def histogram(self, tag, values, bins, step=None):
"""Saves histogram of values.
Args:
tag: str: label for this data
values: ndarray: will be flattened by this routine
bins: number of bins in histogram, or array of bins for onp.histogram
step: int: training step
"""
if step is None:
step = self._step
else:
self._step = step
values = onp.array(values)
bins = onp.array(bins)
values = onp.reshape(values, -1)
counts, limits = onp.histogram(values, bins=bins)
# boundary logic
cum_counts = onp.cumsum(onp.greater(counts, 0, dtype=onp.int32))
start, end = onp.searchsorted(cum_counts, [0, cum_counts[-1] - 1],
side='right')
start, end = int(start), int(end) + 1
counts = (counts[start - 1:end]
if start > 0 else onp.concatenate([[0], counts[:end]]))
limits = limits[start:end + 1]
sum_sq = values.dot(values)
histo = HistogramProto(min=values.min(),
max=values.max(),
num=len(values),
sum=values.sum(),
sum_squares=sum_sq,
bucket_limit=limits.tolist(),
bucket=counts.tolist())
summary = Summary(value=[Summary.Value(tag=tag, histo=histo)])
self.add_summary(summary, step)
def log_histogram(tag, values, step, bins=1000):
"""
log_histogram
Logs the histogram of a list/vector of values.
"""
# Convert to a numpy array
values = np.array(values)
# Create histogram using numpy
counts, bin_edges = np.histogram(values, bins=bins)
# Fill fields of histogram proto
hist = HistogramProto()
hist.min = float(np.min(values))
hist.max = float(np.max(values))
hist.num = int(np.prod(values.shape))
hist.sum = float(np.sum(values))
hist.sum_squares = float(np.sum(values**2))
# Requires equal number as bins, where the first goes from -DBL_MAX to bin_edges[1]
# See https://github.com/tensorflow/tensorflow/blob/master/tensorflow/core/framework/summary.proto#L30
# Thus, we drop the start of the first bin
bin_edges = bin_edges[1:]
# Add bin edges and counts
for edge in bin_edges:
hist.bucket_limit.append(edge)
for c in counts:
hist.bucket.append(c)
return Summary(value=[Summary.Value(tag=tag, histo=hist)])
def make_histogram(values, bins=g_default_bins, max_bins=None, debug_name=''):
"""Convert values into a histogram proto using logic from histogram.cc."""
if values.size == 0:
raise ValueError(
'[make_histogram, {}] The input has no element.'.format(
debug_name))
values = values.reshape(-1)
counts, limits = np.histogram(values, bins=bins)
num_bins = len(counts)
if max_bins is not None and num_bins > max_bins:
subsampling = num_bins // max_bins
subsampling_remainder = num_bins % subsampling
if subsampling_remainder != 0:
counts = np.pad(
counts,
pad_width=[[0, subsampling - subsampling_remainder]],
mode="constant",
constant_values=0)
counts = counts.reshape(-1, subsampling).sum(axis=-1)
new_limits = np.empty((counts.size + 1, ), limits.dtype)
new_limits[:-1] = limits[:-1:subsampling]
new_limits[-1] = limits[-1]
limits = new_limits
# Find the first and the last bin defining the support of the histogram:
cum_counts = np.cumsum(np.greater(counts, 0, dtype=np.int32))
start, end = np.searchsorted(cum_counts, [0, cum_counts[-1] - 1],
side="right")
start = int(start)
end = int(end) + 1
del cum_counts
# TensorBoard only includes the right bin limits. To still have the leftmost limit
# included, we include an empty bin left.
# If start == 0, we need to add an empty one left, otherwise we can just include the bin left to the
# first nonzero-count bin:
counts = counts[start - 1:end] if start > 0 else np.concatenate(
[[0], counts[:end]])
limits = limits[start:end + 1]
if counts.size == 0 or limits.size == 0:
raise ValueError(
'[make_histogram, {}] The histogram is empty, please file a bug report.'
.format(debug_name))
sum_sq = values.dot(values)
from tensorflow import HistogramProto
return HistogramProto(min=values.min(),
max=values.max(),
num=len(values),
sum=values.sum(),
sum_squares=sum_sq,
bucket_limit=limits.tolist(),
bucket=counts.tolist())
def makeHistProto(dist: Counter, bins, keys=None) -> HistogramProto:
if keys == None:
keys = sorted(dist.keys())
hist = HistogramProto()
hist.min = -0.5
hist.max = bins - 0.5
hist.num = sum(dist.values())
hist.sum = sum(i * dist[key] for i, key in enumerate(keys))
hist.sum_squares = sum((i * dist[key])**2 for i, key in enumerate(keys))
for i in range(bins):
hist.bucket_limit.append(i + 0.5)
for key in keys:
hist.bucket.append(dist[key] * (30 / bins))
for _ in range(bins - len(keys)):
hist.bucket.append(0)
return hist
def log_vector(tag, values):
"""
log_histogram
Logs a vector of values.
"""
values = np.array(values).flatten()
# Fill fields of histogram proto
hist = HistogramProto()
hist.min = 0
hist.max = len(values) - 1
hist.num = len(values)
hist.sum = float(np.sum(np.arange(hist.num)))
hist.sum_squares = float(np.sum(np.arange(hist.num)**2))
for idx, c in enumerate(values):
hist.bucket_limit.append(idx)
hist.bucket.append(c)
return Summary(value=[Summary.Value(tag=tag, histo=hist)])