Python源码示例：errorcounter.ComputeErrorRates()
示例1
def SoftmaxEval(self, sess, model, num_steps):
"""Evaluate a model in softmax mode.
Adds char, word recall and sequence error rate events to the sw summary
writer, and returns them as well
TODO(rays) Add LogisticEval.
Args:
sess: A tensor flow Session.
model: The model to run in the session. Requires a VGSLImageModel or any
other class that has a using_ctc attribute and a RunAStep(sess) method
that reurns a softmax result with corresponding labels.
num_steps: Number of steps to evaluate for.
Returns:
ErrorRates named tuple.
Raises:
ValueError: If an unsupported number of dimensions is used.
"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# Run the requested number of evaluation steps, gathering the outputs of the
# softmax and the true labels of the evaluation examples.
total_label_counts = ec.ErrorCounts(0, 0, 0, 0)
total_word_counts = ec.ErrorCounts(0, 0, 0, 0)
sequence_errors = 0
for _ in xrange(num_steps):
softmax_result, labels = model.RunAStep(sess)
# Collapse softmax to same shape as labels.
predictions = softmax_result.argmax(axis=-1)
# Exclude batch from num_dims.
num_dims = len(predictions.shape) - 1
batch_size = predictions.shape[0]
null_label = softmax_result.shape[-1] - 1
for b in xrange(batch_size):
if num_dims == 2:
# TODO(rays) Support 2-d data.
raise ValueError('2-d label data not supported yet!')
else:
if num_dims == 1:
pred_batch = predictions[b, :]
labels_batch = labels[b, :]
else:
pred_batch = [predictions[b]]
labels_batch = [labels[b]]
text = self.StringFromCTC(pred_batch, model.using_ctc, null_label)
truth = self.StringFromCTC(labels_batch, False, null_label)
# Note that recall_errs is false negatives (fn) aka drops/deletions.
# Actual recall would be 1-fn/truth_words.
# Likewise precision_errs is false positives (fp) aka adds/insertions.
# Actual precision would be 1-fp/ocr_words.
total_word_counts = ec.AddErrors(total_word_counts,
ec.CountWordErrors(text, truth))
total_label_counts = ec.AddErrors(total_label_counts,
ec.CountErrors(text, truth))
if text != truth:
sequence_errors += 1
coord.request_stop()
coord.join(threads)
return ec.ComputeErrorRates(total_label_counts, total_word_counts,
sequence_errors, num_steps * batch_size)
示例2
def SoftmaxEval(self, sess, model, num_steps):
"""Evaluate a model in softmax mode.
Adds char, word recall and sequence error rate events to the sw summary
writer, and returns them as well
TODO(rays) Add LogisticEval.
Args:
sess: A tensor flow Session.
model: The model to run in the session. Requires a VGSLImageModel or any
other class that has a using_ctc attribute and a RunAStep(sess) method
that reurns a softmax result with corresponding labels.
num_steps: Number of steps to evaluate for.
Returns:
ErrorRates named tuple.
Raises:
ValueError: If an unsupported number of dimensions is used.
"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# Run the requested number of evaluation steps, gathering the outputs of the
# softmax and the true labels of the evaluation examples.
total_label_counts = ec.ErrorCounts(0, 0, 0, 0)
total_word_counts = ec.ErrorCounts(0, 0, 0, 0)
sequence_errors = 0
for _ in xrange(num_steps):
softmax_result, labels = model.RunAStep(sess)
# Collapse softmax to same shape as labels.
predictions = softmax_result.argmax(axis=-1)
# Exclude batch from num_dims.
num_dims = len(predictions.shape) - 1
batch_size = predictions.shape[0]
null_label = softmax_result.shape[-1] - 1
for b in xrange(batch_size):
if num_dims == 2:
# TODO(rays) Support 2-d data.
raise ValueError('2-d label data not supported yet!')
