lazerliu
lazerliu
@YunYang1994 Hi,I wonder whether the 'with tf.GradientTape() as tape' is necessary,we just want to do forward,while "tape" is to tape the cache to do backpropagation and it'll make some expensive...
请问你是训练的作者的yymnist，还是自己的数据集？
> > 请问你是训练的作者的yymnist，还是自己的数据集？ > > 都测试了 自己的数据集，训练效果怎么样，我用的VOC2007，epoch更改为120，其他设置不变，mAP只有20,，，，
same warning,and canot load things from remote tensorborad server
the same error while infering data2vec-asr, have you fixed it in fairseq?
the same question with Audio. While inverse_mask is an important role in paper, the "model.modalities.audio.inverse_mask" in "example/data2vec/config/v2/base&large_audio_only_task.yaml" is false in default official code.