The keras problem about the bash_train.sh

[GilbertKun]

hello I download the HdenseUnet from your github.But some error occured when I run the code:sh bash_train.sh Traceback (most recent call last): File "train_2ddense.py", line 215, in train_and_predict() File "train_2ddense.py", line 210, in train_and_predict workers=3, use_multiprocessing=False) File "Keras-2.0.8/keras/legacy/interfaces.py", line 87, in wrapper return func(*args, **kwargs) File "Keras-2.0.8/keras/engine/training.py", line 2011, in fit_generator generator_output = next(output_generator) StopIteration Could you give me some help? Thanks!

[xmengli]

That means the generator is not generating data. Please whether the data root is correct? Whether you have load the data.

[GilbertKun]

---

Fitting model......

Then the Exception occured.

Exception in thread Thread-2: Traceback (most recent call last): File "/home/awifi/anaconda3/envs/denseu/lib/python2.7/threading.py", line 801, in __bootstrap_inner self.run() File "/home/awifi/anaconda3/envs/denseu/lib/python2.7/threading.py", line 754, in run self.__target(*self.__args, **self.__kwargs) File "Keras-2.0.8/keras/utils/data_utils.py", line 568, in data_generator_task generator_output = next(self._generator) ValueError: generator already executing

/home/awifi/anaconda3/envs/denseu/lib/python2.7/site-packages/skimage/transform/_warps.py:110: UserWarning: be enabled by default in skimage 0.15 to avoid aliasing artifacts when down-sampling images. warn("Anti-aliasing will be enabled by default in skimage 0.15 to " Exception in thread Thread-1: Traceback (most recent call last): File "/home/awifi/anaconda3/envs/denseu/lib/python2.7/threading.py", line 801, in __bootstrap_inner self.run() File "/home/awifi/anaconda3/envs/denseu/lib/python2.7/threading.py", line 754, in run self.__target(*self.__args, **self.__kwargs) File "Keras-2.0.8/keras/utils/data_utils.py", line 568, in data_generator_task generator_output = next(self._generator) File "train_2ddense.py", line 120, in generate_arrays_from_file result_list = pool.map(load_seq_crop_data_masktumor_try, Parameter_List) File "/home/awifi/anaconda3/envs/denseu/lib/python2.7/multiprocessing/pool.py", line 251, in map return self.map_async(func, iterable, chunksize).get() File "/home/awifi/anaconda3/envs/denseu/lib/python2.7/multiprocessing/pool.py", line 567, in get raise self._value ValueError: low >= high

I change 131 to 5 and change the worker from 3 to 1,then it works.

[xmengli]

It may be the limitation in CPU?

[GilbertKun]

So what is the recommended CPU configuration?

[mnc1423]

Having the same problem. Isn't the data root Liver Tumor Segmentation Challenge data set? the one you download and not the one you prepossessed? any update on the CPU configuration?

[xmengli]

The data is the LiTS challenge dataset. You can download it from the challenge website.

[mnc1423]

Im using Intel(R) Xeon(R) Silver 4116 CPU should this cause a problem?

[xmengli]

I load the whole dataset once before training the network. If you can load the whole dataset, I think the hardware is OK.

[mnc1423]

Thanks i'll try that :)

[mnc1423]

Can i ask what tensorflow, cuda, cudnn version you're using for this build?

[xmengli]

I attach the requirement file.

absl-py==0.1.10 backports-abc==0.5 backports.functools-lru-cache==1.5 backports.weakref==1.0rc1 bleach==1.5.0 bokeh==0.12.15 certifi==2018.1.18 cffi==1.11.5 chardet==3.0.4 click==6.7 cloudpickle==0.5.2 cycler==0.10.0 cytoolz==0.9.0.1 dask==0.17.2 decorator==4.3.0 distributed==1.21.6 dominate==2.3.1 easydict==1.4 enum34==1.1.6 funcsigs==1.0.2 functools32==3.2.3.post2 futures==3.2.0 h5py==2.8.0 heapdict==1.0.0 html5lib==0.9999999 idna==2.6 imageio==2.3.0 Jinja2==2.10 kiwisolver==1.0.1 linecache2==1.0.0 locket==0.2.0 Markdown==2.6.11 MarkupSafe==1.0 matplotlib==2.2.2 MedPy==0.3.0 mkl-fft==1.0.0 mkl-random==1.0.1 mock==2.0.0 msgpack-python==0.5.6 networkx==2.1 nibabel==2.3.1 nltk==2.0.4 numpy==1.14.3 olefile==0.45.1 packaging==17.1 pairwise==0.1 pandas==0.22.0 partd==0.3.8 pathlib==1.0.1 pbr==4.0.2 Pillow==5.0.0 protobuf==3.5.2 psutil==5.4.5 pycparser==2.18 pydicom==1.2.1 pyparsing==2.2.0 python-dateutil==2.7.2 pytz==2018.4 PyWavelets==0.5.2 PyYAML==3.12 pyzmq==17.0.0 requests==2.18.4 scikit-image==0.13.1 scikit-learn==0.19.1 scipy==1.1.0 singledispatch==3.4.0.3 six==1.11.0 sortedcontainers==1.5.10 subprocess32==3.2.7 tblib==1.3.2 tensorflow==1.5.1 tensorflow-gpu==1.2.1 tensorflow-tensorboard==1.5.1 toolz==0.9.0 torch==0.3.0.post4 torchfile==0.1.0 torchvision==0.2.0 tornado==5.0.2 tqdm==4.28.1 traceback2==1.4.0 unittest2==1.1.0 urllib3==1.22 visdom==0.1.8.3 webencodings==0.5 websocket-client==0.48.0 Werkzeug==0.14.1 zict==0.1.3

