orobix / retina-unet

Retina blood vessel segmentation with a convolutional neural network

orobix/retina-unet Issues

semi-supervised learning
Updated 7 months ago
Assertion Error
Updated a year ago3
Trouble with model architecture
Updated a year ago1
U-net Architecture of expansion path
Updated 2 years ago1
I really doubt the evaluation metric auc curve is not favorable?
Updated 2 years ago1
RGB vs Grayscale
Updated 2 years ago1
Any subsequent image repair work
Updated 2 years ago
Process finished with exit code -1073740791 (0xC0000409)
Updated 2 years ago1
ImportError: cannot import name 'jaccard_similarity_score'
Updated 2 years ago1
Keras and tf version
Updated 2 years ago2
Prediction of a general fundus image from hospital
Updated 3 years ago3
Why i am getting less performance than yours?
Updated 3 years ago
For those who are interested in the theoretical part of this code... the article's title of this code is "Retina Blood Vessel Segmentation Using A U-Net Based Convolutional Neural Network".
Closed 3 years ago
Could not get the files after running training code
Updated 3 years ago3
please help "ImportError: No module named visualize_util
Updated 3 years ago
How to python run_training.py ?
Updated 3 years ago
version
Updated 3 years ago
how to train on my own database
Updated 3 years ago1
Why is there no 1st_manual and 2nd_manual under test file after I download the DIRVE?
Updated 3 years ago4
how to create overlapping patches from images
Updated 3 years ago
TypeError: float() argument must be a string or a number, not 'TiffImageFile'
Closed 4 years ago2
AttributeError: module 'tensorflow' has no attribute 'python'
Updated 4 years ago1
errors in Windows+tensorflow_GPU environment
Updated 4 years ago3
how to train on other database?
Updated 4 years ago
Is your maxpooling layer wrong?
Updated 4 years ago2
can't find sample_input_imgs
Closed 4 years ago
only the configuration.txt file is available in the resulting test folder
Updated 5 years ago
Prediction for a single image
Updated 5 years ago
Produce the segmentation for a whole image.
Updated 5 years ago
The model is not trainable
Updated 5 years ago
Training taking too long
Updated 5 years ago2
How to do test_border_masks of STARE
Updated 5 years ago
What kind of upsamling is used here
Updated 5 years ago
error about data_format
Updated 5 years ago
a question about building the net
Updated 5 years ago
Please Specify Keras and TF versions
Updated 5 years ago2
Annotation tool used?
Updated 5 years ago3
ValueError: Unknown layer: Merge
Updated 6 years ago3
concatenate axis=1
Updated 6 years ago
share data
Updated 6 years ago
when excute the run_testing.py ,i have a problem,it said ======== Evaluate the results ======================= Calculating results only inside the FOV: y scores pixels: 2429685 (radius 270: 270*270*3.14==228906), including background around retina: 6599200 (584*565==329960) y true pixels: 2429685 (radius 270: 270*270*3.14==228906), including background around retina: 6599200 (584*565==329960) Traceback (most recent call last): File "./src/retinaNN_predict.py", line 183, in <module> precision, recall, thresholds = precision_recall_curve(y_true, y_scores) File "/home/liushixin/anaconda3/lib/python3.6/site-packages/sklearn/metrics/ranking.py", line 441, in precision_recall_curve sample_weight=sample_weight) File "/home/liushixin/anaconda3/lib/python3.6/site-packages/sklearn/metrics/ranking.py", line 318, in _binary_clf_curve raise ValueError("{0} format is not supported".format(y_type)) ValueError: continuous format is not supported
Closed 6 years ago2
can not work under win system
Updated 6 years ago
3D images and channel 1
Updated 6 years ago
Memory error
Updated 6 years ago1
what is masks_Unet in line 190 of retinaNN_training.py
Updated 6 years ago1
ImportError: cannot import name concatenate
Updated 6 years ago2
Update keras code
Updated 6 years ago2
Why did you use "softmax" and "categorical_crossentropy"?
Updated 6 years ago4
Dimension 1 in both shapes must be equal, but are 12 and 24 for 'merge_1/concat'
Updated 6 years ago4
ValueError: CorrMM images and kernel must have the same stack size
Updated 7 years ago