conv_split_awa.py [497:583]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - print('\t\t\t\tTask updates after Task%d done!'%(task)) # If importance method is '*-GEM' then store the episodic memory for the task if 'GEM' in model.imp_method: data_to_sample_from = { 'images': task_train_images, 'labels': task_train_labels, } if model.imp_method == 'S-GEM': # Get the important samples from the current task if is_herding: # Sampling based on MoF # Compute the features of training data features_dim = model.image_feature_dim features = np.zeros([num_train_examples, features_dim]) samples_at_a_time = 32 residual = num_train_examples % samples_at_a_time for i in range(num_train_examples// samples_at_a_time): offset = i * samples_at_a_time features[offset:offset+samples_at_a_time] = sess.run(model.features, feed_dict={model.x: task_train_images[offset:offset+samples_at_a_time], model.y_: task_train_labels[offset:offset+samples_at_a_time], model.keep_prob: 1.0, model.output_mask: logit_mask, model.train_phase: False}) if residual > 0: offset = (i + 1) * samples_at_a_time features[offset:offset+residual] = sess.run(model.features, feed_dict={model.x: task_train_images[offset:offset+residual], model.y_: task_train_labels[offset:offset+residual], model.keep_prob: 1.0, model.output_mask: logit_mask, model.train_phase: False}) imp_images, imp_labels = sample_from_dataset_icarl(data_to_sample_from, features, task_labels[task], SAMPLES_PER_CLASS) else: # Random sampling # Do the uniform sampling/ only get examples from current task importance_array = np.ones(num_train_examples, dtype=np.float32) imp_images, imp_labels = sample_from_dataset(data_to_sample_from, importance_array, task_labels[task], SAMPLES_PER_CLASS) task_memory = { 'images': deepcopy(imp_images), 'labels': deepcopy(imp_labels), } task_based_memory.append(task_memory) elif model.imp_method == 'A-GEM': # Do the uniform sampling/ only get examples from current task importance_array = np.ones(num_train_examples, dtype=np.float32) if KEEP_EPISODIC_MEMORY_FULL: update_episodic_memory(data_to_sample_from, importance_array, episodic_mem_size, task, episodic_images, episodic_labels) else: imp_images, imp_labels = sample_from_dataset(data_to_sample_from, importance_array, task_labels[task], SAMPLES_PER_CLASS) if not KEEP_EPISODIC_MEMORY_FULL: # Fill the memory to always keep M/T samples per task total_imp_samples = imp_images.shape[0] eps_offset = task * total_imp_samples episodic_images[eps_offset:eps_offset+total_imp_samples] = imp_images episodic_labels[eps_offset:eps_offset+total_imp_samples, head_offset:head_offset+TOTAL_CLASSES] = imp_labels episodic_filled_counter += total_imp_samples print('Unique labels in the episodic memory: {}'.format(np.unique(np.nonzero(episodic_labels)[1]))) # Inspect episodic memory if DEBUG_EPISODIC_MEMORY: # Which labels are present in the memory unique_labels = np.unique(np.nonzero(episodic_labels)[-1]) print('Unique Labels present in the episodic memory'.format(unique_labels)) print('Labels count:') for lbl in unique_labels: print('Label {}: {} samples'.format(lbl, np.where(np.nonzero(episodic_labels)[-1] == lbl)[0].size)) # Is there any space which is not filled print('Empty space: {}'.format(np.where(np.sum(episodic_labels, axis=1) == 0))) print('Episodic memory of {} images at task {} saved!'.format(episodic_images.shape[0], task)) # If sampling flag is set, store few of the samples from previous task if do_sampling: # Do the uniform sampling/ only get examples from current task importance_array = np.ones([datasets[task]['train']['images'].shape[0]], dtype=np.float32) # Get the important samples from the current task imp_images, imp_labels = sample_from_dataset(datasets[task]['train'], importance_array, task_labels[task], SAMPLES_PER_CLASS) if imp_images is not None: if last_task_x is None: last_task_x = imp_images last_task_y_ = imp_labels else: last_task_x = np.concatenate((last_task_x, imp_images), axis=0) last_task_y_ = np.concatenate((last_task_y_, imp_labels), axis=0) # Delete the importance array now that you don't need it in the current run del importance_array print('\t\t\t\tEpisodic memory is saved for Task%d!'%(task)) if cross_validate_mode: # Only evaluate after the last task if (task == model.num_tasks - 1) or MULTI_TASK: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - conv_split_awa_hybrid.py [511:596]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - print('\t\t\t\tTask updates after Task%d done!'