CRAFT-pytorch
CRAFT-pytorch copied to clipboard
clovaai
Official implementation of Character Region Awareness for Text Detection (CRAFT)
Some of the text I am detecting is on an angle. How should I go about cropping around the text in the bounding box and rotating the image so that...
Hello，I want to know how to convert pre-trained model ( craft_refiner_CTW1500.pth ) to onnx ?
I test 800 * 800 pictures, each takes 0.8s on average. Is this normal time?Looking forward to your reply
Thanks for the repo. CRAFT works really well with the test data I have. Without using RefineNet, we are able to generate word-level texts, which is what we need before...
Hi @YoungminBaek, @ClovaAIAdmin, Thank you for your good work. If it is okay, can you share your training details on your "general model"? For your "General model", how many images...
Even though, it isnt possible to release the training code due to copyright reasons. Is there any code or possibility that there will be some code using which can finetune...
Hello Can I use the source code and trained models introduced in this repo (General, IC15 and LinkRefiner) for commercial purposes? Thank you,
Hey first of all great work there is too much too learn from this repo. Your work is appreciable. I have to do one thing in that i want help...
The size of the input image is 3024*4032, the recognition effect is not good, and the recognized text is very dense, is the recognition effect of the model on large-size...
Which parameter is used to change the distance between words. For ex. If I have 2 words close - CRAFT recognize it as 1 word. But I don't really like...
