PyTorchLearnerBackend#
- class PyTorchLearnerBackend[source]#
Bases:
Backend
Backend that uses the rastervision.pytorch_learner package to train models.
- __init__(pipeline_cfg: RVPipelineConfig, learner_cfg: LearnerConfig, tmp_dir: str)[source]#
- Parameters
pipeline_cfg (RVPipelineConfig) –
learner_cfg (LearnerConfig) –
tmp_dir (str) –
Methods
__init__
(pipeline_cfg, learner_cfg, tmp_dir)Returns a SampleWriter for this Backend.
Load the model in preparation for one or more prediction calls.
predict_scene
(scene, chip_sz[, stride])Return predictions for an entire scene using the model.
train
([source_bundle_uri])Train a model.
- __init__(pipeline_cfg: RVPipelineConfig, learner_cfg: LearnerConfig, tmp_dir: str)[source]#
- Parameters
pipeline_cfg (RVPipelineConfig) –
learner_cfg (LearnerConfig) –
tmp_dir (str) –