I encountered an error when submitting the results, like this:Image size of /tmp/codalab/tmpNwJKdx/run/input/ref/ROIs0000_validation_dfc_0_p0.tif is different. My image size is the same as the image size in the original data set (256 * 256), I don't know what causes this error.
Posted by: LiYanPeng @ Jan. 17, 2020, 6:50 a.m.I have checked your submission. Each image has a size of 256x256x3 in your submission. It should be 256x256 (grayscale imagery). Pixel values should be between 1 to 10. The color table we listed is for visualization in manuscripts rather than submissions. I hope it will solve your problem.
Posted by: yky @ Jan. 17, 2020, 12:29 p.m.Thank you for your reply. The previous question has been resolved. I submitted a new prediction result. It is a grayscale image with a value range of 1-10 and an image size of 256 * 256, but it has caused a new one. The error is as follows:
WARNING: Your kernel does not support swap limit capabilities or the cgroup is not mounted. Memory limited without swap.
Traceback (most recent call last):
File "/tmp/codalab/tmpSCY7Bd/run/program/score.py", line 26, in
aa, ca = compute_metrics(truth_dir, submit_dir, html_file)
File "/tmp/codalab/tmpSCY7Bd/run/program/metrics_dfc2020.py", line 61, in compute_metrics
predict_cls_map = np.asarray(misc.imread(predict_map_pth)).astype(int)
TypeError: long() argument must be a string or a number, not 'TiffImageFile'
It seems that your TIFF files are not readable by scipy.misc.imread. As noted in "Participate>>Get Data", please make sure that all TIFF files are readable by scipy.misc.imread.
Posted by: yky @ Jan. 18, 2020, 12:14 a.m.