基于栈式双向LSTM的情感识别 GPU训练报错 about book HOT 2 OPEN

动态rnn也报了一样的错：

Step 189, Epoch 0 Metrics [array([0.45252907], dtype=float32), array([0.8046875], dtype=float32)]
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py:782: UserWarning: The following exception is not an EOF exception.
"The following exception is not an EOF exception.")
Traceback (most recent call last):
File "SA_Test.py", line 231, in
main(use_cuda)
File "SA_Test.py", line 225, in main
infer(use_cuda, params_dirname)
File "SA_Test.py", line 213, in infer
return_numpy=False)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 783, in run
six.reraise(*sys.exc_info())
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/six.py", line 693, in reraise
raise value
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 778, in run
use_program_cache=use_program_cache)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 831, in _run_impl
use_program_cache=use_program_cache)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 902, in _run_program
self._feed_data(program, feed, feed_var_name, scope)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 580, in _feed_data
check_feed_shape_type(var, cur_feed)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py", line 230, in check_feed_shape_type
(var.name, len(var.shape), var.shape, feed_shape))
ValueError: The feeded Variable 'words' should have dimensions = 1, shape = (-1,), but received feeded shape [-1, 1] on each device

from book.

同样遇到这个问题。仔细对照了网页版，和最新的代码是有区别的。
shape = (-1,)的要求，可以把lod转换ndarray
生成lod_tensor之前，加一行
lod = np.array(sum(lod, []), dtype=np.int64)
这样就可以跑通

from book.