rongyixiao

Hello, # view pairs with max OKSs as match ones, add to oks_all oks_all = np.concatenate((oks_all, np.max(oks, axis=1)), axis=0) # accumulate total num by max(gtN,pN) oks_num += np.max(oks.shape) is there...

Regularization

2

hello,I'd like to ask: bulk_feat = Dense(CATES, use_bias=True, activity_regularizer=regularizers.l1(0), activation=softmax)(cfeat) According to the paper should be like this: bulk_feat = Dense(CATES, use_bias=True, kernel_regularizer=regularizers.l1(1.0), activation=softmax)(cfeat) And there should be some adjustment...

About facal loss?

3

Hello, does facal loss address data imbalance? if data is balance, is facal loss useless? In this case, loss in the original paper should be adopted?