def plot_bboxes(bbox_plotter, model, input_image, iteration):
outputs = model.get_outputs()
transform_params, interpolated_areas = bbox_plotter.get_area_data(
1,
outputs[0],
outputs[1],
)
labels = strip_prediction(np.argmax(outputs[2].asnumpy(), axis=1), args.blank_label)
labels = ''.join([chr(char_map[str(x)]) for x in labels])
bbox_plotter.save_extracted_regions(
input_image,
interpolated_areas.asnumpy(),
transform_params.asnumpy(),
iteration,
labels,
)
def plot_bboxes(bbox_plotter, model, input_image, iteration):
outputs = model.get_outputs()
transform_params, interpolated_areas = bbox_plotter.get_area_data(
1,
outputs[0],
outputs[1],
)
labels = strip_prediction(np.argmax(outputs[2].asnumpy(), axis=1),
args.blank_label)
labels = ''.join([chr(char_map[str(x)]) for x in labels])
bbox_plotter.save_extracted_regions(
input_image,
interpolated_areas.asnumpy(),
transform_params.asnumpy(),
iteration,
labels,
)
def plot_bboxes(execution_params):
data_iter = execution_params.locals['train_data']
iters_per_epoch = num_data // data_iter.batch_size
batch_size = data_iter.batch_size if batch_num is None else batch_num
input_data_shapes = {
description.name: (batch_size, ) + description.shape[1:]
for description in data_iter.provide_data
}
for label_data in data_iter.provide_label:
input_data_shapes[
label_data.name] = (batch_size, ) + label_data.shape[1:]
executor = stn_output.simple_bind(
execution_params.locals['ctx'][0],
grad_req='null',
**input_data_shapes)
# set weights of executor
original_executor = execution_params.locals['executor_manager']
params = executor.arg_dict
self.copy_params(params, original_executor, attr_name='param')
aux_params = executor.aux_dict
self.copy_params(aux_params, original_executor, attr_name='aux')
params['data'][:] = mx.nd.array(
np.tile(data, (batch_size, 1, 1, 1)))
params['softmax_label'] = mx.nd.array(label)
executor.forward(is_train=False)
transform_params, interpolated_areas = self.get_area_data(
batch_size,
executor.outputs[0],
executor.outputs[1],
)
if self.show_labels:
if self.label_majority_vote:
labels = self.majority_vote(
np.argmax(executor.outputs[2].asnumpy(), axis=1))
labels = strip_prediction(labels, self.blank_label)
else:
labels = strip_prediction(
np.argmax(executor.outputs[2].asnumpy(), axis=1),
self.blank_label)
labels = ''.join([chr(self.label_map[str(x)]) for x in labels])
else:
labels = ''
extra_transform_params = None
extra_interpolated_areas = None
if self.plot_extra_loc:
extra_transform_params = executor.outputs[3]
size, num_params = extra_transform_params.shape
extra_transform_params = extra_transform_params.reshape(
(size // batch_size, batch_size, num_params))
extra_transform_params = mx.nd.transpose(
extra_transform_params, axes=(1, 0, 2))[0]
extra_interpolated_areas = executor.outputs[4]
size, num_channels, height, width = extra_interpolated_areas.shape
extra_interpolated_areas = extra_interpolated_areas.reshape(
(size // batch_size, batch_size, num_channels, height,
width))
extra_interpolated_areas = mx.nd.transpose(
extra_interpolated_areas, axes=(1, 0, 2, 3, 4))[0]
gt_bboxes = None
if show_gt_bboxes:
num_timesteps = size // batch_size
_, gt_bboxes = np.split(label, [-(num_timesteps * 4)])
gt_bboxes = gt_bboxes.reshape(num_timesteps, 4)
iteration = execution_params.epoch * iters_per_epoch + execution_params.nbatch
