def test_postprocess_global(self):
"""Test the postprocess with global nms."""
tf.random.set_seed(1111)
cls_outputs = {
1: tf.random.normal([2, 4, 4, 2]),
2: tf.random.normal([2, 2, 2, 2])
}
box_outputs = {
1: tf.random.normal([2, 4, 4, 4]),
2: tf.random.normal([2, 2, 2, 4])
}
cls_outputs_list = [cls_outputs[1], cls_outputs[2]]
box_outputs_list = [box_outputs[1], box_outputs[2]]
scales = [1.0, 2.0]
self.params['max_detection_points'] = 10
boxes, scores, classes, valid_len = postprocess.postprocess_global(
self.params, cls_outputs_list, box_outputs_list, scales)
self.assertAllClose(valid_len, [2, 2])
self.params['disable_pyfun'] = True
score_thresh = 0.5
self.params['batch_size'] = len(scales)
max_output_size = self.params['nms_configs']['max_output_size']
legacy_detections = inference.det_post_process(self.params,
cls_outputs,
box_outputs, scales,
score_thresh,
max_output_size)
legacy_boxes = legacy_detections[:, :, 1:5]
legacy_scores = legacy_detections[:, :, 5]
legacy_classes = legacy_detections[:, :, 6]
self.assertAllClose(boxes, legacy_boxes)
self.assertAllClose(scores, legacy_scores)
self.assertAllClose(classes, legacy_classes)
def _postprocess(self, cls_outputs, box_outputs, scales, mode='global'):
"""Postprocess class and box predictions."""
if not mode:
return cls_outputs, box_outputs
if mode == 'global':
return postprocess.postprocess_global(self.config.as_dict(),
cls_outputs, box_outputs,
scales)
if mode == 'per_class':
return postprocess.postprocess_per_class(self.config.as_dict(),
cls_outputs, box_outputs,
scales)
if mode == 'combined':
return postprocess.postprocess_combined(self.config.as_dict(),
cls_outputs, box_outputs,
scales)
if mode == 'tflite':
if scales is not None:
# pre_mode should be None for TFLite.
raise ValueError(
'scales not supported for TFLite post-processing')
return postprocess.postprocess_tflite(self.config.as_dict(),
cls_outputs, box_outputs)
raise ValueError('Unsupported postprocess mode {}'.format(mode))
def _postprocess(self, cls_outputs, box_outputs, scales, mode='global'):
if not mode:
return cls_outputs, box_outputs
if mode == 'global':
return postprocess.postprocess_global(self.config.as_dict(), cls_outputs,
box_outputs, scales)
if mode == 'per_class':
return postprocess.postprocess_per_class(self.config.as_dict(),
cls_outputs, box_outputs, scales)
raise ValueError('Unsupported postprocess mode {}'.format(mode))
def _postprocess(self, cls_outputs, box_outputs, scales, mode='global'):
if not mode:
return cls_outputs, box_outputs
# TODO(tanmingxing): remove this cast once FP16 works postprocessing.
cls_outputs = [tf.cast(i, tf.float32) for i in cls_outputs]
box_outputs = [tf.cast(i, tf.float32) for i in box_outputs]
if mode == 'global':
return postprocess.postprocess_global(self.config.as_dict(), cls_outputs,
box_outputs, scales)
if mode == 'per_class':
return postprocess.postprocess_per_class(self.config.as_dict(),
cls_outputs, box_outputs, scales)
raise ValueError('Unsupported postprocess mode {}'.format(mode))
def det_post_process(
params: Dict[Any, Any],
cls_outputs: Dict[int, tf.Tensor],
box_outputs: Dict[int, tf.Tensor],
scales: List[float],
):
"""Post preprocessing the box/class predictions.
Args:
params: a parameter dictionary that includes `min_level`, `max_level`,
`batch_size`, and `num_classes`.
cls_outputs: an OrderDict with keys representing levels and values
representing logits in [batch_size, height, width, num_anchors].
box_outputs: an OrderDict with keys representing levels and values
representing box regression targets in [batch_size, height, width,
num_anchors * 4].
scales: a list of float values indicating image scale.
Returns:
detections_batch: a batch of detection results. Each detection is a tensor
with each row as [image_id, ymin, xmin, ymax, xmax, score, class].
"""
if params.get("combined_nms", None):
# Use combined version for dynamic batch size.
nms_boxes, nms_scores, nms_classes, _ = postprocess.postprocess_combined(
params, cls_outputs, box_outputs, scales)
else:
nms_boxes, nms_scores, nms_classes, _ = postprocess.postprocess_global(
params, cls_outputs, box_outputs, scales)
batch_size = tf.shape(cls_outputs[params["min_level"]])[0]
img_ids = tf.expand_dims(
tf.cast(tf.range(0, batch_size), nms_scores.dtype), -1)
detections = [
img_ids * tf.ones_like(nms_scores),
nms_boxes[:, :, 0],
nms_boxes[:, :, 1],
nms_boxes[:, :, 2],
nms_boxes[:, :, 3],
nms_scores,
nms_classes,
]
return tf.stack(detections, axis=-1, name="detections")
def test_postprocess_global(self):
"""Test the postprocess with global nms."""
tf.random.set_seed(1111)
cls_outputs = {
1: tf.random.normal([2, 4, 4, 2]),
2: tf.random.normal([2, 2, 2, 2])
}
box_outputs = {
1: tf.random.normal([2, 4, 4, 4]),
2: tf.random.normal([2, 2, 2, 4])
}
cls_outputs_list = [cls_outputs[1], cls_outputs[2]]
box_outputs_list = [box_outputs[1], box_outputs[2]]
scales = [1.0, 2.0]
self.params['max_detection_points'] = 10
_, scores, classes, valid_len = postprocess.postprocess_global(
self.params, cls_outputs_list, box_outputs_list, scales)
self.assertAllClose(valid_len, [2, 2])
self.assertAllClose(classes.numpy(), [[2., 1.], [1., 2.]])
self.assertAllClose(scores.numpy(),
[[0.90157586, 0.88812476], [0.88454413, 0.8158828]])
def _postprocess(self, cls_outputs, box_outputs, scales, mode='global'):
"""Postprocess class and box predictions."""
if not mode:
return cls_outputs, box_outputs
# TODO(tanmingxing): remove this cast once FP16 works postprocessing.
cls_outputs = [tf.cast(i, tf.float32) for i in cls_outputs]
box_outputs = [tf.cast(i, tf.float32) for i in box_outputs]
if mode == 'global':
return postprocess.postprocess_global(self.config.as_dict(), cls_outputs,
box_outputs, scales)
if mode == 'per_class':
return postprocess.postprocess_per_class(self.config.as_dict(),
cls_outputs, box_outputs, scales)
if mode == 'tflite':
if scales is not None:
# pre_mode should be None for TFLite.
raise ValueError('scales not supported for TFLite post-processing')
return postprocess.postprocess_tflite(self.config.as_dict(), cls_outputs,
box_outputs)
raise ValueError('Unsupported postprocess mode {}'.format(mode))
