Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

update as_batch to work correctly with multiclass labels #2

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

update as_batch to work correctly with multiclass labels #2

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
eba21a5
update as_batch to work correctly with multiclass labels
karolzak Aug 20, 2019
49c9155
added output dtype parameters to as_batch function
karolzak Aug 21, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 9 additions & 6 deletions mPyPl/keras.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
import numpy as np

@Pipe
def as_batch(flow, feature_field_name='features', label_field_name='label', batchsize=16):
def as_batch(flow, feature_field_name='features', label_field_name='label', batchsize=16, out_features_dtype=None, out_labels_dtype=None):
"""
Split input datastream into a sequence of batches suitable for keras training.
:param flow: input datastream
Expand All @@ -22,18 +22,21 @@ def as_batch(flow, feature_field_name='features', label_field_name='label', batc
# explicitly compute all fields - this is needed for all fields to be computed only once for on-demand evaluation
flds = { i : data[i] for i in (feature_field_name if isinstance(feature_field_name, list) else [feature_field_name])}
lbls = data[label_field_name] # TODO: what happens when label_field_name is a list?

if batch is None:
if isinstance(feature_field_name, list):
batch = [np.zeros((batchsize,)+flds[i].shape) for i in feature_field_name]
batch = [np.zeros((batchsize,)+flds[i].shape, dtype=flds[i].dtype if out_features_dtype is None else out_features_dtype) for i in feature_field_name]
else:
batch = np.zeros((batchsize,)+flds[feature_field_name].shape)
lbls_shape = lbls.shape if lbls is np.ndarray else (1,)
labels = np.zeros((batchsize,)+lbls_shape)
batch = np.zeros((batchsize,)+flds[feature_field_name].shape, dtype=flds[feature_field_name].dtype if out_features_dtype is None else out_features_dtype)

lbls_shape = lbls.shape if type(lbls) is np.ndarray else (1,)
out_labels_dtype = out_labels_dtype if out_labels_dtype is not None else lbls.dtype if type(lbls) is np.ndarray else None
labels = np.zeros((batchsize,)+lbls_shape, dtype=out_labels_dtype)
if isinstance(feature_field_name, list):
for j,n in enumerate(feature_field_name):
batch[j][i] = flds[n]
else:
batch[i] = flds[feature_field_name]
labels[i] = data[label_field_name]
labels[i] = lbls
yield (batch, labels)
batch = labels = None