self.save_extracted_regions(
data,
interpolated_areas.asnumpy(),
transform_params.asnumpy(),
iteration,
labels,
gt_bboxes=gt_bboxes,
extra_transform_params=extra_transform_params.asnumpy()
if extra_transform_params is not None else None,
extra_interpolated_areas=extra_interpolated_areas.asnumpy()
if extra_interpolated_areas is not None else None,
)
def plot_bboxes(execution_params):
data_iter = execution_params.locals['train_data']
iters_per_epoch = num_data // data_iter.batch_size
batch_size = data_iter.batch_size if batch_num is None else batch_num
input_data_shapes = {description.name: (batch_size, ) + description.shape[1:] for description in data_iter.provide_data}
for label_data in data_iter.provide_label:
input_data_shapes[label_data.name] = (batch_size, ) + label_data.shape[1:]
executor = stn_output.simple_bind(execution_params.locals['ctx'][0], grad_req='null', **input_data_shapes)
# set weights of executor
original_executor = execution_params.locals['executor_manager']
params = executor.arg_dict
self.copy_params(params, original_executor, attr_name='param')
aux_params = executor.aux_dict
self.copy_params(aux_params, original_executor, attr_name='aux')
params['data'][:] = mx.nd.array(np.tile(data, (batch_size, 1, 1, 1)))
params['softmax_label'] = mx.nd.array(label)
executor.forward(is_train=False)
transform_params, interpolated_areas = self.get_area_data(
batch_size,
executor.outputs[0],
executor.outputs[1],
)
if self.show_labels:
if self.label_majority_vote:
labels = self.majority_vote(np.argmax(executor.outputs[2].asnumpy(), axis=1))
labels = strip_prediction(labels, self.blank_label)
else:
labels = strip_prediction(np.argmax(executor.outputs[2].asnumpy(), axis=1), self.blank_label)
labels = ''.join([chr(self.label_map[str(x)]) for x in labels])
else:
labels = ''
extra_transform_params = None
extra_interpolated_areas = None
if self.plot_extra_loc:
extra_transform_params = executor.outputs[3]
size, num_params = extra_transform_params.shape
extra_transform_params = extra_transform_params.reshape((size // batch_size, batch_size, num_params))
extra_transform_params = mx.nd.transpose(extra_transform_params, axes=(1, 0, 2))[0]
extra_interpolated_areas = executor.outputs[4]
size, num_channels, height, width = extra_interpolated_areas.shape
extra_interpolated_areas = extra_interpolated_areas.reshape((size // batch_size, batch_size, num_channels, height, width))
extra_interpolated_areas = mx.nd.transpose(extra_interpolated_areas, axes=(1, 0, 2, 3, 4))[0]
gt_bboxes = None
if show_gt_bboxes:
num_timesteps = size // batch_size
_, gt_bboxes = np.split(label, [-(num_timesteps * 4)])
gt_bboxes = gt_bboxes.reshape(num_timesteps, 4)
iteration = execution_params.epoch * iters_per_epoch + execution_params.nbatch
self.save_extracted_regions(
data,
interpolated_areas.asnumpy(),
transform_params.asnumpy(),
iteration,
labels,
gt_bboxes=gt_bboxes,
extra_transform_params=extra_transform_params.asnumpy() if extra_transform_params is not None else None,
extra_interpolated_areas=extra_interpolated_areas.asnumpy() if extra_interpolated_areas is not None else None,
)
the_image = Image.open(file_name)
the_image = the_image.convert('L')
the_image = the_image.resize((input_size.width, input_size.height), Image.ANTIALIAS)
image = np.asarray(the_image, dtype=np.float32)[np.newaxis, np.newaxis, ...]
