Jonah Turner

I have tried every single package attempting to find a solution like this and none work well. I will write the most flattering Medium article ever written if you get...

Thank you for typing this up, Tong! I am hoping to use [PARSeq](https://github.com/baudm/parseq) for text recognition and will be following the steps you laid out here. I am looking forward...

@Mekacher-Anis No, I've just finished finetuning PARSeq. I'm leaning towards DBNet++ for detection, but I haven't even tried finetuning it yet. I should be making more progress this week and...

@Mekacher-Anis Wow, that is very clean. I was planning to just keep my detection and recognition fairly separate, but your implementation is inspiring! Thank you for your work on this

@huyhoang17 I would love to see your code for ONNX inference, I am very interested in and impressed by your speedtesting!

@huyhoang17 I can't manage to get the same values out of ONNX inference, and I'm wondering if it is because of my older pytorch version. Are you getting identical inference...

@phamkhactu There seems to be a common method to send the input to numpy, it works for me. I would be very interested to hear if your inference results are...

Hi! Any updates here? I'm trying to transition a TabularPredictor trained on GPU to CPU for inference (by setting no CUDA_VISIBLE_DEVICES) and am getting the following error 

@sxjscience The MultimodalPredictor (thanks @Innixma , quite right) I was trying to use had a TextPredictor component. That's why it failed when taking over to CPU? Could I skip loading...

@sxjscience Yes, I was loading a saved TabularPredictor with these models  The model loaded on CPU but errored on inference.