Muran337287

some questions about char2wordBB and the generated text

2

1. I don't understand the function char2wordBB, what's the meaning of "cc = np.squeeze(np.concatenate(np.dsplit(cc,cc.shape[-1]),axis=1)).T.astype('float32')" and " cc_tblr"? Someone can help me? 2. I met some cases with the generated text....

prob question

1

``` preds0, preds1 = MORAN(image, length, text, text_rev, test=True) cost = criterion(torch.cat([preds0, preds1], 0), torch.cat([text, text_rev], 0)) preds0_prob, preds0 = preds0.max(1) preds0 = preds0.view(-1) preds0_prob = preds0_prob.view(-1) sim_preds0 = converter.decode(preds0.data,...

Does it support stride=(2,1) for DCNv2?

IoU threshold in IoU Net

2

Hi, in your paper, predicted boxes with IoU larger than 0.5 will be fed into IoUNet. I have a question that did you have a try to set the threshold...

I want to use it to compute parameters and memory for my model, but my model needs other things to input, how can I input the arguments?

Hi, can you tell me how to obtain lexicon for each dataset? download or generate?