Open fcivardi opened 7 years ago
It seems I have the same problem reported here: https://github.com/Microsoft/CNTK/issues/1369 but I'm training using python, how can I specify grayscale=True in the Python trainer?
I tried deserializer['grayscale'] = True, suggested here: https://github.com/Microsoft/CNTK/issues/1172 but nothing changed.
Try:
cntk.io.MinibatchSource(cntk.io.ImageDeserializer(map_file, cntk.io.StreamDefs(
features = cntk.io.StreamDef(field='image', transforms=transforms),
labels = cntk.io.StreamDef(field='label', shape=num_classes))),
grayscale = True,
randomize=is_training)
With that I get this error: TypeError: init() got an unexpected keyword argument 'grayscale' I'm using beta10.
That's a bug. We will fix it.
By the way, because my images are 16bit grayscale instead of 8bit , do you know if the issue below has been fixed in the current code: https://github.com/Microsoft/CNTK/issues/961 ? MartIgap proposed to fix it, but I don't now if it has been done. Maybe my problem is affected by both flags that should be defined in the Reader (grayscale, and CV_LOAD_IMAGE_ANYDEPTH for opencv) . Could you also tell me when the fix will be available? Thanks
Any updates on this bug fix?
No update since december 2017, what is the status of this?
To score new images and print the probability of the class being 1 (it's a binary classifier), I've written this code:
but it always returns the same classification, [1.0 1....e-17] , even for images in the test set, where the Training Error was very low. Images are grayscale png (0-65535), and I trained the model using the CNTK reader (so it expects a color axis). Am I doing something wrong?