[mnc1423]

Hi i have a question, if i wanted to train the data on different CT do i need to change something? i'm currently trying on a different CT with image and segmentation but keeps giving me an error Traceback (most recent call last): File "Ktrain_2ddense.py", line 259, in train_and_predict() File "Ktrain_2ddense.py", line 228, in train_and_predict workers=3, use_multiprocessing=True) File "Keras-2.0.8/keras/legacy/interfaces.py", line 87, in wrapper return func(*args, **kwargs) File "Keras-2.0.8/keras/engine/training.py", line 2011, in fit_generator generator_output = next(output_generator) StopIteration

[guolihong]

Hi i have a question, if i wanted to train the data on different CT do i need to change something? i'm currently trying on a different CT with image and segmentation but keeps giving me an error Traceback (most recent call last): File "Ktrain_2ddense.py", line 259, in train_and_predict() File "Ktrain_2ddense.py", line 228, in train_and_predict workers=3, use_multiprocessing=True) File "Keras-2.0.8/keras/legacy/interfaces.py", line 87, in wrapper return func(*args, **kwargs) File "Keras-2.0.8/keras/engine/training.py", line 2011, in fit_generator generator_output = next(output_generator) StopIteration Hello! I have the same problem.Would you please tell me how did you solve it?

[lyxlynn]

Fitting model......

Then the Exception occured.

Exception in thread Thread-2: Traceback (most recent call last): File "/home/awifi/anaconda3/envs/denseu/lib/python2.7/threading.py", line 801, in __bootstrap_inner self.run() File "/home/awifi/anaconda3/envs/denseu/lib/python2.7/threading.py", line 754, in run self.__target(*self.__args, **self.__kwargs) File "Keras-2.0.8/keras/utils/data_utils.py", line 568, in data_generator_task generator_output = next(self._generator) ValueError: generator already executing

/home/awifi/anaconda3/envs/denseu/lib/python2.7/site-packages/skimage/transform/_warps.py:110: UserWarning: be enabled by default in skimage 0.15 to avoid aliasing artifacts when down-sampling images. warn("Anti-aliasing will be enabled by default in skimage 0.15 to " Exception in thread Thread-1: Traceback (most recent call last): File "/home/awifi/anaconda3/envs/denseu/lib/python2.7/threading.py", line 801, in __bootstrap_inner self.run() File "/home/awifi/anaconda3/envs/denseu/lib/python2.7/threading.py", line 754, in run self.__target(*self.__args, **self.__kwargs) File "Keras-2.0.8/keras/utils/data_utils.py", line 568, in data_generator_task generator_output = next(self._generator) File "train_2ddense.py", line 120, in generate_arrays_from_file result_list = pool.map(load_seq_crop_data_masktumor_try, Parameter_List) File "/home/awifi/anaconda3/envs/denseu/lib/python2.7/multiprocessing/pool.py", line 251, in map return self.map_async(func, iterable, chunksize).get() File "/home/awifi/anaconda3/envs/denseu/lib/python2.7/multiprocessing/pool.py", line 567, in get raise self._value ValueError: low >= high

I change 131 to 5 and change the worker from 3 to 1,then it works.

I have the same problem with you . I change 131 to 5 and change the worker from 3 to 1,then it works. do you know why is it?

[larry-11]

Hi i have a question, if i wanted to train the data on different CT do i need to change something? i'm currently trying on a different CT with image and segmentation but keeps giving me an error Traceback (most recent call last): File "Ktrain_2ddense.py", line 259, in train_and_predict() File "Ktrain_2ddense.py", line 228, in train_and_predict workers=3, use_multiprocessing=True) File "Keras-2.0.8/keras/legacy/interfaces.py", line 87, in wrapper return func(*args, **kwargs) File "Keras-2.0.8/keras/engine/training.py", line 2011, in fit_generator generator_output = next(output_generator) StopIteration

I have the same question when I training on my own data. I wonder how you solved it. thx!

[larry-11]

Hi i have a question, if i wanted to train the data on different CT do i need to change something? i'm currently trying on a different CT with image and segmentation but keeps giving me an error Traceback (most recent call last): File "Ktrain_2ddense.py", line 259, in train_and_predict() File "Ktrain_2ddense.py", line 228, in train_and_predict workers=3, use_multiprocessing=True) File "Keras-2.0.8/keras/legacy/interfaces.py", line 87, in wrapper return func(*args, **kwargs) File "Keras-2.0.8/keras/engine/training.py", line 2011, in fit_generator generator_output = next(output_generator) StopIteration Hello! I have the same problem.Would you please tell me how did you solve it?

same problem. Have you solved it now?

[mnc1423]

I have the code in my repo https://github.com/mnc1423/H-DenseUNet/blob/master/train_2ddense.py Can't remember how i did it but hope this helps

[ee-hash]

I load the whole dataset once before training the network. If you can load the whole dataset, I think the hardware is OK.

Hi, because the memory is not enouph，what should I do to load data by batch not the whole dataset? Thank u.