tfclass_predict.prediction_manager

Classes

PredictionManager

Prediction manager class. Coordinates the prediction for a single bed file.

Functions

_generate_count_vectors(predictions, sequence_indices)

Generates count vectors from prediction results.

Module Contents

tfclass_predict.prediction_manager._generate_count_vectors(predictions, sequence_indices, num_classes=NUM_CLASSES)

Generates count vectors from prediction results. :param predictions: Aggregated predictions from Predictor.predict_bed_data() :param sequence_indices: Indices of each sequence in predictions. :param num_classes: Number of classes that were predicted. :return: Count vectors and prediction dictionary.

class tfclass_predict.prediction_manager.PredictionManager(bed_file, genome_file, res_dir, bert_model, tfclass_model, tfargs=None)

Prediction manager class. Coordinates the prediction for a single bed file.

iointerface
tokenizer
bed_data
predictor
_init_BERT(bert_model)

Initalizes the BERT tokenizer.

Parameters:

bert_model – Path to BERT model directory.

_init_devices(num_threads, num_gpus, num_cpus, memory_limit)

Initializes the devices, i.e. GPU and CPU usages.

Parameters:

  • num_threads – Number of threads used.

  • num_gpus – Number of GPUs.

  • num_cpus – Number of CPUs.

  • memory_limit – Memory limit per GPU.

_init_GPU(memory_limit=None)

Initializes GPU usage and enables memory growth.

predict(subseq_length=15, batch_size=2000)

Start the prediction. :param subseq_length: Length in which a read should be split into subsequences. :param batch_size: Number of intervals that should be processed in one batch. :return: Count vectors and prediction dictionary.

save_results()

Saves the prediction results to disk.