mlm22222


大佬，受累问一下，损失函数逐步收敛到3.3左右突然上升到4.1，是adam的问题还是其他问题

1

 我学习率和batch_size都调了，还是这样

大佬问一下tensor2，怎么解决contrib_tpu的问题

2

from tensorflow.contrib import tpu as contrib_tpu ModuleNotFoundError: No module named 'tensorflow.contrib'

请问一下运行eval时报的错，怎末处理

3

Traceback (most recent call last): File "D:/Text-Summarizer-Pytorch-Chinese-master/eval.py", line 171, in eval_processor.evaluate_batch(True) File "D:/Text-Summarizer-Pytorch-Chinese-master/eval.py", line 78, in evaluate_batch start_id, end_id, unk_id) File "D:\Text-Summarizer-Pytorch-Chinese-master\beam_search.py", line 179, in beam_search sum_temporal_srcs_i, prev_s_i).type(T.long) File "D:\Text-Summarizer-Pytorch-Chinese-master\beam_search.py",...

大佬，受累问一下，损失函数逐步收敛到3.3左右突然上升到4.1，是adam的问题还是其他问题

1

 我学习率和batch_size都跳了，还是这样

if len(ctx_list) == 1: TypeError: object of type 'Context' has no len()

1

大佬，问一下gpu_Xs = gutils.split_and_load(X, ctx, even_split=False)报错是什莫情况

大佬，问一下readme中提到的这两个文件没有啊