search

xinwucwp / faultSeg

Using synthetic datasets to train an end-to-end CNN for 3D fault segmentation (We are working on an improved version!)
223 stars 136 forks source link

Whether Inline, Crossline and Time is even？ #13

Closed 1197155807 closed 2 years ago

1197155807 commented 3 years ago

Dear Dr. Wu I would like to ask if there are any requirements for Inline, Crossline and Time in predicting faults on my own data set. Whether it must be an even number or 2 to the power of n？

Is there a limit to the size of the predicted data？

Thanks again.

humbertogeologia commented 3 years ago

Hi, fantastic piece of work. The result "fp.dat" can be converted to sgy? If yes can you please tell me how to do it with python? My aim is to import the results to petrel or opendtect

augustoicaro commented 3 years ago

@humbertogeologia, please see the snippet in https://github.com/xinwucwp/faultSeg/issues/2#issuecomment-550130689.

Best,

llmpass commented 2 years ago

Dear Dr. Wu I would like to ask if there are any requirements for Inline, Crossline and Time in predicting faults on my own data set. Whether it must be an even number or 2 to the power of n？

Is there a limit to the size of the predicted data？

Thanks again.

To feed the data into the current Unet structure, the size of the cube must be divisible of 8. However, you can always cut your data into such pieces before feeding them into the network.