deepmicroscopy / midog_reference_docker Goto Github PK
View Code? Open in Web Editor NEWReference implementation of domain-adversarial training on a RetinaNet (to use as template in the MIDOG challenge)
Reference implementation of domain-adversarial training on a RetinaNet (to use as template in the MIDOG challenge)
Hi,
When implementing this docker locally my code fails in the final stage of prediction on transforming the coordinates. E.g.:
world_coords = image_data.TransformContinuousIndexToPhysicalPoint(
[c for c in coord]
)
The following error is then given:
Traceback (most recent call last):
File "process.py", line 121, in <module>
Mitosisdetection().process()
File "/home/adams/anaconda3/envs/tf23/lib/python3.8/site-packages/evalutils/evalutils.py", line 183, in process
self.process_cases()
File "/home/adams/anaconda3/envs/tf23/lib/python3.8/site-packages/evalutils/evalutils.py", line 191, in process_cases
self._case_results.append(self.process_case(idx=idx, case=case))
File "process.py", line 74, in process_case
scored_candidates = self.predict(input_image=input_image)
File "process.py", line 105, in predict
world_coords = input_image.TransformContinuousIndexToPhysicalPoint(
File "/home/adams/anaconda3/envs/tf23/lib/python3.8/site-packages/SimpleITK/SimpleITK.py", line 3264, in TransformContinuousIndexToPhysicalPoint
return _SimpleITK.Image_TransformContinuousIndexToPhysicalPoint(self, index)
TypeError: in method 'Image_TransformContinuousIndexToPhysicalPoint', argument 2 of type 'std::vector< double,std::allocator< double > > const &'
Please can someone advise? Thanks for your help.
Bets wishes,
Adam Shephard
Hi, will the training code be provided ? I am wondering whether the original training data is processed the same as the test data (in this repository, create overlapping patches for the whole image). Or directly resize to 512*512
Hi,
Is the test set of MIDOG 2021 available now that the challenge is over? How can I access it?
Or how can I test my model on the test set?
Thanks
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.