WesSurento1
commented
6 years ago I am having the same issue...
line 82, in __load_one_volume assert (volume_name is not None) AssertionError
-I ran rename_crop_BRATS.py on the BraTS '17 training data set -Subsequently, I had to change the patient_dir variable in line 62 in data_loader.py
I suspect that rename_crop_BRATS.py is somehow responsible for this and causing the load_one_volume function in data_loader.py to be unable to find the images/volumes?
Thanks
taigw
@taigw I tried for the code of training i am getting the assertion error. What will be the solution for this?
Thank you.
ujjwal@ujjwal-precision-t1700:~/Desktop/ALL_TRIES/brats17-master_NIFTYNET$ python train.py config17/train_wt_ax.txt data data_root /home/ujjwal/Desktop/ALL_TRIES/brats17-master_NIFTYNET/data_root/Brats17TrainingData /home/ujjwal/Desktop/ALL_TRIES/brats17-master_NIFTYNET/data_root/Brats17TrainingData data data_names config17/train_names_all.txt config17/train_names_all.txt data modality_postfix [flair, t1, t1ce, t2] ['flair', 't1', 't1ce', 't2'] data label_postfix seg seg data file_postfix nii.gz nii.gz data with_ground_truth True True data batch_size 5 5 data data_shape [19, 144, 144, 4] [19, 144, 144, 4] data label_shape [11, 144, 144, 1] [11, 144, 144, 1] data label_convert_source [0, 1, 2, 4] [0, 1, 2, 4] data label_convert_target [0, 1, 1, 1] [0, 1, 1, 1] data batch_slice_direction axial axial data train_with_roi_patch False False data label_roi_mask None data roi_patch_margin None network net_type MSNet MSNet network net_name MSNet_WT32 MSNet_WT32 network downsample_twice True True network class_num 2 2 training learning_rate 1e-3 0.001 training decay 1e-7 1e-07 training maximal_iteration 20000 20000 training snapshot_iteration 5000 5000 training start_iteration 0 0 training test_iteration 100 100 training test_step 10 10 training model_pre_trained None training model_save_prefix model17/msnet_wt32 model17/msnet_wt32 size of predicty: Tensor("MSNet_WT32/final_pred/conv:0", shape=(5, 11, 144, 144, 2), dtype=float32) 2018-06-05 09:23:03.159216: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations. 2018-06-05 09:23:03.159247: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations. 2018-06-05 09:23:03.159253: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations. 2018-06-05 09:23:03.159256: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations. 2018-06-05 09:23:03.159260: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations. Data load, 49.0196078431% finished Data load, 98.0392156863% finished Traceback (most recent call last): File "train.py", line 124, in
train(config_file)
File "train.py", line 83, in train
dataloader.load_data()
File "/home/ujjwal/Desktop/ALL_TRIES/brats17-master_NIFTYNET/util/data_loader.py", line 91, in load_data
volume, volume_name = self.load_one_volume(self.patient_names[i], self.modality_postfix[mod_idx])
File "/home/ujjwal/Desktop/ALL_TRIES/brats17-master_NIFTYNET/util/data_loader.py", line 69, in load_one_volume
assert(volume_name is not None)
AssertionError