yuting-gao/crnn_mxnet

MXnet version of CRNN for scene text recognition with CNN+2-layer BLSTM+CTC architecture.

crnn_mxnet's Issues

model .params

model下的参数文件只有134字节

I use 0.10.1,but come across this mistake : Shape of labels 1 does not match shape of predictions 2

[18:42:02] src/operator/././cudnn_algoreg-inl.h:65: Running performance tests to find the best convolution algorithm, this can take a while... (setting env variable MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable)
Traceback (most recent call last):
File "text_deep_ocr_bucketing.py", line 121, in
batch_end_callback = mx.callback.Speedometer(BATCH_SIZE, 20))
File "/usr/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/module/base_module.py", line 495, in fit
self.update_metric(eval_metric, data_batch.label)
File "/usr/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/module/bucketing_module.py", line 462, in update_metric
self._curr_module.update_metric(eval_metric, labels)
File "/usr/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/module/module.py", line 680, in update_metric
self.exec_group.update_metric(eval_metric, labels)
File "/usr/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/module/executor_group.py", line 561, in update_metric
eval_metric.update_dict(labels, preds)
File "/usr/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/metric.py", line 91, in update_dict
self.update(label, pred)
File "/usr/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/metric.py", line 1005, in update
check_label_shapes(labels, preds)
File "/usr/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/metric.py", line 24, in check_label_shapes
"predictions {}".format(label_shape, pred_shape))
ValueError: Shape of labels 1 does not match shape of predictions 2