search

reachsumit / deep-unet-for-satellite-image-segmentation

Satellite Imagery Feature Detection with SpaceNet dataset using deep UNet
309 stars 139 forks source link

how to show the data? #9

Closed swpucl closed 5 years ago

HetSP07 commented 5 years ago

I think you can use this code https://github.com/ternaus/kaggle_dstl_submission/blob/master/src/visualize.py

reachsumit commented 5 years ago

You can use tifffile to display image in an interactive environment like Jupyter notebooks. You may want to use just the RGB bands depending on your case. And, you could also colorize the outcomes like this: https://github.com/reachsumit/deep-unet-for-satellite-image-segmentation/blob/master/predict.py#L47.

swpucl commented 5 years ago

You can use tifffile to display image in an interactive environment like Jupyter notebooks. You may want to use just the RGB bands depending on your case. And, you could also colorize the outcomes like this: https://github.com/reachsumit/deep-unet-for-satellite-image-segmentation/blob/master/predict.py#L47.

Thank you for your advice.But now I can only show grayscale images.my code like this: img = tiff.imread('test.tif') tiff.imsave('result.tif', img.astype('uint8'))