else:
if num_dims == 1:
pred_batch = predictions[b, :]
labels_batch = labels[b, :]
else:
pred_batch = [predictions[b]]
labels_batch = [labels[b]]
text = self.StringFromCTC(pred_batch, model.using_ctc, null_label)
truth = self.StringFromCTC(labels_batch, False, null_label)
# Note that recall_errs is false negatives (fn) aka drops/deletions.
# Actual recall would be 1-fn/truth_words.
# Likewise precision_errs is false positives (fp) aka adds/insertions.
# Actual precision would be 1-fp/ocr_words.
total_word_counts = ec.AddErrors(total_word_counts,
ec.CountWordErrors(text, truth))
total_label_counts = ec.AddErrors(total_label_counts,
ec.CountErrors(text, truth))
if text != truth:
sequence_errors += 1
coord.request_stop()
coord.join(threads)
return ec.ComputeErrorRates(total_label_counts, total_word_counts,
sequence_errors, num_steps * batch_size)
示例3
def SoftmaxEval(self, sess, model, num_steps):
"""Evaluate a model in softmax mode.
Adds char, word recall and sequence error rate events to the sw summary
writer, and returns them as well
TODO(rays) Add LogisticEval.
Args:
sess: A tensor flow Session.
model: The model to run in the session. Requires a VGSLImageModel or any
other class that has a using_ctc attribute and a RunAStep(sess) method
that reurns a softmax result with corresponding labels.
num_steps: Number of steps to evaluate for.
Returns:
ErrorRates named tuple.
Raises:
ValueError: If an unsupported number of dimensions is used.
"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# Run the requested number of evaluation steps, gathering the outputs of the
# softmax and the true labels of the evaluation examples.
total_label_counts = ec.ErrorCounts(0, 0, 0, 0)
total_word_counts = ec.ErrorCounts(0, 0, 0, 0)
sequence_errors = 0
for _ in xrange(num_steps):
softmax_result, labels = model.RunAStep(sess)
# Collapse softmax to same shape as labels.
predictions = softmax_result.argmax(axis=-1)
# Exclude batch from num_dims.
num_dims = len(predictions.shape) - 1
batch_size = predictions.shape[0]
null_label = softmax_result.shape[-1] - 1
for b in xrange(batch_size):
if num_dims == 2:
# TODO(rays) Support 2-d data.
raise ValueError('2-d label data not supported yet!')
else:
if num_dims == 1:
pred_batch = predictions[b, :]
labels_batch = labels[b, :]
else:
pred_batch = [predictions[b]]
labels_batch = [labels[b]]
text = self.StringFromCTC(pred_batch, model.using_ctc, null_label)
truth = self.StringFromCTC(labels_batch, False, null_label)
# Note that recall_errs is false negatives (fn) aka drops/deletions.
# Actual recall would be 1-fn/truth_words.
# Likewise precision_errs is false positives (fp) aka adds/insertions.
# Actual precision would be 1-fp/ocr_words.
total_word_counts = ec.AddErrors(total_word_counts,
ec.CountWordErrors(text, truth))
total_label_counts = ec.AddErrors(total_label_counts,
ec.CountErrors(text, truth))
if text != truth:
sequence_errors += 1
coord.request_stop()
coord.join(threads)
return ec.ComputeErrorRates(total_label_counts, total_word_counts,
sequence_errors, num_steps * batch_size)
示例4
def SoftmaxEval(self, sess, model, num_steps):
"""Evaluate a model in softmax mode.
Adds char, word recall and sequence error rate events to the sw summary
writer, and returns them as well
TODO(rays) Add LogisticEval.
Args:
sess: A tensor flow Session.
model: The model to run in the session. Requires a VGSLImageModel or any
other class that has a using_ctc attribute and a RunAStep(sess) method
that reurns a softmax result with corresponding labels.
num_steps: Number of steps to evaluate for.
Returns:
ErrorRates named tuple.
Raises:
ValueError: If an unsupported number of dimensions is used.
