daniel_deng

I've redefine the network using placeholder for input and optimize by sess.run(optimizer) By this change I can save&load pb file successfully. https://github.com/danielkaifeng/TF_BERT_Chinese_Article_Auto_Generation

It takes time to load model and start session. if you use load_and_align_data only once at start, then the later prediction will be much faster.

could you please send me the model file? thanks! [email protected]

I‘ve play SinGAN for several days and curious about super resolution. In test pharse we feed the LR image into the last generator for several times, only the last generator...

I think the training process is loading last scale's G and D repeatedly, so the learning info is forward from very coarse level to the finest level. That's the reason...

Thank you! I will tried this out and give more feedback.

Could someone kindly upload the downloaded data to BaiduYun ?

I meet the same problem, my machine enviroment is: pytorch 1.3.1 CUDA 10.1 NVIDIA Driver Version: 430.64 python3.7.6 I follow the instruction above and helps me a lot. After I...

I am also waiting for answers on this. In deep Q learning, the target Qt is calculate as `target_q_t = (1. - terminal) * self.discount_r * max_q_t_plus_1 + reward`, which...

用的是不是tokenization/clue-vocab.txt？