def histo_summary(self, tag, values, step, bins=1000):
"""Log a histogram of the tensor of values."""
# Create a histogram using numpy
counts, bin_edges = np.histogram(values, bins=bins)
# Fill the fields of the histogram proto
hist = tf.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))
# 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)
# Create and write Summary
summary = tf.Summary(value=[tf.Summary.Value(tag=tag, histo=hist)])
self.writer.add_summary(summary, step)
def histogram_summary(self, tag, values, step, bins=1000):
if self.use_tensorboard:
"""
Logs the histogram of a list/vector of values.
From: https://gist.github.com/gyglim/1f8dfb1b5c82627ae3efcfbbadb9f514
"""
# Create histogram using numpy
counts, bin_edges = np.histogram(values, bins=bins)
# Fill fields of histogram proto
hist = tf.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
# Therefore 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)
# Create and write Summary
summary = tf.Summary(value=[tf.Summary.Value(tag=tag, histo=hist)])
self.writer.add_summary(summary, step)
def get_histogram(values):
hist = tf_v1.HistogramProto()
# Fill attributes in the histogram Proto
counts, bin_edges = np.histogram(values)
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))
hist.bucket_limit = bin_edges[1:]
hist.bucket = counts
return hist
def make_tf_summary_histogram(values, num_bins=10):
"""Constructs a tf Summary of type histogram from a np array of values.
Args:
values: list or np.array.
num_bins: int. Number of histogram bins.
Returns:
tf.HistogramProto.
"""
values = np.reshape(values, [-1])
counts, limits = np.histogram(values, bins=num_bins)
return tf.HistogramProto(min=np.amin(values),
max=np.amax(values),
num=values.size,
sum=np.sum(values),
sum_squares=np.sum(values**2),
bucket_limit=limits.tolist()[1:],
bucket=counts.tolist())
def make_histogram_proto(data, bins_count=None):
# number of elements in the array
elem_count = np.prod(data.shape)
# Make sure the number of bins is defined and
# doesn't exceed the nume of element
if bins_count is None:
bins_count = elem_count
else:
bins_count = np.min([bins_count, elem_count]).astype(np.int)
# compute histogram using numpy
occurrences, bin_edges = np.histogram(data, bins=bins_count)
return tf.HistogramProto(
min=data.min().astype(np.float),
max=data.min().astype(np.float),
num=elem_count.astype(np.int),
sum=np.sum(data).astype(np.float),
sum_squares=np.sum([datum * datum for datum in data]).astype(np.float),
bucket_limit=bin_edges[1:].tolist(),
bucket=occurrences.tolist())