"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# Run the requested number of evaluation steps, gathering the outputs of the
# softmax and the true labels of the evaluation examples.
total_label_counts = ec.ErrorCounts(0, 0, 0, 0)
total_word_counts = ec.ErrorCounts(0, 0, 0, 0)
sequence_errors = 0
for _ in xrange(num_steps):
softmax_result, labels = model.RunAStep(sess)
# Collapse softmax to same shape as labels.
predictions = softmax_result.argmax(axis=-1)
# Exclude batch from num_dims.
num_dims = len(predictions.shape) - 1
batch_size = predictions.shape[0]
null_label = softmax_result.shape[-1] - 1
for b in xrange(batch_size):
if num_dims == 2:
# TODO(rays) Support 2-d data.
raise ValueError('2-d label data not supported yet!')
else:
if num_dims == 1:
pred_batch = predictions[b, :]
labels_batch = labels[b, :]
else:
pred_batch = [predictions[b]]
labels_batch = [labels[b]]
text = self.StringFromCTC(pred_batch, model.using_ctc, null_label)
truth = self.StringFromCTC(labels_batch, False, null_label)
# Note that recall_errs is false negatives (fn) aka drops/deletions.
# Actual recall would be 1-fn/truth_words.
# Likewise precision_errs is false positives (fp) aka adds/insertions.
# Actual precision would be 1-fp/ocr_words.
total_word_counts = ec.AddErrors(total_word_counts,
ec.CountWordErrors(text, truth))
total_label_counts = ec.AddErrors(total_label_counts,
ec.CountErrors(text, truth))
if text != truth:
sequence_errors += 1
coord.request_stop()
coord.join(threads)
return ec.ComputeErrorRates(total_label_counts, total_word_counts,
sequence_errors, num_steps * batch_size)
示例5
def SoftmaxEval(self, sess, model, num_steps):
"""Evaluate a model in softmax mode.
Adds char, word recall and sequence error rate events to the sw summary
writer, and returns them as well
TODO(rays) Add LogisticEval.
Args:
sess: A tensor flow Session.
model: The model to run in the session. Requires a VGSLImageModel or any
other class that has a using_ctc attribute and a RunAStep(sess) method
that reurns a softmax result with corresponding labels.
num_steps: Number of steps to evaluate for.
Returns:
ErrorRates named tuple.
Raises:
ValueError: If an unsupported number of dimensions is used.
"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# Run the requested number of evaluation steps, gathering the outputs of the
# softmax and the true labels of the evaluation examples.
total_label_counts = ec.ErrorCounts(0, 0, 0, 0)
total_word_counts = ec.ErrorCounts(0, 0, 0, 0)
sequence_errors = 0
for _ in xrange(num_steps):
softmax_result, labels = model.RunAStep(sess)
# Collapse softmax to same shape as labels.
predictions = softmax_result.argmax(axis=-1)
# Exclude batch from num_dims.
num_dims = len(predictions.shape) - 1
batch_size = predictions.shape[0]
null_label = softmax_result.shape[-1] - 1
for b in xrange(batch_size):
if num_dims == 2:
# TODO(rays) Support 2-d data.
raise ValueError('2-d label data not supported yet!')
else:
if num_dims == 1:
pred_batch = predictions[b, :]
labels_batch = labels[b, :]
else:
pred_batch = [predictions[b]]
labels_batch = [labels[b]]
text = self.StringFromCTC(pred_batch, model.using_ctc, null_label)
truth = self.StringFromCTC(labels_batch, False, null_label)
# Note that recall_errs is false negatives (fn) aka drops/deletions.
# Actual recall would be 1-fn/truth_words.
# Likewise precision_errs is false positives (fp) aka adds/insertions.
# Actual precision would be 1-fp/ocr_words.
total_word_counts = ec.AddErrors(total_word_counts,
ec.CountWordErrors(text, truth))
total_label_counts = ec.AddErrors(total_label_counts,
ec.CountErrors(text, truth))
if text != truth:
sequence_errors += 1
coord.request_stop()
coord.join(threads)
return ec.ComputeErrorRates(total_label_counts, total_word_counts,
sequence_errors, num_steps * batch_size)
示例6
def SoftmaxEval(self, sess, model, num_steps):
"""Evaluate a model in softmax mode.
Adds char, word recall and sequence error rate events to the sw summary
writer, and returns them as well
TODO(rays) Add LogisticEval.
