Kaggle-Carvana-Image-Masking-Challenge

Kaggle-Carvana-Image-Masking-Challenge copied to clipboard

train_mask.csv does not exist

1

Hello, i prepared all the Training and masks into the Right Folders. When i run the Network, the following Error ocurs: " IOError: [Errno 2] File Input/Train_masks.csv does not exist:...

mrtalkingbadger

@metakermit thanks for your sharing. There is a problem i can not figure it out: when i run predict_multithreaded.py, i found the code go into a dead loop in the...

whrenstone

Correct architecture for lots of small objects?

3

Hello, I have a question regarding the architecture. I have images like this example, and want to do image segmentation for the white spots.  Do I understand it correctly,...

fschi

Getting StopIteration error

7

Hey,I am getting a StopIteration error when valid_generator( ) is called .The error is given below StopIteration Traceback (most recent call last) in () 6 #callbacks=callbacks, 7 validation_data=valid_generator(), ----> 8...

shivam-chandhok

Thanks for sharing your work, but I have a problem in the loss function. In dice_coeff, y_true is a label, but y_pred is a probility, what does dice_coeff mean? I...

lizhiyuanUSTC

How long does it for training with 128/256/512/1024 for your training epoch = 50?

2

heroxrq

get 0.995 with 1024 * 1024

3

have changed the batch size to 1, any suggestion?

CanoeFZH

Add hue-saturation-value data augmentation, converge slower?

1

I find add hue-saturation-value data augmentation, SGD converge becomes slower?

heroxrq