%(task)) # If importance method is '*-GEM' then store the episodic memory for the task if 'GEM' in model.imp_method: data_to_sample_from = { 'images': task_train_images, 'labels': task_train_labels, } if model.imp_method == 'S-GEM': # Get the important samples from the current task if is_herding: # Sampling based on MoF # Compute the features of training data features_dim = model.image_feature_dim features = np.zeros([num_train_examples, features_dim]) samples_at_a_time = 32 residual = num_train_examples % samples_at_a_time for i in range(num_train_examples// samples_at_a_time): offset = i * samples_at_a_time features[offset:offset+samples_at_a_time] = sess.run(model.features, feed_dict={model.x: task_train_images[offset:offset+samples_at_a_time], model.y_: task_train_labels[offset:offset+samples_at_a_time], model.keep_prob: 1.0, model.output_mask: logit_mask, model.train_phase: False}) if residual > 0: offset = (i + 1) * samples_at_a_time features[offset:offset+residual] = sess.run(model.features, feed_dict={model.x: task_train_images[offset:offset+residual], model.y_: task_train_labels[offset:offset+residual], model.keep_prob: 1.0, model.output_mask: logit_mask, model.train_phase: False}) imp_images, imp_labels = sample_from_dataset_icarl(data_to_sample_from, features, task_labels[task], SAMPLES_PER_CLASS) else: # Random sampling # Do the uniform sampling/ only get examples from current task importance_array = np.ones(num_train_examples, dtype=np.float32) imp_images, imp_labels = sample_from_dataset(data_to_sample_from, importance_array, task_labels[task], SAMPLES_PER_CLASS) task_memory = { 'images': deepcopy(imp_images), 'labels': deepcopy(imp_labels), } task_based_memory.append(task_memory) elif model.imp_method == 'A-GEM': # Do the uniform sampling/ only get examples from current task importance_array = np.ones(num_train_examples, dtype=np.float32) if KEEP_EPISODIC_MEMORY_FULL: update_episodic_memory(data_to_sample_from, importance_array, episodic_mem_size, task, episodic_images, episodic_labels) else: imp_images, imp_labels = sample_from_dataset(data_to_sample_from, importance_array, task_labels[task], SAMPLES_PER_CLASS) if not KEEP_EPISODIC_MEMORY_FULL: # Fill the memory to always keep M/T samples per task total_imp_samples = imp_images.shape[0] eps_offset = task * total_imp_samples episodic_images[eps_offset:eps_offset+total_imp_samples] = imp_images episodic_labels[eps_offset:eps_offset+total_imp_samples, head_offset:head_offset+TOTAL_CLASSES] = imp_labels episodic_filled_counter += total_imp_samples print('Unique labels in the episodic memory: {}'.format(np.unique(np.nonzero(episodic_labels)[1]))) # Inspect episodic memory if DEBUG_EPISODIC_MEMORY: # Which labels are present in the memory unique_labels = np.unique(np.nonzero(episodic_labels)[-1]) print('Unique Labels present in the episodic memory'.format(unique_labels)) print('Labels count:') for lbl in unique_labels: print('Label {}: {} samples'.format(lbl, np.where(np.nonzero(episodic_labels)[-1] == lbl)[0].size)) # Is there any space which is not filled print('Empty space: {}'.format(np.where(np.sum(episodic_labels, axis=1) == 0))) print('Episodic memory of {} images at task {} saved!'.format(episodic_images.shape[0], task)) # If sampling flag is set, store few of the samples from previous task if do_sampling: # Do the uniform sampling/ only get examples from current task importance_array = np.ones([datasets[task]['train']['images'].shape[0]], dtype=np.float32) # Get the important samples from the current task imp_images, imp_labels = sample_from_dataset(datasets[task]['train'], importance_array, task_labels[task], SAMPLES_PER_CLASS) if imp_images is not None: if last_task_x is None: last_task_x = imp_images last_task_y_ = imp_labels else: last_task_x = np.concatenate((last_task_x, imp_images), axis=0) last_task_y_ = np.concatenate((last_task_y_, imp_labels), axis=0) # Delete the importance array now that you don't need it in the current run del importance_array print('\t\t\t\tEpisodic memory is saved for Task%d!'%(task)) if cross_validate_mode: if (task == model.num_tasks - 1) or MULTI_TASK: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -