wangleihitcs/medicalreportgeneration

A Base Tensorflow Project for Medical Report Generation

medicalreportgeneration's Issues

Download file from Italy

Hi, is possible to have a link to download dataset from Italy? Is impossible to create account from Italy in Baidu. Thanks for your work

Extractation Code to get processed NLMCXR images_pairs

Hi when I open the link for images pnd pair .zip it asks for extraction code. Could you help me please.

Which file to call for MRNA

which file to call for MRNA because in train.py it call cnn_hier_rnn_model. And if I look for MRNA implementation I could not get a clue

Output unchanges

I found that after training, the output never changes no matter what your input is... did you get the same problem?

I got OutOfRangeError when runn train.py

Hi, I got error like this
Error message as showing below:
Traceback (most recent call last):
File "/home/ike/Workspace/MedicalReportGeneration/train.py", line 101, in
train()
File "/home/ike/Workspace/MedicalReportGeneration/train.py", line 39, in train
images_frontal, images_lateral, sentences, masks, image_ids = sess.run([image_frontal_batch, image_lateral_batch, sentence_batch, mask_batch, image_id_batch])
File "/home/ike/anaconda3/envs/MICCAI/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 900, in run
run_metadata_ptr)
File "/home/ike/anaconda3/envs/MICCAI/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1135, in _run
feed_dict_tensor, options, run_metadata)
File "/home/ike/anaconda3/envs/MICCAI/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1316, in _do_run
run_metadata)
File "/home/ike/anaconda3/envs/MICCAI/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1335, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.OutOfRangeError: RandomShuffleQueue '_1_shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 26, current size 0)
[[Node: shuffle_batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_FLOAT, DT_INT64, DT_INT64, DT_INT64], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/device:CPU:0"](shuffle_batch/random_shuffle_queue, shuffle_batch/n)]]

Caused by op u'shuffle_batch', defined at:
File "/home/ike/Workspace/MedicalReportGeneration/train.py", line 101, in
train()
File "/home/ike/Workspace/MedicalReportGeneration/train.py", line 17, in train
image_frontal_batch, image_lateral_batch, sentence_batch, mask_batch, image_id_batch = datasets.get_train_batch(c.train_tfrecord_path, c, md.batch_size)
File "/home/ike/Workspace/MedicalReportGeneration/datasets.py", line 38, in get_train_batch
min_after_dequeue=2 * batch_size
File "/home/ike/anaconda3/envs/MICCAI/lib/python2.7/site-packages/tensorflow/python/training/input.py", line 1300, in shuffle_batch
name=name)
File "/home/ike/anaconda3/envs/MICCAI/lib/python2.7/site-packages/tensorflow/python/training/input.py", line 846, in _shuffle_batch
dequeued = queue.dequeue_many(batch_size, name=name)
File "/home/ike/anaconda3/envs/MICCAI/lib/python2.7/site-packages/tensorflow/python/ops/data_flow_ops.py", line 483, in dequeue_many
self._queue_ref, n=n, component_types=self._dtypes, name=name)
File "/home/ike/anaconda3/envs/MICCAI/lib/python2.7/site-packages/tensorflow/python/ops/gen_data_flow_ops.py", line 3480, in queue_dequeue_many_v2
component_types=component_types, timeout_ms=timeout_ms, name=name)
File "/home/ike/anaconda3/envs/MICCAI/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/ike/anaconda3/envs/MICCAI/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3392, in create_op
op_def=op_def)
File "/home/ike/anaconda3/envs/MICCAI/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1718, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

OutOfRangeError (see above for traceback): RandomShuffleQueue '_1_shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 26, current size 0)
[[Node: shuffle_batch = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_FLOAT, DT_INT64, DT_INT64, DT_INT64], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/device:CPU:0"](shuffle_batch/random_shuffle_queue, shuffle_batch/n)]]

any suggestion?

A few questions about the implementation

Hi, thanks for sharing your implementation! This is awesome work and helps others to catch up easily. I am trying to play with your code and meet a few questions. It will be great if you could spare some time to reply.

1. You mentioned the "ours" method which achieves the best performance. Would you mind to share what changes have you made compared with MRNA?
2. You've provided two pre-trained inception nets for the frontal and lateral images. I am wondering about which task have you fine-tuned the inception net to obtain these two pre-trained models? Is it fine for us to load the original inception nets for both images and train from scratch?
3. Are you training on one GPU?
4. How do you separate the Normal Reports and Abnormal Reports?

Looking forward to hearing from you :-)