def main(_):
config = hparams_config.get_efficientdet_config(FLAGS.model_name)
config.override(FLAGS.hparams)
config.batch_size = FLAGS.batch_size
config.val_json_file = FLAGS.val_json_file
# dataset
ds = dataloader.InputReader(
FLAGS.val_file_pattern,
is_training=False,
use_fake_data=False,
max_instances_per_image=config.max_instances_per_image)(config)
# Network
model = efficientdet_keras.EfficientDetNet(config=config)
model.build((config.batch_size, None, None, 3))
model.load_weights(tf.train.latest_checkpoint(FLAGS.model_dir))
evaluator = coco_metric.EvaluationMetric(filename=config.val_json_file)
# compute stats for all batches.
for images, labels in ds:
config.nms_configs.max_nms_inputs = anchors.MAX_DETECTION_POINTS
cls_outputs, box_outputs = model(images, training=False)
detections = postprocess.generate_detections(config, cls_outputs,
box_outputs,
labels['image_scales'],
labels['source_ids'],
False)
if FLAGS.enable_tta:
images_flipped = tf.image.flip_left_right(images)
cls_outputs_flipped, box_outputs_flipped = model(images_flipped,
training=False)
detections_flipped = postprocess.generate_detections(
config, cls_outputs_flipped, box_outputs_flipped,
labels['image_scales'], labels['source_ids'], True)
for d, df in zip(detections, detections_flipped):
combined_detections = wbf.ensemble_detections(
config, tf.concat([d, df], 0))
combined_detections = tf.stack([combined_detections])
evaluator.update_state(
labels['groundtruth_data'].numpy(),
postprocess.transform_detections(
combined_detections).numpy())
else:
evaluator.update_state(
labels['groundtruth_data'].numpy(),
postprocess.transform_detections(detections).numpy())
# compute the final eval results.
metric_values = evaluator.result()
metric_dict = {}
for i, metric_value in enumerate(metric_values):
metric_dict[evaluator.metric_names[i]] = metric_value
print(metric_dict)
def test_ensemble_boxes(self):
d1 = tf.constant([1, 2, 1, 10, 1, 0.75, 1], dtype=tf.float32)
d2 = tf.constant([1, 3, 1, 10, 1, 0.75, 1], dtype=tf.float32)
d3 = tf.constant([1, 3, 1, 10, 1, 1, 2], dtype=tf.float32)
ensembled = wbf.ensemble_detections({'num_classes': 3},
tf.stack([d1, d2, d3]))
self.assertAllClose(
ensembled, [[1, 3, 1, 10, 1, 1, 2], [1, 2.5, 1, 10, 1, 0.75, 1]])
def main(_):
config = hparams_config.get_efficientdet_config(FLAGS.model_name)
config.override(FLAGS.hparams)
config.batch_size = FLAGS.batch_size
config.val_json_file = FLAGS.val_json_file
config.nms_configs.max_nms_inputs = anchors.MAX_DETECTION_POINTS
base_height, base_width = utils.parse_image_size(config['image_size'])
if FLAGS.strategy == 'tpu':
tpu_cluster_resolver = tf.distribute.cluster_resolver.TPUClusterResolver(
FLAGS.tpu, zone=FLAGS.tpu_zone, project=FLAGS.gcp_project)
tf.config.experimental_connect_to_cluster(tpu_cluster_resolver)
tf.tpu.experimental.initialize_tpu_system(tpu_cluster_resolver)
ds_strategy = tf.distribute.TPUStrategy(tpu_cluster_resolver)
logging.info('All devices: %s', tf.config.list_logical_devices('TPU'))
elif FLAGS.strategy == 'gpus':
ds_strategy = tf.distribute.MirroredStrategy()
logging.info('All devices: %s', tf.config.list_physical_devices('GPU'))
else:
if tf.config.list_physical_devices('GPU'):
ds_strategy = tf.distribute.OneDeviceStrategy('device:GPU:0')
else:
ds_strategy = tf.distribute.OneDeviceStrategy('device:CPU:0')
# in format (height, width, flip)
augmentations = []
if FLAGS.enable_tta:
for size_offset in (0, 128, 256):
for flip in (False, True):
augmentations.append((base_height + size_offset,
base_width + size_offset, flip))
else:
augmentations.append((base_height, base_width, False))
all_detections = []
all_labels = []
with ds_strategy.scope():
