Comments (2)
When I test the model,it occurs a problem.The situation is as follows:
customer@node01:~/FCN/brats17-master$ python test.py test_all_class.txt
data data_root /home/customer/data/Brats17ValidationData /home/customer/data/Brats17ValidationData
data save_folder /home/customer/data/result17/two /home/customer/data/result17/two
data data_names config17/test_names_temp.txt config17/test_names_temp.txt
data modality_postfix [flair, t1, t1ce, t2] ['flair', 't1', 't1ce', 't2']
data file_postfix nii.gz nii.gz
network1ax net_type MSNet MSNet
network1ax net_name MSNet_WT32 MSNet_WT32
network1ax downsample_twice True True
network1ax data_shape [19, 180, 160, 4] [19, 180, 160, 4]
network1ax label_shape [11, 180, 160, 1] [11, 180, 160, 1]
network1ax class_num 2 2
network1ax model_file model17/msnet_wt32_20000.ckpt model17/msnet_wt32_20000.ckpt
network1sg net_type MSNet MSNet
network1sg net_name MSNet_WT32sg MSNet_WT32sg
network1sg downsample_twice True True
network1sg data_shape [19, 160, 180, 4] [19, 160, 180, 4]
network1sg label_shape [11, 160, 180, 1] [11, 160, 180, 1]
network1sg class_num 2 2
network1sg model_file model17/msnet_wt32sg_20000.ckpt model17/msnet_wt32sg_20000.ckpt
network1cr net_type MSNet MSNet
network1cr net_name MSNet_WT32cr MSNet_WT32cr
network1cr downsample_twice True True
network1cr data_shape [19, 160, 160, 4] [19, 160, 160, 4]
network1cr label_shape [11, 160, 160, 1] [11, 160, 160, 1]
network1cr class_num 2 2
network1cr model_file model17/msnet_wt32cr_20000.ckpt model17/msnet_wt32cr_20000.ckpt
network2ax net_type MSNet MSNet
network2ax net_name MSNet_TC32 MSNet_TC32
network2ax downsample_twice True True
network2ax data_shape [19, 96, 96, 4] [19, 96, 96, 4]
network2ax label_shape [11, 96, 96, 1] [11, 96, 96, 1]
network2ax class_num 2 2
network2ax model_file model17/msnet_tc32_20000.ckpt model17/msnet_tc32_20000.ckpt
network2sg net_type MSNet MSNet
network2sg net_name MSNet_TC32sg MSNet_TC32sg
network2sg downsample_twice True True
network2sg data_shape [19, 96, 96, 4] [19, 96, 96, 4]
network2sg label_shape [11, 96, 96, 1] [11, 96, 96, 1]
network2sg class_num 2 2
network2sg model_file model17/msnet_tc32sg_20000.ckpt model17/msnet_tc32sg_20000.ckpt
network2cr net_type MSNet MSNet
network2cr net_name MSNet_TC32cr MSNet_TC32cr
network2cr downsample_twice True True
network2cr data_shape [19, 96, 96, 4] [19, 96, 96, 4]
network2cr label_shape [11, 96, 96, 1] [11, 96, 96, 1]
network2cr class_num 2 2
network2cr model_file model17/msnet_tc32cr_20000.ckpt model17/msnet_tc32cr_20000.ckpt
network3ax net_type MSNet MSNet
network3ax net_name MSNet_EN32 MSNet_EN32
network3ax downsample_twice False False
network3ax data_shape [19, 96, 96, 4] [19, 96, 96, 4]
network3ax label_shape [11, 96, 96, 1] [11, 96, 96, 1]
network3ax class_num 2 2
network3ax model_file model17/msnet_en32_20000.ckpt model17/msnet_en32_20000.ckpt
network3sg net_type MSNet MSNet
network3sg net_name MSNet_EN32sg MSNet_EN32sg
network3sg downsample_twice False False
network3sg data_shape [19, 96, 96, 4] [19, 96, 96, 4]
network3sg label_shape [11, 96, 96, 1] [11, 96, 96, 1]
network3sg class_num 2 2
network3sg model_file model17/msnet_en32sg_20000.ckpt model17/msnet_en32sg_20000.ckpt
network3cr net_type MSNet MSNet
network3cr net_name MSNet_EN32cr MSNet_EN32cr
network3cr downsample_twice False False
network3cr data_shape [19, 96, 96, 4] [19, 96, 96, 4]
network3cr label_shape [11, 96, 96, 1] [11, 96, 96, 1]
network3cr class_num 2 2
network3cr model_file model17/msnet_en32cr_20000.ckpt model17/msnet_en32cr_20000.ckpt
testing test_slice_direction all all
2019-03-07 16:12:09.919758: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2019-03-07 16:12:10.170770: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1212] Found device 0 with properties:
name: TITAN Xp major: 6 minor: 1 memoryClockRate(GHz): 1.582
pciBusID: 0000:02:00.0
totalMemory: 11.90GiB freeMemory: 11.46GiB
