def get2d_histogram(x, y, value_range, nbins=100, dtype=tf.dtypes.int32):
"""
Bins x, y coordinates of points onto simple square 2d histogram
Given the tensor x and y:
x: x coordinates of points
y: y coordinates of points
this operation returns a rank 2 `Tensor`
representing the indices of a histogram into which each element
of `values` would be binned. The bins are equal width and
determined by the arguments `value_range` and `nbins`.
Args:
x: Numeric `Tensor`.
y: Numeric `Tensor`.
value_range[0] lims for x
value_range[1] lims for y
nbins: Scalar `int32 Tensor`. Number of histogram bins.
dtype: dtype for returned histogram.
"""
x_range = value_range[0]
y_range = value_range[1]
histy_bins = tf.histogram_fixed_width_bins(y,
y_range,
nbins=nbins,
dtype=dtype)
H = tf.map_fn(
lambda i: tf.histogram_fixed_width(
x[histy_bins == i], x_range, nbins=nbins), tf.range(nbins))
return H # Matrix!
def scale_channel(im, c):
"""Scale the data in the channel to implement equalize."""
im = tf.cast(im[:, :, c], tf.int32)
# Compute the histogram of the image channel.
histo = tf.histogram_fixed_width(im, [0, 255], nbins=256)
# For the purposes of computing the step, filter out the nonzeros.
nonzero = tf.where(tf.not_equal(histo, 0))
nonzero_histo = tf.reshape(tf.gather(histo, nonzero), [-1])
step = (tf.reduce_sum(nonzero_histo) - nonzero_histo[-1]) // 255
def build_lut(histo, step):
# Compute the cumulative sum, shifting by step // 2
# and then normalization by step.
lut = (tf.cumsum(histo) + (step // 2)) // step
# Shift lut, prepending with 0.
lut = tf.concat([[0], lut[:-1]], 0)
# Clip the counts to be in range. This is done
# in the C code for image.point.
return tf.clip_by_value(lut, 0, 255)
# If step is zero, return the original image. Otherwise, build
# lut from the full histogram and step and then index from it.
result = tf.cond(tf.equal(step, 0),
lambda: im,
lambda: tf.gather(build_lut(histo, step), im))
return tf.cast(result, tf.uint8)
def tf_batch_histogram(values, value_range, axis, nbins=100, dtype=tf.int32, use_map=True):
"""
Computes histogram with fixed width considering batch dimensions
:param values: Numeric `Tensor` containing the values for histogram computation.
:param value_range: Shape [2] `Tensor` of same `dtype` as `values`. values <= value_range[0] will be mapped to
hist[0], values >= value_range[1] will be mapped to hist[-1].
:param axis: Number of batch dimensions. First axis to apply histogram computation to.
:param nbins: Scalar `int32 Tensor`. Number of histogram bins.
:param dtype: dtype for returned histogram, can be either tf.int32 or tf.int64.
:return: histogram with batch dimensions.
"""
# Get shape
values_shape = tf.shape(values)
batch_dim = values_shape[:axis]
rest_dim = values_shape[axis:]
num_batch = tf.reduce_prod(batch_dim)
if use_map:
values_reshaped = tf.reshape(values, tf.concat([[num_batch], rest_dim], 0))
hist = tf.map_fn(lambda x: tf.histogram_fixed_width(x, value_range, nbins=nbins, dtype=dtype), values_reshaped,
dtype=dtype, parallel_iterations=64)
else:
# Normalize
values_float = tf.cast(values, tf.float32)
value_range_float = tf.cast(value_range, tf.float32)
# Clip values
values_norm = (values_float - value_range_float[0]) / (value_range_float[1] - value_range_float[0])
values_clip1 = tf.maximum(values_norm, 0.5 / tf.cast(nbins, tf.float32))
values_clip2 = tf.minimum(values_clip1, 1.0 - 0.5 / tf.cast(nbins, tf.float32))
# Shift values
values_shift = values_clip2 + tf.reshape(tf.range(tf.cast(num_batch, tf.float32), dtype=tf.float32),
tf.concat([batch_dim, tf.ones(tf.size(rest_dim), tf.int32)], 0))
# Get histogram
hist = tf.histogram_fixed_width(values_shift, [0., tf.cast(num_batch, tf.float32)], nbins=num_batch * nbins,
dtype=dtype)
return tf.reshape(hist, tf.concat([batch_dim, [nbins]], 0))
def contrast(image, factor): """Equivalent of PIL Contrast.""" degenerate = tf.image.rgb_to_grayscale(image) # Cast before calling tf.histogram. degenerate = tf.cast(degenerate, tf.int32) # Compute the grayscale histogram, then compute the mean pixel value, # and create a constant image size of that value. Use that as the # blending degenerate target of the original image. hist = tf.histogram_fixed_width(degenerate, [0, 255], nbins=256) mean = tf.reduce_sum(tf.cast(hist, tf.float32)) / 256.0 degenerate = tf.ones_like(degenerate, dtype=tf.float32) * mean degenerate = tf.clip_by_value(degenerate, 0.0, 255.0) degenerate = tf.image.grayscale_to_rgb(tf.cast(degenerate, tf.uint8)) return blend(degenerate, image, factor)
def get_jh(x, y, value_range, nbins):
dtype = tf.dtypes.int32
x_range = value_range[0]
y_range = value_range[1]
histy_bins = tf.histogram_fixed_width_bins(y,
y_range,
nbins=nbins,
dtype=dtype)
def masking_info(tf_val):
return tf.math.equal(histy_bins, tf_val)
H = tf.map_fn(
lambda i: tf.histogram_fixed_width(
x[masking_info(i)], x_range, nbins=nbins), tf.range(nbins))
return H
def idx2csr(indices, rows, columns):
"""Convert index format meta-data to compressed sparse row format.