Args:
sess: A tensor flow Session.
model: The model to run in the session. Requires a VGSLImageModel or any
other class that has a using_ctc attribute and a RunAStep(sess) method
that reurns a softmax result with corresponding labels.
num_steps: Number of steps to evaluate for.
Returns:
ErrorRates named tuple.
Raises:
ValueError: If an unsupported number of dimensions is used.
"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# Run the requested number of evaluation steps, gathering the outputs of the
# softmax and the true labels of the evaluation examples.
total_label_counts = ec.ErrorCounts(0, 0, 0, 0)
total_word_counts = ec.ErrorCounts(0, 0, 0, 0)
sequence_errors = 0
for _ in xrange(num_steps):
softmax_result, labels = model.RunAStep(sess)
# Collapse softmax to same shape as labels.
predictions = softmax_result.argmax(axis=-1)
# Exclude batch from num_dims.
num_dims = len(predictions.shape) - 1
batch_size = predictions.shape[0]
null_label = softmax_result.shape[-1] - 1
for b in xrange(batch_size):
if num_dims == 2:
# TODO(rays) Support 2-d data.
raise ValueError('2-d label data not supported yet!')
else:
if num_dims == 1:
pred_batch = predictions[b, :]
labels_batch = labels[b, :]
else:
pred_batch = [predictions[b]]
labels_batch = [labels[b]]
text = self.StringFromCTC(pred_batch, model.using_ctc, null_label)
truth = self.StringFromCTC(labels_batch, False, null_label)
# Note that recall_errs is false negatives (fn) aka drops/deletions.
# Actual recall would be 1-fn/truth_words.
# Likewise precision_errs is false positives (fp) aka adds/insertions.
# Actual precision would be 1-fp/ocr_words.
total_word_counts = ec.AddErrors(total_word_counts,
ec.CountWordErrors(text, truth))
total_label_counts = ec.AddErrors(total_label_counts,
ec.CountErrors(text, truth))
if text != truth:
sequence_errors += 1
coord.request_stop()
coord.join(threads)
return ec.ComputeErrorRates(total_label_counts, total_word_counts,
sequence_errors, num_steps * batch_size)
示例7
def SoftmaxEval(self, sess, model, num_steps):
"""Evaluate a model in softmax mode.
Adds char, word recall and sequence error rate events to the sw summary
writer, and returns them as well
TODO(rays) Add LogisticEval.
Args:
sess: A tensor flow Session.
model: The model to run in the session. Requires a VGSLImageModel or any
other class that has a using_ctc attribute and a RunAStep(sess) method
that reurns a softmax result with corresponding labels.
num_steps: Number of steps to evaluate for.
Returns:
ErrorRates named tuple.
Raises:
ValueError: If an unsupported number of dimensions is used.
"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# Run the requested number of evaluation steps, gathering the outputs of the
# softmax and the true labels of the evaluation examples.
total_label_counts = ec.ErrorCounts(0, 0, 0, 0)
total_word_counts = ec.ErrorCounts(0, 0, 0, 0)
sequence_errors = 0
for _ in xrange(num_steps):
softmax_result, labels = model.RunAStep(sess)
# Collapse softmax to same shape as labels.
predictions = softmax_result.argmax(axis=-1)
# Exclude batch from num_dims.
num_dims = len(predictions.shape) - 1
batch_size = predictions.shape[0]
null_label = softmax_result.shape[-1] - 1
for b in xrange(batch_size):
if num_dims == 2:
# TODO(rays) Support 2-d data.
raise ValueError('2-d label data not supported yet!')
else:
if num_dims == 1:
pred_batch = predictions[b, :]
labels_batch = labels[b, :]
else:
pred_batch = [predictions[b]]
labels_batch = [labels[b]]
text = self.StringFromCTC(pred_batch, model.using_ctc, null_label)
truth = self.StringFromCTC(labels_batch, False, null_label)
# Note that recall_errs is false negatives (fn) aka drops/deletions.
# Actual recall would be 1-fn/truth_words.
# Likewise precision_errs is false positives (fp) aka adds/insertions.
# Actual precision would be 1-fp/ocr_words.
total_word_counts = ec.AddErrors(total_word_counts,
ec.CountWordErrors(text, truth))
total_label_counts = ec.AddErrors(total_label_counts,
ec.CountErrors(text, truth))
if text != truth:
sequence_errors += 1
coord.request_stop()
coord.join(threads)
return ec.ComputeErrorRates(total_label_counts, total_word_counts,
sequence_errors, num_steps * batch_size)
示例8
def SoftmaxEval(self, sess, model, num_steps):
"""Evaluate a model in softmax mode.
