Atul Shukla
Atul Shukla
@lucidrains Thanks . How the data will look like in terms of json file such as two different json or single json containing annotation for both the different head classes?
Thanks for open-sourcing this wonderful library. I am waiting for the feature to add vocabulary or words at the runtime. Thanks
Thanks for ur reply, but i reslove this earlier at my end 😊 -Atul On 17-Nov-2017 4:29 AM, "Ricardo Barona" wrote: > Hi @Atul997 , > > The script is...
What exact problem u r facing ?? On 25-Jan-2018 12:20 PM, "Yashaswini Bhat" wrote: > Hi @Atul997 , > > I have similar issue. > How did you resolve it?...
Pls chk that image is inside the specified folder or not. Keep all the images inside a folder and then re-run the code. Hope it helps. ---- On Wed, Jul...
Your welcome☺️ On Sat, Jul 14, 2018, 1:22 PM Technebby wrote: > @Atul997 thanks for the valuable comment, i > was doing it wrong all together. it worked for me...
@wolfshow yes the accuracy of both models are good enough.
VIT backbone for both the models given in publaynet and icdar configs.
Well I can try but I don't want to include text in training just want to try with images only. Also if possible I can go with any one of...