute the reward value.

Parameters:

• state_arr – Tensor of state.
• action_arr – Tensor of action.
• meta_data_arr – Meta data of actions.

Returns:

Reward value.

observe_state(state_arr, meta_data_arr)

Observe states of agents in last epoch.

Parameters:

• state_arr – Tensor of state.
• meta_data_arr – meta data of the state.

set_labeled_image_iterator(value)

setter for LabeledImageIterator.

update_state(action_arr, meta_data_arr=None)

Update state.

This method can be overrided for concreate usecases.

Parameters:

• action_arr – action in self.t.
• meta_data_arr – meta data of the action.

Returns:

Tuple data. - state in self.t+1. - meta data of the state.

accelbrainbase.samplabledata.policysampler._mxnet.labeled_summarization_policy module

class accelbrainbase.samplabledata.policysampler._mxnet.labeled_summarization_policy.LabeledSummarizationPolicy(txt_path_list, abstract_pos='top', s_a_dist_weight=0.3)

Bases: accelbrainbase.samplabledata.policy_sampler.PolicySampler

Policy sampler for the Deep Q-learning to evaluate the value of the “action” of selecting the image with the highest similarity based on the “state” of observing an image.

The state-action value is proportional to the similarity between the previously observed image and the currently selected image.

This class calculates the image similarity by mean squared error of images.

check_the_end_flag(state_arr, meta_data_arr=None)

Check the end flag.

If this return value is True, the learning is end.

As a rule, the learning can not be stopped. This method should be overrided for concreate usecases.

Parameters:

• state_arr – state in self.t.
• meta_data_arr – meta data of the state.

Returns:

bool

draw()

Draw samples from distribtions.

Returns:Tuple of `mx.nd.array`s.

get_unlabeled_t_hot_txt_iterator()

getter for UnlabeledTHotTXTIterator.

observe_reward_value(state_arr, action_arr, meta_data_arr=None)

Compute the reward value.

Parameters:

• state_arr – Tensor of state.
• action_arr – Tensor of action.
• meta_data_arr – Meta data of actions.

Returns:

Reward value.

observe_state(state_arr, meta_data_arr)

Observe states of agents in last epoch.

Parameters:

• state_arr – Tensor of state.
• meta_data_arr – meta data of the state.

set_unlabeled_t_hot_txt_iterator(value)

setter for UnlabeledTHotTXTIterator.

unlabeled_t_hot_txt_iterator

getter for UnlabeledTHotTXTIterator.

update_state(action_arr, meta_data_arr=None)

Update state.

This method can be overrided for concreate usecases.

Parameters:

• action_arr – action in self.t.
• meta_data_arr – meta data of the action.

Returns:

Tuple data. - state in self.t+1. - meta data of the state.

accelbrainbase.samplabledata.policysampler._mxnet.unlabeled_similar_image_policy module

class accelbrainbase.samplabledata.policysampler._mxnet.unlabeled_similar_image_policy.UnlabeledSimilarImagePolicy

Bases: accelbrainbase.samplabledata.policy_sampler.PolicySampler

Policy sampler for the Deep Q-learning to evaluate the value of the “action” of selecting the image with the highest similarity based on the “state” of observing an image.

The state-action value is proportional to the similarity between the previously observed image and the currently selected image.

This class calculates the image similarity by mean squared error of images.

check_the_end_flag(state_arr, meta_data_arr=None)

Check the end flag.

If this return value is True, the learning is end.

As a rule, the learning can not be stopped. This method should be overrided for concreate usecases.

Parameters:

• state_arr – state in self.t.
• meta_data_arr – meta data of the state.

Returns:

bool

draw()

Draw samples from distribtions.

Returns:Tuple of `mx.nd.array`s.

get_unlabeled_image_iterator()

getter for UnlabeledImageIterator.

observe_reward_value(state_arr, action_arr, meta_data_arr=None)

Compute the reward value.

Parameters:

• state_arr – Tensor of state.
• action_arr – Tensor of action.
• meta_data_arr – Meta data of actions.

Returns:

Reward value.

observe_state(state_arr, meta_data_arr)

Observe states of agents in last epoch.

Parameters:

• state_arr – Tensor of state.
• meta_data_arr – meta data of the state.

set_unlabeled_image_iterator(value)

setter for UnlabeledImageIterator.

unlabeled_image_iterator

getter for UnlabeledImageIterator.

update_state(action_arr, meta_data_arr=None)

Update state.

This method can be overrided for concreate usecases.

Parameters:

• action_arr – action in self.t.
• meta_data_arr – meta data of the action.

Returns:

Tuple data. - state in self.t+1. - meta data of the state.

Module contents