Adds char, word recall and sequence error rate events to the sw summary
writer, and returns them as well
TODO(rays) Add LogisticEval.
Args:
sess: A tensor flow Session.
model: The model to run in the session. Requires a VGSLImageModel or any
other class that has a using_ctc attribute and a RunAStep(sess) method
that reurns a softmax result with corresponding labels.
num_steps: Number of steps to evaluate for.
Returns:
ErrorRates named tuple.
Raises:
ValueError: If an unsupported number of dimensions is used.
"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# Run the requested number of evaluation steps, gathering the outputs of the
# softmax and the true labels of the evaluation examples.
total_label_counts = ec.ErrorCounts(0, 0, 0, 0)
total_word_counts = ec.ErrorCounts(0, 0, 0, 0)
sequence_errors = 0
for _ in xrange(num_steps):
softmax_result, labels = model.RunAStep(sess)
# Collapse softmax to same shape as labels.
predictions = softmax_result.argmax(axis=-1)
# Exclude batch from num_dims.
num_dims = len(predictions.shape) - 1
batch_size = predictions.shape[0]
null_label = softmax_result.shape[-1] - 1
for b in xrange(batch_size):
if num_dims == 2:
# TODO(rays) Support 2-d data.
raise ValueError('2-d label data not supported yet!')
else:
if num_dims == 1:
pred_batch = predictions[b, :]
labels_batch = labels[b, :]
else:
pred_batch = [predictions[b]]
labels_batch = [labels[b]]
text = self.StringFromCTC(pred_batch, model.using_ctc, null_label)
truth = self.StringFromCTC(labels_batch, False, null_label)
# Note that recall_errs is false negatives (fn) aka drops/deletions.
# Actual recall would be 1-fn/truth_words.
# Likewise precision_errs is false positives (fp) aka adds/insertions.
# Actual precision would be 1-fp/ocr_words.
total_word_counts = ec.AddErrors(total_word_counts,
ec.CountWordErrors(text, truth))
total_label_counts = ec.AddErrors(total_label_counts,
ec.CountErrors(text, truth))
if text != truth:
sequence_errors += 1
coord.request_stop()
coord.join(threads)
return ec.ComputeErrorRates(total_label_counts, total_word_counts,
sequence_errors, num_steps * batch_size)
示例9
def SoftmaxEval(self, sess, model, num_steps):
"""Evaluate a model in softmax mode.
Adds char, word recall and sequence error rate events to the sw summary
writer, and returns them as well
TODO(rays) Add LogisticEval.
Args:
sess: A tensor flow Session.
model: The model to run in the session. Requires a VGSLImageModel or any
other class that has a using_ctc attribute and a RunAStep(sess) method
that reurns a softmax result with corresponding labels.
num_steps: Number of steps to evaluate for.
Returns:
ErrorRates named tuple.
Raises:
ValueError: If an unsupported number of dimensions is used.
"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# Run the requested number of evaluation steps, gathering the outputs of the
# softmax and the true labels of the evaluation examples.
total_label_counts = ec.ErrorCounts(0, 0, 0, 0)
total_word_counts = ec.ErrorCounts(0, 0, 0, 0)
sequence_errors = 0
for _ in xrange(num_steps):
softmax_result, labels = model.RunAStep(sess)
# Collapse softmax to same shape as labels.
predictions = softmax_result.argmax(axis=-1)
# Exclude batch from num_dims.
num_dims = len(predictions.shape) - 1
batch_size = predictions.shape[0]
null_label = softmax_result.shape[-1] - 1
for b in xrange(batch_size):
if num_dims == 2:
# TODO(rays) Support 2-d data.
raise ValueError('2-d label data not supported yet!')
