RayShark

Nice work! I wonder how to pass weights to this custom ASL loss, because our previous task used 'criterion = nn.BCEWithLogitsLoss(weight=self.y_pos_weight)'. Can you give some advice on handling the weights...

Does this tool support chinese?

1

I just wondering whether this tool support chinese corpus. For example, do i suppose to use Jieba or other chinese tokenizer ? And is there interface reserved for chinese tokenizer......

Traceback (most recent call last): File "/Users/druw_shark/PycharmProjects/keras-zhihu-master-ForEasyDeepLeaning/zhihu.py", line 179, in cropModel = load_model(crop_model) File "/Library/Python/2.7/site-packages/keras/models.py", line 280, in load_model model.optimizer.set_weights(optimizer_weight_values) File "/Library/Python/2.7/site-packages/keras/optimizers.py", line 79, in set_weights 'provided weight shape '...