image /= 255
input_batch = Batch(data=[mx.nd.array(image)], label=[mx.nd.array(label)])
model.forward(input_batch, is_train=False)
if args.plot:
plot_bboxes(bbox_plotter, model, image, idx)
predictions = model.get_outputs()[2].asnumpy()
predicted_classes = np.argmax(predictions, axis=1)
# cut all word end predictions
predicted_classes = strip_prediction(predicted_classes, int(reverse_char_map[args.blank_symbol]))
predicted_word = ''.join([chr(char_map[str(p)]) for p in predicted_classes]).replace(' ', '')
distance = editdistance.eval(gt_word, predicted_word)
print("{} - {}\t\t{}: {}".format(idx, gt_word, predicted_word, distance))
results = [prediction == label for prediction, label in zip(predicted_word, gt_word)]
if all(results):
num_correct += 1
num_overall += 1
print("Accuracy: {}".format(num_correct / num_overall))
label=[mx.nd.array(labels)])
model.forward(input_batch, is_train=False)
if args.plot:
plot_bboxes(bbox_plotter, model, image, idx)
# extract predictions from model
predictions = model.get_outputs()[2].asnumpy()
# get predicted classes
predicted_classes = np.argmax(predictions, axis=1)
# interpret batch or predictions as three different predictions (for each time step one prediction)
predicted_classes = predicted_classes.reshape(3, -1)
# strip blanks and double symbols from prediction
predicted_classes = [
strip_prediction(predicted_classes[i], args.blank_label)
for i in range(len(predicted_classes))
]
# concat groundtruth
gt_words = [l for l in [label_1, label_2, label_3]]
# convert groundtruth from labels to chars
gt_words = [
''.join([chr(char_map[str(p)]) for p in g]) for g in gt_words
]
# strip blank labels from groundtruth
gt_words = [
g.strip(chr(char_map[str(args.blank_label)])) for g in gt_words
]
# convert predicted classes to characters
predicted_words = [
input_batch = Batch(data=[mx.nd.array(image)], label=[mx.nd.array(labels)])
model.forward(input_batch, is_train=False)
if args.plot:
plot_bboxes(bbox_plotter, model, image, idx)
# extract predictions from model
predictions = model.get_outputs()[2].asnumpy()
# get predicted classes
predicted_classes = np.argmax(predictions, axis=1)
# interpret batch or predictions as three different predictions (for each time step one prediction)
predicted_classes = predicted_classes.reshape(3, -1)
# strip blanks and double symbols from prediction
predicted_classes = [strip_prediction(predicted_classes[i], args.blank_label) for i in range(len(predicted_classes))]
# concat groundtruth
gt_words = [l for l in [label_1, label_2, label_3]]
# convert groundtruth from labels to chars
gt_words = [''.join([chr(char_map[str(p)]) for p in g]) for g in gt_words]
# strip blank labels from groundtruth
gt_words = [g.strip(chr(char_map[str(args.blank_label)])) for g in gt_words]
# convert predicted classes to characters
predicted_words = [''.join([chr(char_map[str(g)]) for g in p]) for p in predicted_classes]
model_predictions.append((file_name, predicted_words))
# eval predictions
for gt_word, predicted_word in zip(gt_words, predicted_words):
distance = editdistance.eval(gt_word, predicted_word)
print("{} - {}\t\t{}: {}".format(idx, gt_word, predicted_word, distance))
image = np.asarray(the_image, dtype=np.float32)[np.newaxis,
np.newaxis, ...]
image /= 255
input_batch = Batch(data=[mx.nd.array(image)],
label=[mx.nd.array(label)])
model.forward(input_batch, is_train=False)
if args.plot:
plot_bboxes(bbox_plotter, model, image, idx)
predictions = model.get_outputs()[2].asnumpy()
predicted_classes = np.argmax(predictions, axis=1)
# cut all word end predictions
predicted_classes = strip_prediction(
predicted_classes, int(reverse_char_map[args.blank_symbol]))
predicted_word = ''.join([
chr(char_map[str(p)]) for p in predicted_classes
]).replace(' ', '')
model_predictions.append((file_name, predicted_word))
distance = editdistance.eval(gt_word, predicted_word)
print("{} - {}\t\t{}: {}".format(idx, gt_word, predicted_word,
distance))
results = [
prediction == label
for prediction, label in zip(predicted_word, gt_word)
]
if all(results):
num_correct += 1
num_overall += 1