 Stephen
|
246fd93525
adam changed
|
2 лет назад |
|
Stephen
|
240cf851b9
Changed radom number generator objects to old functions.
|
2 лет назад |
|
Stephen
|
9907b2f345
Starting to oldify unet for the supercomputer.
|
2 лет назад |
|
Stephen
|
54f869a113
Messed up. Need TPR and FPR. Started making roc curve stuff.
|
3 лет назад |
|
Stephen
|
694f95636d
Created helper functions to make main clearer. Created a new conda environment.
|
3 лет назад |
|
Stephen
|
21d2def447
Made the confusion mask apply to a single image.
|
3 лет назад |
|
Stephen
|
3ee36b9901
Increased the color intensity of the color masks.
|
3 лет назад |
|
Stephen
|
bf3ed43398
Successfullyy created the false positive mask.
|
3 лет назад |
|
Stephen
|
76c79266c7
COmmented out the reza unet sections.
|
3 лет назад |
|
Stephen
|
a470d5c239
Added reza azad's unet file. It doesn't work yet though. It expects inputs of only int32 but my net works on float64.
|
3 лет назад |
|
Stephen
|
ad00dbd741
Added the reza azad unet for later testing. Need to change its input size. Currently it takes only grascale images as input at size 256x256.
|
3 лет назад |
|
Stephen
|
f5c20f6a41
Found bug in standard unet. 16 was in place of a variable.
|
3 лет назад |
|
Stephen
|
88bbedfd7c
Switched to jaccard accuracy score for the monitor. Also saved originals with the output images.
|
3 лет назад |
|
Stephen
|
8d24d9184b
Added some printing if statements to clean things up. Added some metrics to the model.
|
3 лет назад |
|
Stephen
|
116af0efce
This version makes the correctly predicted white pixels get a red mask image saved to file. Good results start at 3 epochs in terms of redness.
|
3 лет назад |
|
Stephen
|
ad4a3d2608
I made a hack to fix the boundary box sizes. The PILLOW function image.paste(im, sizewhatever) seems to be bugged? Or maybe my pictures are strange in some way. To be clear, occasionally image.getbbox() returns something other than (0, 0, width, height), (width, height) come from image.size.
|
3 лет назад |
|
Stephen
|
a63b55f1ef
Currently getting a weird error where the image.getbbox() function returns a different size than image.size; BUT ONLY FOR INVERTED IMAGES!
|
3 лет назад |
|
Stephen
|
551469d2d8
Ok, the Autoinit thing was messing things up. Working again.
|
3 лет назад |
|
Stephen
|
e87dda9966
Something is very wrong. The program no longer creates good outputs.
|
3 лет назад |
|
Stephen
|
06e0d9860f
Commented out autoinit for now. About to start going ham on this code.
|
3 лет назад |
|
Stephen
|
a52787b597
Added note to remind myself to change the background setting after I fix the foreground/background issue.
|
3 лет назад |
|
Stephen
|
81189b7f7a
Updated TODO.
|
3 лет назад |
|
Stephen
|
61611d84f4
Updated TODO list.
|
3 лет назад |
|
Stephen
|
c33ab62fac
Added the AutoInit thingy. Tested to see it work. Must do tests to see what effect it has.
|
3 лет назад |
|
Stephen
|
007429a02e
Implemented a function to create a mask of the prediction with the truth-- Areas in both are shown. Also, I discovered that my model is technically finding the background instead of the foreground. It shouldn't matter much technically, but it explains some of the weird issues I've been having.
|
3 лет назад |
|
Stephen
|
80e5619d56
Remembered to use the clever way of multiplication elementwise.
|
3 лет назад |
|
Stephen
|
dabe7d428f
Created mask function to output a mask of the whole predicted images.
|
3 лет назад |
|
Stephen
|
d6745445cf
update todo
|
3 лет назад |
|
Stephen
|
2952a1b013
Added jaccard and dice accuracy score calculations for the predicted full sized images.
|
3 лет назад |
|
Stephen
|
2398085d44
Found the error. There was a high in the wide loop. line 595. lol. This version works to produce binarized images of any size!
|
3 лет назад |
