shahinshh / covid-fact Goto Github PK
View Code? Open in Web Editor NEWA Fully-Automated Capsule Network-based Framework for Identification of COVID-19 Cases from Chest CT scans
A Fully-Automated Capsule Network-based Framework for Identification of COVID-19 Cases from Chest CT scans
Hi and thank you for your code!
I am trying to run the indentification script, but running into a reshape error. My test input is two DICOM file of a lung scan with the shape of 512x512
. The error code I am running into is
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 1048576 values, but the requested shape has 32768
[[node functional_1/capsule_1/Reshape (defined at COVID-FACT_binary_test.py:123) ]] [Op:__inference_predict_function_1338]
Errors may have originated from an input operation.
Input Source operations connected to node functional_1/capsule_1/Reshape:
functional_1/capsule_1/convolution/Squeeze (defined at COVID-FACT_binary_test.py:114)
Function call stack:
predict_function
Thanks a lot for sharing code! I've read the papers about the dataset and model. But I'm still confused about how to use the unlabeled subset to develop the second stage of the model. May I get the training code? Thanks again!
[email protected]
Hi everyone,
I have installed COVID-FACT on Ubuntu 18
when I was running the python script I got the following message:
Using TensorFlow backend.
Illegal instruction (core dumped)
Any advice ?
Thanks
Jaafar
First of all, I want to thank you for the code provided and the effort put into it.
I have encountered the reshape problem that was already raised as an issue, so I followed your proposed fix and downgraded the version of keras and tensorflow to those mentioned in the README (tensorflow 1.14.0 and keras 2.2.4), however another problem was raised when instantiating the 'Capsule' class, the problem is as follows:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/tensor_util.py in make_tensor_proto(values, dtype, shape, verify_shape, allow_broadcast)
557 try:
--> 558 str_values = [compat.as_bytes(x) for x in proto_values]
559 except TypeError:
26 frames
TypeError: Expected binary or unicode string, got 1
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/tensor_util.py in make_tensor_proto(values, dtype, shape, verify_shape, allow_broadcast)
560 raise TypeError("Failed to convert object of type %s to Tensor. "
561 "Contents: %s. Consider casting elements to a "
--> 562 "supported type." % (type(values), values))
563 tensor_proto.string_val.extend(str_values)
564 return tensor_proto
TypeError: Failed to convert object of type <class 'tuple'> to Tensor. Contents: (1, Dimension(128), 512). Consider casting elements to a supported type.
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.