Args:
indices: Tensor, the linear indices for the sparse matrix.
rows: Tensor, the number of rows in the sparse matrix.
columns: Tensor, the number of columns in the sparse matrix.
Returns:
row_indices: Tensor, the row indices sorted by size.
row_offset: Tensor, the offsets for each row in the sparse matrix.
column_indices: Tensor, the column indices for each nonzero in the
matrix.
"""
# Calculate the length of each row by histogramming the indices.
row_lengths = tf.histogram_fixed_width(indices, [0, rows * columns],
nbins=rows)
row_offsets = tf.concat([[0], tf.cumsum(row_lengths)], axis=0)
row_indices = tf.argsort(row_lengths, direction="DESCENDING")
column_indices = tf.mod(indices, columns)
return row_indices, row_offsets, column_indices
def add_single_image_info(self, image_id, eval_dict):
groundtruth_boxes = eval_dict[
standard_fields.InputDataFields.groundtruth_boxes]
groundtruth_classes = eval_dict[
standard_fields.InputDataFields.groundtruth_classes]
detection_boxes = eval_dict[
standard_fields.DetectionResultFields.detection_boxes]
detection_scores = eval_dict[
standard_fields.DetectionResultFields.detection_scores]
detection_classes = eval_dict[
standard_fields.DetectionResultFields.detection_classes]
groundtruth_has_rotation = groundtruth_classes > 1
groundtruth_boxes_with_rotation = groundtruth_boxes[
groundtruth_has_rotation]
#ensure classes are both not 'dot' class, so they have a meaningful rotation value
detection_within_score = detection_scores > self._score_threshold
detection_class_has_rotation = detection_classes > 1
detection_has_rotation_and_score = tf.logical_and(
detection_within_score, detection_class_has_rotation)
detection_boxes_within_score = detection_boxes[
detection_has_rotation_and_score]
detection_classes_within_score = detection_classes[
detection_has_rotation_and_score]
gt_boxlist = box_list.BoxList(
tf.convert_to_tensor(groundtruth_boxes_with_rotation))
det_boxlist = box_list.BoxList(
tf.convert_to_tensor(detection_boxes_within_score))
detection_y_rotation_angles = eval_dict[
additional_fields.DetectionResultFields.y_rotation_angles]
groundtruth_y_rotation_angles = eval_dict[
additional_fields.GroundtruthResultFields.y_rotation_angles]
detection_y_rotation_angles_within_score = detection_y_rotation_angles[
detection_has_rotation_and_score]
for iou_threshold, assigner in self._iou_thresholds_and_assigners:
cls_targets, cls_weights, reg_targets, reg_weights, match = assigner.assign(
det_boxlist, gt_boxlist)
fg_detections = match >= 0
fg_detection_boxes = detection_boxes_within_score[fg_detections, :]
fg_matches = match[fg_detections]
fg_matches_argsort = tf.argsort(fg_matches)
fg_matches_sorted = tf.gather(fg_matches, fg_matches_argsort)
gt_match_indices, fg_match_sorted_indices_with_repeats, fg_match_sorted_indices_counts = tf.unique_with_counts(
fg_matches_sorted)
fg_match_sorted_indices_no_repeats = tf.cumsum(
tf.pad(fg_match_sorted_indices_counts, [[1, 0]]))[:-1]
fg_match_indices_no_repeats = tf.gather(
fg_matches_argsort, fg_match_sorted_indices_no_repeats)
def get_matches_and_angle_difference(fg_match_idx_tensor,
gt_match_idx_tensor):
if debug_get_matching_boxes:
gt_matching_detection_boxes = tf.gather(
groundtruth_boxes_with_rotation,
gt_match_idx_tensor,
axis=0)
fg_matching_detection_boxes = tf.gather(
fg_detection_boxes, fg_match_idx_tensor, axis=0)
pass
fg_matching_detection_y_rot_angles = tf.gather(
detection_y_rotation_angles_within_score,
fg_match_idx_tensor,
axis=0)
groundtruth_y_rotation_angles_matches = tf.gather(
groundtruth_y_rotation_angles, gt_match_idx_tensor, axis=0)
groundtruth_has_y_rot = tf.math.logical_not(
tf.math.equal(groundtruth_y_rotation_angles_matches, 0))
groundtruth_existant_y_rot_angle = groundtruth_y_rotation_angles_matches[
groundtruth_has_y_rot]
detection_existant_y_rot_angle = fg_matching_detection_y_rot_angles[
groundtruth_has_y_rot]
angle_diff = detection_existant_y_rot_angle - groundtruth_existant_y_rot_angle
angle_diff_unwrapped = tf.math.atan2(tf.math.sin(angle_diff),
tf.math.cos(angle_diff))
angle_diff_abs = tf.math.abs(angle_diff_unwrapped)
n_angle_matches = len(angle_diff)
return n_angle_matches, angle_diff_abs
num_angle_matches, abs_angle_differences = get_matches_and_angle_difference(
fg_match_indices_no_repeats, gt_match_indices)
angle_diff_sum_square = tf.reduce_sum(
tf.math.square(abs_angle_differences * 180 / np.pi))
match_angle_diff_histogram = tf.histogram_fixed_width(
abs_angle_differences * 180 / np.pi,
self._histogram_range,
nbins=self._num_angle_bins,
dtype=tf.dtypes.int32)
self.total_num_angle_matches[iou_threshold] += num_angle_matches
self.total_angle_diff_sum_squared[
iou_threshold] += angle_diff_sum_square
self.angle_histograms[iou_threshold] += match_angle_diff_histogram