else:
if num_dims == 1:
pred_batch = predictions[b, :]
labels_batch = labels[b, :]
else:
pred_batch = [predictions[b]]
labels_batch = [labels[b]]
text = self.StringFromCTC(pred_batch, model.using_ctc, null_label)
truth = self.StringFromCTC(labels_batch, False, null_label)
# Note that recall_errs is false negatives (fn) aka drops/deletions.
# Actual recall would be 1-fn/truth_words.
# Likewise precision_errs is false positives (fp) aka adds/insertions.
# Actual precision would be 1-fp/ocr_words.
total_word_counts = ec.AddErrors(total_word_counts,
ec.CountWordErrors(text, truth))
total_label_counts = ec.AddErrors(total_label_counts,
ec.CountErrors(text, truth))
if text != truth:
sequence_errors += 1
coord.request_stop()
coord.join(threads)
return ec.ComputeErrorRates(total_label_counts, total_word_counts,
sequence_errors, num_steps * batch_size)
示例10
def SoftmaxEval(self, sess, model, num_steps):
"""Evaluate a model in softmax mode.
Adds char, word recall and sequence error rate events to the sw summary
writer, and returns them as well
TODO(rays) Add LogisticEval.
Args:
sess: A tensor flow Session.
model: The model to run in the session. Requires a VGSLImageModel or any
other class that has a using_ctc attribute and a RunAStep(sess) method
that reurns a softmax result with corresponding labels.
num_steps: Number of steps to evaluate for.
Returns:
ErrorRates named tuple.
Raises:
ValueError: If an unsupported number of dimensions is used.
"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# Run the requested number of evaluation steps, gathering the outputs of the
# softmax and the true labels of the evaluation examples.
total_label_counts = ec.ErrorCounts(0, 0, 0, 0)
total_word_counts = ec.ErrorCounts(0, 0, 0, 0)
sequence_errors = 0
for _ in xrange(num_steps):
softmax_result, labels = model.RunAStep(sess)
# Collapse softmax to same shape as labels.
predictions = softmax_result.argmax(axis=-1)
# Exclude batch from num_dims.
num_dims = len(predictions.shape) - 1
batch_size = predictions.shape[0]
null_label = softmax_result.shape[-1] - 1
for b in xrange(batch_size):
if num_dims == 2:
# TODO(rays) Support 2-d data.
raise ValueError('2-d label data not supported yet!')
else:
if num_dims == 1:
pred_batch = predictions[b, :]
labels_batch = labels[b, :]
else:
pred_batch = [predictions[b]]
labels_batch = [labels[b]]
text = self.StringFromCTC(pred_batch, model.using_ctc, null_label)
truth = self.StringFromCTC(labels_batch, False, null_label)
# Note that recall_errs is false negatives (fn) aka drops/deletions.
# Actual recall would be 1-fn/truth_words.
# Likewise precision_errs is false positives (fp) aka adds/insertions.
# Actual precision would be 1-fp/ocr_words.
total_word_counts = ec.AddErrors(total_word_counts,
ec.CountWordErrors(text, truth))
total_label_counts = ec.AddErrors(total_label_counts,
ec.CountErrors(text, truth))
if text != truth:
sequence_errors += 1
coord.request_stop()
coord.join(threads)
return ec.ComputeErrorRates(total_label_counts, total_word_counts,
sequence_errors, num_steps * batch_size)
示例11
def SoftmaxEval(self, sess, model, num_steps):
"""Evaluate a model in softmax mode.
Adds char, word recall and sequence error rate events to the sw summary
writer, and returns them as well
TODO(rays) Add LogisticEval.
Args:
sess: A tensor flow Session.
model: The model to run in the session. Requires a VGSLImageModel or any
other class that has a using_ctc attribute and a RunAStep(sess) method
that reurns a softmax result with corresponding labels.
num_steps: Number of steps to evaluate for.
Returns:
ErrorRates named tuple.
Raises:
ValueError: If an unsupported number of dimensions is used.