# Network
model = efficientdet_keras.EfficientDetNet(config=config)
model.build((config.batch_size, base_height, base_width, 3))
model.load_weights(tf.train.latest_checkpoint(FLAGS.model_dir))
first_loop = True
for height, width, flip in augmentations:
config.image_size = (height, width)
# dataset
ds = dataloader.InputReader(
FLAGS.val_file_pattern,
is_training=False,
use_fake_data=False,
max_instances_per_image=config.max_instances_per_image)(config)
# create the function once per augmentation, since it closes over the
# value of config, which gets updated with the new image size
@tf.function
def f(images, labels):
cls_outputs, box_outputs = model(images, training=False)
return postprocess.generate_detections(config, cls_outputs,
box_outputs,
labels['image_scales'],
labels['source_ids'],
flip)
# inference
for images, labels in ds:
if flip:
images = tf.image.flip_left_right(images)
detections = f(images, labels)
all_detections.append(detections)
if first_loop:
all_labels.append(labels)
first_loop = False
# collect the giant list of detections into a map from image id to
# detections
detections_per_source = dict()
for batch in all_detections:
for d in batch:
img_id = d[0][0]
if img_id.numpy() in detections_per_source:
detections_per_source[img_id.numpy()] = tf.concat(
[d, detections_per_source[img_id.numpy()]], 0)
else:
detections_per_source[img_id.numpy()] = d
# collect the groundtruth per image id
groundtruth_per_source = dict()
for batch in all_labels:
for img_id, groundtruth in zip(batch['source_ids'],
batch['groundtruth_data']):
groundtruth_per_source[img_id.numpy()] = groundtruth
# calucate the AP scores for all the images
evaluator = coco_metric.EvaluationMetric(filename=config.val_json_file)
for img_id, d in detections_per_source.items():
if FLAGS.enable_tta:
d = wbf.ensemble_detections(config, d, len(augmentations))
evaluator.update_state(
tf.stack([groundtruth_per_source[img_id]]).numpy(),
postprocess.transform_detections(tf.stack([d])).numpy())
# compute the final eval results.
if evaluator:
metrics = evaluator.result()
metric_dict = {}
for i, name in enumerate(evaluator.metric_names):
metric_dict[name] = metrics[i]
label_map = label_util.get_label_map(config.label_map)
if label_map:
for i, cid in enumerate(sorted(label_map.keys())):
name = 'AP_/%s' % label_map[cid]
metric_dict[name] = metrics[i - len(evaluator.metric_names)]
print(metric_dict)
def main(_):
config = hparams_config.get_efficientdet_config(FLAGS.model_name)
config.override(FLAGS.hparams)
config.batch_size = FLAGS.batch_size
config.val_json_file = FLAGS.val_json_file
config.nms_configs.max_nms_inputs = anchors.MAX_DETECTION_POINTS
base_height, base_width = utils.parse_image_size(config['image_size'])
# Network
model = efficientdet_keras.EfficientDetNet(config=config)
model.build((config.batch_size, base_height, base_width, 3))
model.load_weights(tf.train.latest_checkpoint(FLAGS.model_dir))
@tf.function
def f(imgs, labels, flip):
cls_outputs, box_outputs = model(imgs, training=False)
return postprocess.generate_detections(config, cls_outputs,
box_outputs,
labels['image_scales'],
labels['source_ids'], flip)
# in format (height, width, flip)
augmentations = []
if FLAGS.enable_tta:
for size_offset in (0, 128, 256):
for flip in (False, True):
augmentations.append((base_height + size_offset,
base_width + size_offset, flip))
else:
augmentations.append((base_height, base_width, False))
evaluator = None
detections_per_source = dict()
for height, width, flip in augmentations:
config.image_size = (height, width)
# dataset
ds = dataloader.InputReader(
FLAGS.val_file_pattern,
is_training=False,
use_fake_data=False,
max_instances_per_image=config.max_instances_per_image)(config)
