Closed kei6 closed 5 years ago
we normalized all data to common format, ours gt start with bottom left.
neděle 2. června 2019 Kei_Cin notifications@github.com napsal(a):
I'm going deeper to your repo and I cannot understand this below code: https://github.com/MichalBusta/E2E-MLT/blob/28583581fb17b6e83bc8dc8c84b6bc 7fb4957341/data_gen.py#L122-L123
I've checked some examples with this and find out that will shift an array liked: [1224. 2041. 1537. 2041. 1537. 2134. 1224. 2134.] into: [1224. 2134. 1224. 2041. 1537. 2041. 1537. 2134.]
I know how numpy.roll function works, but I don't understand why you did it only for ICDAR dataset. Can you help to explain this? Thanks,
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/MichalBusta/E2E-MLT/issues/36?email_source=notifications&email_token=AA7KHMGJS4OQ7QZF53A4XKDPYSIM7A5CNFSM4HSEM5ZKYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4GXGAQUQ, or mute the thread https://github.com/notifications/unsubscribe-auth/AA7KHMHXTF6QMWNCEM76TVLPYSIM7ANCNFSM4HSEM5ZA .
Thanks for this quick explanation! It is really important information if anyone wants to train your network with their own data, they need to make sure the data format start with bottom left.
I'm going deeper to your repo and I cannot understand this below code: https://github.com/MichalBusta/E2E-MLT/blob/28583581fb17b6e83bc8dc8c84b6bc7fb4957341/data_gen.py#L122-L123
I've checked some examples with this and find out that will shift an array liked:
[1224. 2041. 1537. 2041. 1537. 2134. 1224. 2134.]
into:[1224. 2134. 1224. 2041. 1537. 2041. 1537. 2134.]
I know how numpy.roll function works, but I don't understand why you did it only for ICDAR dataset. Can you help to explain this? Thanks,