tureckova / isles2018 Goto Github PK

`[INFO] model compiled
Epoch 1/250

Epoch 00001: LearningRateScheduler setting learning rate to 0.005.
Traceback (most recent call last):
File "train.py", line 146, in
, validation_steps=np.ceil(float(len(testX)) / config["batch_size"])
File "/home/cb201/anaconda3/envs/quanquan/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/home/cb201/anaconda3/envs/quanquan/lib/python3.6/site-packages/keras/engine/training.py", line 1418, in fit_generator
initial_epoch=initial_epoch)
File "/home/cb201/anaconda3/envs/quanquan/lib/python3.6/site-packages/keras/engine/training_generator.py", line 217, in fit_generator
class_weight=class_weight)
File "/home/cb201/anaconda3/envs/quanquan/lib/python3.6/site-packages/keras/engine/training.py", line 1217, in train_on_batch
outputs = self.train_function(ins)
File "/home/cb201/anaconda3/envs/quanquan/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2721, in call
return self._legacy_call(inputs)
File "/home/cb201/anaconda3/envs/quanquan/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2693, in _legacy_call
**self.session_kwargs)
File "/home/cb201/anaconda3/envs/quanquan/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 789, in run
run_metadata_ptr)
File "/home/cb201/anaconda3/envs/quanquan/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 968, in _run
np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)
File "/home/cb201/anaconda3/envs/quanquan/lib/python3.6/site-packages/numpy/core/numeric.py", line 501, in asarray
return array(a, dtype, copy=False, order=order)
TypeError: float() argument must be a string or a number, not 'NoneType'
`

I dont know how to solve this.
sad

in the training file (train.py)

• I have to do the segmentation for training dataset and the segmentation for testing dataset or only i have to do the segmentation for training dataset ?

I'm facing an error "index out of range" while executing the file find_mean_std.py. It also states that the error is wrt the file datasetloader.py. Pls help.

Where can I download the data set?

why we need the mean and std of the dataset?
I dont know.please tell me the resons,thanks!
:)

Hey,
Thanks for your work!
Since I m new to ISLES, I have several Qs about it:

1. what's the bias_collection.py for? Is that only for testing data? I noticed in find_mean_std.py, the training data is not from the PREPROCESSED folder.
2. about the dataset, several papers mentioned there is still a DWI modality in ISLES2018, is that the 4DPWI?
   It would be a great honor if you can answer these Qs. Thanks again.

Hello, I am a student from China, please allow me to ask you some question.
Downloading the ISLES challenge dataset needs to register in the Simr, I tried to register in it ,but I didn't receive the reply after I apply for registration. So, may I ask you for the dataset ? I am looking for your reply, thank you so much! And this is my email address ：[email protected] or through Baidu Cloud

I want to upload my result to the challenge, but it told me that the dice is -1. I don't understand, because in my opinion, the range of dice should be (0,1),I don't know what happened to result to this. Can you help me ? Thank you so much,