# compute stats for all batches.
total_steps = FLAGS.eval_samples // FLAGS.batch_size
progress = tf.keras.utils.Progbar(total_steps)
for i, (images, labels) in enumerate(ds):
progress.update(i, values=None)
if i > total_steps:
break
if flip:
images = tf.image.flip_left_right(images)
detections = f(images, labels, flip)
for img_id, d in zip(labels['source_ids'], detections):
if img_id.numpy() in detections_per_source:
detections_per_source[img_id.numpy()] = tf.concat(
[d, detections_per_source[img_id.numpy()]], 0)
else:
detections_per_source[img_id.numpy()] = d
evaluator = coco_metric.EvaluationMetric(
filename=config.val_json_file)
for d in detections_per_source.values():
if FLAGS.enable_tta:
d = wbf.ensemble_detections(config, d, len(augmentations))
evaluator.update_state(
labels['groundtruth_data'].numpy(),
postprocess.transform_detections(tf.stack([d])).numpy())
# compute the final eval results.
if evaluator:
metrics = evaluator.result()
metric_dict = {}
for i, name in enumerate(evaluator.metric_names):
metric_dict[name] = metrics[i]
label_map = label_util.get_label_map(config.label_map)
if label_map:
for i, cid in enumerate(sorted(label_map.keys())):
name = 'AP_/%s' % label_map[cid]
metric_dict[name] = metrics[i - len(evaluator.metric_names)]
print(metric_dict)
def main(_):
config = hparams_config.get_efficientdet_config(FLAGS.model_name)
config.override(FLAGS.hparams)
config.batch_size = FLAGS.batch_size
config.val_json_file = FLAGS.val_json_file
config.nms_configs.max_nms_inputs = anchors.MAX_DETECTION_POINTS
base_height, base_width = utils.parse_image_size(config['image_size'])
# Network
model = efficientdet_keras.EfficientDetNet(config=config)
model.build((config.batch_size, base_height, base_width, 3))
model.load_weights(tf.train.latest_checkpoint(FLAGS.model_dir))
# in format (height, width, flip)
augmentations = []
if FLAGS.enable_tta:
for size_offset in (0, 128, 256):
for flip in (False, True):
augmentations.append((base_height + size_offset, base_width + size_offset, flip))
else:
augmentations.append((base_height, base_width, False))
detections_per_source = dict()
for height, width, flip in augmentations:
config.image_size = (height, width)
# dataset
ds = dataloader.InputReader(
FLAGS.val_file_pattern,
is_training=False,
use_fake_data=False,
max_instances_per_image=config.max_instances_per_image)(
config)
# compute stats for all batches.
for images, labels in ds:
if flip:
images = tf.image.flip_left_right(images)
cls_outputs, box_outputs = model(images, training=False)
detections = postprocess.generate_detections(config, cls_outputs,
box_outputs,
labels['image_scales'],
labels['source_ids'], flip)
for id, d in zip(labels['source_ids'], detections):
if id.numpy() in detections_per_source:
detections_per_source[id.numpy()] = tf.concat([d, detections_per_source[id.numpy()]], 0)
else:
detections_per_source[id.numpy()] = d
evaluator = coco_metric.EvaluationMetric(filename=config.val_json_file)
for d in detections_per_source.values():
if FLAGS.enable_tta:
d = wbf.ensemble_detections(config, d, len(augmentations))
evaluator.update_state(
labels['groundtruth_data'].numpy(),
postprocess.transform_detections(tf.stack([d])).numpy())
# compute the final eval results.
metric_values = evaluator.result()
metric_dict = {}
for i, metric_value in enumerate(metric_values):
metric_dict[evaluator.metric_names[i]] = metric_value
print(metric_dict)