Aggregation-Cross-Entropy

Aggregation-Cross-Entropy copied to clipboard

loss decline but accuracy near to 0

5

I train a model(CRNN) base on dataset synth90k, through the loss decline step by step, the accuracy is near to 0 all the time. What casue this problem?

bjlgcxc

是否可以用在中文OCR上面呢

2

s1162276945

Can’t reproduce your results in your cvpr paper

3

I reproduced crnn+ctc and test it on IIIT5K+SVT+IC03+IC13 test database, got WER 0.153, which is same as the reported results in paper. I also reproduced crnn+ace loss, but only got...

yflv-yanxia

It doesn't work on my data, why don't you provide a pretrained model?

5

I pretrained a model using ctcloss and it works well. Then I loaded the weights and continued to train with the aceloss. The losses seemed to be coming down, but...

LJXLJXLJX

Hi, have you experimented on HWDB 2.0-2.2, could you share your results for ACE? Thanks

DietDietDiet

Use ACE loss for English handwriting recognition，but not converge

2

I use the ACE loss function to do English handwriting recognition. When the model is trained, it does not converge, but with CTC, it gets a good convergence effect. How...

liudatutu

combined with CTC?

1

Very nice work, can this method combine with CTC in 1D case to improve performace further? does it conflict with CTC when training?

liangzimei

对general loss function为何可以通过第3节的公式（2）来估计？估计公式中的每一项概率不是远大于general loss function中的对应项吗？

yyr6661

in https://github.com/summerlvsong/Aggregation-Cross-Entropy/blob/master/source/models/seq_module.py#L65, should it be pred_string_set = [pred_string[i:i+self.w] for i in xrange(0, len(pred_string), self.w)] instetad of self.w*2? please verify. Thanks

shanenian

As the model can only recognize the characters and characters' number, so what's the accuracy criterion for 2D prediction in the paper?

Cherway