2019-03-07 16:12:10.344403: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1212] Found device 1 with properties:
name: TITAN Xp major: 6 minor: 1 memoryClockRate(GHz): 1.582
pciBusID: 0000:81:00.0
totalMemory: 11.90GiB freeMemory: 11.74GiB
2019-03-07 16:12:10.344474: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1227] Device peer to peer matrix
2019-03-07 16:12:10.344503: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1233] DMA: 0 1
2019-03-07 16:12:10.344512: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1243] 0: Y N
2019-03-07 16:12:10.344518: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1243] 1: N Y
2019-03-07 16:12:10.344528: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1312] Adding visible gpu devices: 0, 1
2019-03-07 16:12:10.844580: I tensorflow/core/common_runtime/gpu/gpu_device.cc:993] Creating TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 11101 MB memory) -> physical GPU (device: 0, name: TITAN Xp, pci bus id: 0000:02:00.0, compute capability: 6.1)
2019-03-07 16:12:10.845693: I tensorflow/core/common_runtime/gpu/gpu_device.cc:993] Creating TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:1 with 11364 MB memory) -> physical GPU (device: 1, name: TITAN Xp, pci bus id: 0000:81:00.0, compute capability: 6.1)
INFO:niftynet: Restoring parameters from model17/msnet_wt32_20000.ckpt
INFO:niftynet: Restoring parameters from model17/msnet_wt32sg_20000.ckpt
INFO:niftynet: Restoring parameters from model17/msnet_wt32cr_20000.ckpt
INFO:niftynet: Restoring parameters from model17/msnet_tc32_20000.ckpt
INFO:niftynet: Restoring parameters from model17/msnet_tc32sg_20000.ckpt
INFO:niftynet: Restoring parameters from model17/msnet_tc32cr_20000.ckpt
INFO:niftynet: Restoring parameters from model17/msnet_en32_20000.ckpt
INFO:niftynet: Restoring parameters from model17/msnet_en32sg_20000.ckpt
INFO:niftynet: Restoring parameters from model17/msnet_en32cr_20000.ckpt
Data load, 100.0% finished
net1 output is null Brats17_TCIA_600_1
Brats17_TCIA_600_1
test time 34.72197985649109
and when I open the Brats17_TCIA_600_1.nii.gz using mipav ,it's whole black.And I changed the code of test_all_class as follows:
data_root = /home/customer/data/Brats17ValidationData
save_folder = /home/customer/data/result17/two
all the folder are exist.Could you please suggest the solution.
from brats17.
Hi @Gaojun211 and @taigw,
Have you found a solution to this?
I have a similar error:
/content/brats17/util/data_process.py:95: RuntimeWarning: divide by zero encountered in true_divide out = (volume - mean)/std /content/brats17/util/data_process.py:95: RuntimeWarning: invalid value encountered in true_divide out = (volume - mean)/std Data load, 100.0% finished 2019-10-31 01:47:45.793500: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2019-10-31 01:47:48.677996: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0 net1 output is null HGG/Brats17_CBICA_ATX_1 HGG/Brats17_CBICA_ATX_1 net1 output is null HGG/Brats17_CBICA_AXN_1 HGG/Brats17_CBICA_AXN_1 test time 86.31490552425385
from brats17.
Related Issues (20)
- Regarding subimage patch and label size HOT 7
- ERROR (nifti_image_write_hdr_img2): cannot open output file HOT 11
- the validation data segmentation result HOT 3
- How to use multi-gpu? HOT 1
- Do I have to rewrite test.py when I define the network without NiftyNet? HOT 1
- About the size of data_shape HOT 9
- UnboundedLocalError: local variable referenced before assignment.
- Activation Layer Before Convolution layer in ResBlock HOT 1
- Can I stop training early?
- Some questions about data_root
- test_one_image_three_nets_adaptive_shape function
- Config File Generation for brats 2018 Data
- Overlap in Train/Test Data
- How to enable NiftyNet's balanced window sampler?
- loss is not declined HOT 1
- OOM about training with brats17 data HOT 1
- Error: Provided indices are out-of-bounds
- No module named 'util'
- Where can we find the labels for Brats 2015 dataset?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from brats17.