def _evaluate_pipeline(pipeline_name, validation_size):
meta = pd.read_csv(os.path.join(params.meta_dir, 'stage1_metadata.csv'))
meta_train = meta[meta['is_train'] == 1]
valid_ids = eval(params.valid_category_ids)
meta_train_split, meta_valid_split = train_valid_split(meta_train, validation_size, valid_category_ids=valid_ids)
data = {'input': {'meta': meta_valid_split,
'meta_valid': None,
'train_mode': False,
'target_sizes': meta_valid_split[SIZE_COLUMNS].values
},
}
y_true = read_masks(meta_valid_split[Y_COLUMNS_SCORING].values)
pipeline = PIPELINES[pipeline_name]['inference'](SOLUTION_CONFIG)
pipeline.clean_cache()
output = pipeline.transform(data)
pipeline.clean_cache()
y_pred = output['y_pred']
logger.info('Calculating IOU and IOUT Scores')
iou_score = intersection_over_union(y_true, y_pred)
logger.info('IOU score on validation is {}'.format(iou_score))
ctx.channel_send('IOU Score', 0, iou_score)
iout_score = intersection_over_union_thresholds(y_true, y_pred)
logger.info('IOUT score on validation is {}'.format(iout_score))
ctx.channel_send('IOUT Score', 0, iout_score)
def _train_pipeline(pipeline_name, validation_size):
if bool(params.overwrite) and os.path.isdir(params.experiment_dir):
shutil.rmtree(params.experiment_dir)
meta = pd.read_csv(os.path.join(params.meta_dir, 'stage1_metadata.csv'))
meta_train_split, meta_valid_split = train_valid_split(meta, validation_size)
data = {'input': {'meta': meta_train_split,
'meta_valid': meta_valid_split,
'train_mode': True,
'target_sizes': meta_train_split[SIZE_COLUMNS].values
},
}
pipeline = PIPELINES[pipeline_name]['train'](SOLUTION_CONFIG)
pipeline.fit_transform(data)