Nanubala Gnana Sai

If you won't mind, I'd like to take a stab at this. I've found a [repo](https://github.com/howl-anderson/tf_crf_layer) which implements CRF Loss. CRF Loss: https://github.com/howl-anderson/tf_crf_layer/blob/master/tf_crf_layer/loss/crf_loss.py CRF Accuracy: https://github.com/howl-anderson/tf_crf_layer/blob/master/tf_crf_layer/metrics/crf_accuracy.py A bit of polish,...

Okay, I did some research on this. Thing is, the loss function doesn't solely depend on y_true and y_pred but also the internal variables. So, we **can't use eager tensor**...

Hi! May I take this up?

I think our current implementation is wrong, it uses one vs all for getting Matthew's coefficient for each class. Instead, it should've used the generalized Matthew's Formula(for Multi & binary)...

I was meaning to implement this myself but since nobody was replying I reconsidered if I was permitted to do it(and whether you were interested still) . Regardless, I'm happy...

@WindQAQ I was wondering, how about we keep them both? That is, Matthew correlation in one vs all method & the [actual method](https://en.wikipedia.org/wiki/Matthews_correlation_coefficient#Multiclass_case) using a boolean switch?

> Hi, Everyone. Since we have this fix in the merge queue, I was wondering if the stable version's (`0.12.1`) MCC for Multiclass is implemented correctly or not. Shall I...

Smells like #5139. I'll add this to my list. Although, I'm a bit worried about its implications in SWIG interfaces.

@gf712 This issue seems stale, shall I take it up? I've already done 80% of the work. Some unit tests and integration tests are failing that's all.

@Jia1018 I've already made the changes in my PR. If you want, you can copy my PR and modify it a bit to answer the build failure. I'll close my...