ubamba98 / brain-segmentation Goto Github PK
View Code? Open in Web Editor NEWBrain Segmentation on MRBrains18
License: MIT License
Brain Segmentation on MRBrains18
License: MIT License
Good afternoon sir.
there is an error saying undefined variable CLASS at line number 100 in the train.py file
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-9-66b3304bbf9c> in <module>()
94 X_FLAIR_val = to_uint8(get_data(FLAIR_val))[None,None,...]
95 X_IR_val = IR_to_uint8(get_data(IR_val))[None,None,...]
---> 96 y_val = np.array(get_data(segm_val)==CLASS).astype(np.uint8)[None,...]
97 print("STARTING TRAINING...")
98 model_ = model()
NameError: name 'CLASS' is not defined
i am running this code in colab so. please ignore line number here
Hi. I'm trying to download the MRBrainS18 dataset recently and I've sent my confidentiality agreement to [email protected].
However, no reply is received and the website seems to be unavailable now. Could you send me a copy of the dataset? My email is [email protected]. Please help me. Thank you very much.
Hello, may I ask what kind of database you use, you can share your database, I have not found a suitable database. Iโm sorry to bother you. I need a dataset now. My email is [email protected]
I had copied entire project and pasted it on google colab. It is throwing errors. because it is using deepbrain package which uses tensorflow v1 as backend. and colab is using tensorflow version 2 since a while. the error is :
LOADING DATA...
/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:10: DeprecationWarning: get_data() is deprecated in favor of get_fdata(), which has a more predictable return type. To obtain get_data() behavior going forward, use numpy.asanyarray(img.dataobj).
* deprecated from version: 3.0
* Will raise <class 'nibabel.deprecator.ExpiredDeprecationError'> as of version: 5.0
# Remove the CWD from sys.path while we load stuff.
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-28-4ee8cd402a2d> in <module>()
80 y = []
81 for T1_,FLAIR_,IR_,seg_ in zip(T1path, FLAIRpath, IRpath, segpath):
---> 82 T1 = histeq(to_uint8(get_data_with_skull_scraping(T1_)))
83 IR = IR_to_uint8(get_data(IR_))
84 FLAIR = to_uint8(get_data(FLAIR_))
2 frames
/usr/local/lib/python3.6/dist-packages/deepbrain/extractor.py in load_pb(self)
16
17 def load_pb(self):
---> 18 print(tf.__version__)
19 graph = tf.Graph()
20 print(tf.Session(graph=graph))
AttributeError: module 'tensorflow' has no attribute 'Session'
kindly help
Hi,
I am trying to train using your codes for small basal ganglia regions using my dataset and trying to replicate what you did.
For the moment, I use exactly as you did using 6 subjects for training and 1 subject for validation.
But I am unable to succeed. My final prediction image is very similar to the input T1 brain with some tiny contrast modification.
I tried using model_thresholding() as well as model().
I do not change the model. Should I?
Can you advise please?
Regards,
JMC
Hello , I wonder how I can run this project for my own dataset ?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.