"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# Run the requested number of evaluation steps, gathering the outputs of the
# softmax and the true labels of the evaluation examples.
total_label_counts = ec.ErrorCounts(0, 0, 0, 0)
total_word_counts = ec.ErrorCounts(0, 0, 0, 0)
sequence_errors = 0
for _ in xrange(num_steps):
softmax_result, labels = model.RunAStep(sess)
# Collapse softmax to same shape as labels.
predictions = softmax_result.argmax(axis=-1)
# Exclude batch from num_dims.
num_dims = len(predictions.shape) - 1
batch_size = predictions.shape[0]
null_label = softmax_result.shape[-1] - 1
for b in xrange(batch_size):
if num_dims == 2:
# TODO(rays) Support 2-d data.
raise ValueError('2-d label data not supported yet!')
else:
if num_dims == 1:
pred_batch = predictions[b, :]
labels_batch = labels[b, :]
else:
pred_batch = [predictions[b]]
labels_batch = [labels[b]]
text = self.StringFromCTC(pred_batch, model.using_ctc, null_label)
truth = self.StringFromCTC(labels_batch, False, null_label)
# Note that recall_errs is false negatives (fn) aka drops/deletions.
# Actual recall would be 1-fn/truth_words.
# Likewise precision_errs is false positives (fp) aka adds/insertions.
# Actual precision would be 1-fp/ocr_words.
total_word_counts = ec.AddErrors(total_word_counts,
ec.CountWordErrors(text, truth))
total_label_counts = ec.AddErrors(total_label_counts,
ec.CountErrors(text, truth))
if text != truth:
sequence_errors += 1
coord.request_stop()
coord.join(threads)
return ec.ComputeErrorRates(total_label_counts, total_word_counts,
sequence_errors, num_steps * batch_size)
示例12
def SoftmaxEval(self, sess, model, num_steps):
"""Evaluate a model in softmax mode.
Adds char, word recall and sequence error rate events to the sw summary
writer, and returns them as well
TODO(rays) Add LogisticEval.
Args:
sess: A tensor flow Session.
model: The model to run in the session. Requires a VGSLImageModel or any
other class that has a using_ctc attribute and a RunAStep(sess) method
that reurns a softmax result with corresponding labels.
num_steps: Number of steps to evaluate for.
Returns:
ErrorRates named tuple.
Raises:
ValueError: If an unsupported number of dimensions is used.
"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# Run the requested number of evaluation steps, gathering the outputs of the
# softmax and the true labels of the evaluation examples.
total_label_counts = ec.ErrorCounts(0, 0, 0, 0)
total_word_counts = ec.ErrorCounts(0, 0, 0, 0)
sequence_errors = 0
for _ in xrange(num_steps):
softmax_result, labels = model.RunAStep(sess)
# Collapse softmax to same shape as labels.
predictions = softmax_result.argmax(axis=-1)
# Exclude batch from num_dims.
num_dims = len(predictions.shape) - 1
batch_size = predictions.shape[0]
null_label = softmax_result.shape[-1] - 1
for b in xrange(batch_size):
if num_dims == 2:
# TODO(rays) Support 2-d data.
raise ValueError('2-d label data not supported yet!')
else:
if num_dims == 1:
pred_batch = predictions[b, :]
labels_batch = labels[b, :]
else:
pred_batch = [predictions[b]]
labels_batch = [labels[b]]
text = self.StringFromCTC(pred_batch, model.using_ctc, null_label)
truth = self.StringFromCTC(labels_batch, False, null_label)
# Note that recall_errs is false negatives (fn) aka drops/deletions.
# Actual recall would be 1-fn/truth_words.
# Likewise precision_errs is false positives (fp) aka adds/insertions.
# Actual precision would be 1-fp/ocr_words.
total_word_counts = ec.AddErrors(total_word_counts,
ec.CountWordErrors(text, truth))
total_label_counts = ec.AddErrors(total_label_counts,
ec.CountErrors(text, truth))
if text != truth:
sequence_errors += 1
coord.request_stop()
coord.join(threads)
return ec.ComputeErrorRates(total_label_counts, total_word_counts,
sequence_errors, num_steps * batch_size)
