def do_evaluate_unlabeled(pred_config, output_file, reuse=True):
"""Evaluate unlabled data."""
for i, dataset in enumerate(cfg.DATA.VAL):
output = output_file + '-' + dataset
if not os.path.isfile(output) or not reuse:
if i == 0:
num_tower = max(cfg.TRAIN.NUM_GPUS, 1)
graph_funcs = MultiTowerOfflinePredictor(
pred_config, list(range(num_tower))).get_predictors()
logger.info('Evaluating {} ...'.format(dataset))
dataflows = [
get_eval_dataflow(dataset, shard=k, num_shards=num_tower)
for k in range(num_tower)
]
all_results = multithread_predict_dataflow(dataflows, graph_funcs)
eval_metrics = DatasetRegistry.get(
dataset).eval_inference_results2(
all_results, output, threshold=cfg.TRAIN.CONFIDENCE)
else:
all_results = json.load(open(output, 'r'))
eval_metrics = DatasetRegistry.get(
dataset).eval_inference_results2(
all_results,
output,
threshold=cfg.TRAIN.CONFIDENCE,
metric_only=True)
with open(output + '_cocometric.json', 'w') as f:
json.dump(eval_metrics, f)
def do_evaluate(pred_config, output_file):
num_tower = max(cfg.TRAIN.NUM_GPUS, 1)
graph_funcs = MultiTowerOfflinePredictor(
pred_config, list(range(num_tower))).get_predictors()
for dataset in cfg.DATA.VAL:
logger.info("Evaluating {} ...".format(dataset))
dataflows = [
get_eval_dataflow(dataset, shard=k, num_shards=num_tower)
for k in range(num_tower)]
all_results = multithread_predict_dataflow(dataflows, graph_funcs)
output = output_file + '-' + dataset
DatasetRegistry.get(dataset).eval_inference_results(all_results, output)
def do_evaluate(pred_config, output_file, batch_size):
'''
Multi-gpu evaluation, if available
'''
num_tower = max(cfg.TRAIN.NUM_GPUS, 1)
graph_funcs = MultiTowerOfflinePredictor(pred_config, list(
range(num_tower))).get_predictors()
dataflows = [
get_eval_dataflow(batch_size, shard=k, num_shards=num_tower)
for k in range(num_tower)
]
all_results = multithread_pred_dataflow(dataflows, graph_funcs)
# df = get_eval_dataflow()
# all_results = pred_dataflow(df, lambda img: detect_batch(img, pred_func))
logger.info('Dumping evaluation results')
np.savez(output_file, **all_results)
return print_evaluation_scores(output_file)
def predict_unlabeled(model,
model_path,
nr_visualize=100,
output_dir='output_patch_samples'):
"""Predict the pseudo label information of unlabeled data."""
assert cfg.EVAL.PSEUDO_INFERENCE, 'set cfg.EVAL.PSEUDO_INFERENCE=True'
df, dataset_size = get_eval_unlabeled_dataflow(cfg.DATA.TRAIN,
return_size=True)
df.reset_state()
predcfg = PredictConfig(
model=model,
session_init=SmartInit(model_path),
input_names=['image'], # ['image', 'gt_boxes', 'gt_labels'],
output_names=[
'generate_{}_proposals/boxes'.format(
'fpn' if cfg.MODE_FPN else 'rpn'),
'generate_{}_proposals/scores'.format(
'fpn' if cfg.MODE_FPN else 'rpn'),
'fastrcnn_all_scores',
'output/boxes',
'output/scores', # score of the labels
'output/labels',
])
pred = OfflinePredictor(predcfg)
if os.path.isdir(output_dir):
if os.path.isfile(os.path.join(output_dir, 'pseudo_data.npy')):
os.remove(os.path.join(output_dir, 'pseudo_data.npy'))
if not os.path.isdir(os.path.join(output_dir, 'vis')):
os.makedirs(os.path.join(output_dir, 'vis'))
else:
shutil.rmtree(os.path.join(output_dir, 'vis'))
fs.mkdir_p(output_dir + '/vis')
else:
fs.mkdir_p(output_dir)
fs.mkdir_p(output_dir + '/vis')
logger.warning('-' * 100)
logger.warning('Write to {}'.format(output_dir))
logger.warning('-' * 100)
with tqdm.tqdm(total=nr_visualize) as pbar:
for idx, dp in itertools.islice(enumerate(df), nr_visualize):
img, img_id = dp # dp['image'], dp['img_id']
rpn_boxes, rpn_scores, all_scores, \
final_boxes, final_scores, final_labels = pred(img)
outs = {
'proposals_boxes': rpn_boxes, # (?,4)
'proposals_scores': rpn_scores, # (?,)
'boxes': final_boxes,
'scores': final_scores,
'labels': final_labels
}
ratios = [10,
10] # [top 20% as background, bottom 20% as background]
bg_ind, fg_ind = custom.find_bg_and_fg_proposals(all_scores,
ratios=ratios)
bg_viz = draw_predictions(img, rpn_boxes[bg_ind],
all_scores[bg_ind])
fg_viz = draw_predictions(img, rpn_boxes[fg_ind],
all_scores[fg_ind])
results = [
DetectionResult(*args)
for args in zip(final_boxes, final_scores, final_labels,
[None] * len(final_labels))
]
final_viz = draw_final_outputs(img, results)
viz = tpviz.stack_patches([bg_viz, fg_viz, final_viz], 2, 2)
if os.environ.get('DISPLAY', None):
tpviz.interactive_imshow(viz)
assert cv2.imwrite('{}/vis/{:03d}.png'.format(output_dir, idx),
viz)
pbar.update()
logger.info('Write {} samples to {}'.format(nr_visualize, output_dir))
## Parallel inference the whole unlabled data
pseudo_preds = collections.defaultdict(list)
num_tower = max(cfg.TRAIN.NUM_GPUS, 1)
graph_funcs = MultiTowerOfflinePredictor(predcfg, list(
range(num_tower))).get_predictors()
dataflows = [
get_eval_unlabeled_dataflow(cfg.DATA.TRAIN,
shard=k,
num_shards=num_tower)
for k in range(num_tower)
]
all_results = multithread_predict_dataflow(dataflows, graph_funcs)
for id, result in tqdm.tqdm(enumerate(all_results)):
img_id = result['image_id']
outs = {
'proposals_boxes':
result['proposal_box'].astype(np.float16), # (?,4)
'proposals_scores':
result['proposal_score'].astype(np.float16), # (?,)
# 'frcnn_all_scores': result['frcnn_score'].astype(np.float16),
'boxes': result['bbox'].astype(np.float16), # (?,4)
'scores': result['score'].astype(np.float16), # (?,)
'labels': result['category_id'].astype(np.float16) # (?,)
}
pseudo_preds[img_id] = outs
logger.warn('Writing to {}'.format(
os.path.join(output_dir, 'pseudo_data.npy')))
try:
dd.io.save(os.path.join(output_dir, 'pseudo_data.npy'), pseudo_preds)
except RuntimeError:
logger.error('Save failed. Check reasons manually...')