Ctrl+K

epbd_bert.dnabert2_classifier package

epbd_bert.dnabert2_classifier package#

Submodules#

epbd_bert.dnabert2_classifier.configs module#

class epbd_bert.dnabert2_classifier.configs.Configs(*, n_classes: int = 690, batch_size: int = 170, num_workers: int = 32, learning_rate: float = 1e-05, weight_decay: float = 0.1, max_epochs: int = 100, best_model_monitor: str = 'val_loss', best_model_monitor_mode: str = 'min')[source]#

Bases: object

batch_size: int = 170#
best_model_monitor: str = 'val_loss'#
best_model_monitor_mode: str = 'min'#
learning_rate: float = 1e-05#
max_epochs: int = 100#
n_classes: int = 690#
num_workers: int = 32#
weight_decay: float = 0.1#

epbd_bert.dnabert2_classifier.model module#

class epbd_bert.dnabert2_classifier.model.DNABERT2Classifier(configs: Configs)[source]#

Bases: LightningModule

_summary_

Parameters:

configs (Configs) – _description_

calculate_loss(logits: Tensor, targets: Tensor) → float[source]#

_summary_

Parameters:

  • logits (torch.Tensor) – _description_

  • targets (torch.Tensor) – _description_

Returns:

_description_

Return type:

float

configure_optimizers()[source]#
Returns:

_description_

Return type:

_type_

forward(inputs)[source]#

_summary_

Parameters:

inputs (_type_) – _description_

Returns:

_description_

Return type:

_type_

on_validation_epoch_end()[source]#

_summary_

training_step(batch, batch_idx) → float[source]#

_summary_

Parameters:

  • batch (_type_) – _description_

  • batch_idx (_type_) – _description_

Returns:

_description_

Return type:

float

validation_step(batch, batch_idx) → float[source]#

_summary_

Parameters:

  • batch (_type_) – _description_

  • batch_idx (_type_) – _description_

Returns:

_description_

Return type:

float

epbd_bert.dnabert2_classifier.test module#

epbd_bert.dnabert2_classifier.train_lightning module#

Module contents#

Contents