search

tkuanlun350 / 3DUnet-Tensorflow-Brats18

3D Unet biomedical segmentation model powered by tensorpack with fast io speed
202 stars 68 forks source link

can only concatenate tuple (not "list") to tuple #5

Closed AllanZuo closed 6 years ago

AllanZuo commented 6 years ago

Hi, Thanks for your great work firstly. There is issue when I do inference .

Below is the detailed information.

Traceback (most recent call last): File "train.py", line 203, in offline_pred([pred], args.evaluate) File "train.py", line 117, in offline_pred df, lambda img: segment_one_image(img, pred_func)) File "E:\network\3DUnet-Tensorflow-Brats18-master\eval.py", line 339, in pred_brats final_label, probs = detect_func(data) File "train.py", line 117, in df, lambda img: segment_one_image(img, pred_func)) File "E:\network\3DUnet-Tensorflow-Brats18-master\eval.py", line 254, in segment_one_image final_probs = np.zeros(temp_size + [config.NUM_CLASS], np.float32) TypeError: can only concatenate tuple (not "list") to tuple

I don't konw how to fix it.

tkuanlun350 commented 6 years ago

HI, thanks you for reporting this issue. This should be fixed in the latest commit !

AllanZuo commented 6 years ago

Thkans.I have fixed the isuue mentioned above. And it run well in brats2018. But I want to change the datasets to my own and training it. My dataset organizes much similar to the brats2018. My nunber class is 1. /HGG/FAR1 {one img,one label}in FAR1 file /LGG/......

But when it went to iteration, there is a error. Traceback (most recent call last): File "C:\ProgramData\Anaconda3\lib\site-packages\tensorpack\input_source\input_source.py", line 162, in run self.op.run(feed_dict=feed) File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 2280, in run _run_using_default_session(self, feed_dict, self.graph, session) File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 5051, in _run_using_default_session session.run(operation, feed_dict) File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 905, in run run_metadata_ptr) File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1116, in _run str(subfeed_t.get_shape()))) ValueError: Cannot feed value of shape (2, 128, 128, 128, 1) for Tensor 'image:0', which has shape '(2, 128, 128, 128, 4)'

It seems like that the problem lies the input shape.Could you help to find where is the problem?

tkuanlun350 commented 6 years ago

Hi, can you confirm the latest fix solved the first issue ? or you fixed it with another way ? can you submit an pull requests.

You can modified the input tensor shape at train.py line 58. You may also change the data_loader since it assume 4 modalities.

AllanZuo commented 6 years ago

The first problem I fixed in another way.I test the latest version of "eval.py",and it is working well on my computer too. Thanks your guidance on the second problem.I change the line 58 in trin.py for 3(becouse I only have 3 for each case). And the dataloder.py should be changed too(modalities=['one','two','three'],which should be the same as in your image file).At last,the eval.py should be changed too(temp_bbox[1]+[4]→temp_bbox[1]+[3]). Thank you again.

tkuanlun350 commented 6 years ago

No problem ! Thanks for your feedback.