楼主的chat_bot_seq2seq_attention能跑起来吗？ #49
Comments
|
把beam_search相关的注释打开才行。。。 |
|
看起来中文的项目确实漏洞百出啊 |
predict跑起来了吗 |
能predict 起来。但绝对不是你想像中那样子： |
嗯嗯，跑起来了，训练数据都是英文的，输入中文的话不知道能不能理解，确实答非所问 |
请问tf版本是多少？我在predict出错了。 |
不是tf的问题，训练和预测时不要用beam_search（beam_search=False） |
|
好的，谢谢，我测试一下。
Davion <[email protected]> 于2019年12月17日周二 下午5:09写道：
… 把beam_search相关的注释打开才行。。。
predict跑起来了吗
能predict 起来。但绝对不是你想像中那样子：
第一，输入输出都是英文
第二，效果很差
嗯嗯，跑起来了，训练数据都是英文的，输入中文的话不知道能不能理解，确实答非所问
请问tf版本是多少？我在predict出错了。
报错如下：
2019-12-17 14:15:28.290374: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Input to reshape is a tensor with 1024 values, but the requested shape has 5120
[[Node: decoder/Reshape_4 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](decoder/AttentionWrapperZeroState/zeros_1, decoder/concat_4)]]
2019-12-17 14:15:28.290477: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Input to reshape is a tensor with 1024 values, but the requested shape has 5120
[[Node: decoder/Reshape_4 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](decoder/AttentionWrapperZeroState/zeros_1, decoder/concat_4)]]
2019-12-17 14:15:28.290502: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Input to reshape is a tensor with 1024 values, but the requested shape has 5120
[[Node: decoder/Reshape_4 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](decoder/AttentionWrapperZeroState/zeros_1, decoder/concat_4)]]
2019-12-17 14:15:28.290489: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Input to reshape is a tensor with 1024 values, but the requested shape has 5120
[[Node: decoder/Reshape_4 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](decoder/AttentionWrapperZeroState/zeros_1, decoder/concat_4)]]
2019-12-17 14:15:28.290570: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Input to reshape is a tensor with 1024 values, but the requested shape has 5120
[[Node: decoder/Reshape_4 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](decoder/AttentionWrapperZeroState/zeros_1, decoder/concat_4)]]
2019-12-17 14:15:28.290810: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Input to reshape is a tensor with 1024 values, but the requested shape has 5120
[[Node: decoder/Reshape_4 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](decoder/AttentionWrapperZeroState/zeros_1, decoder/concat_4)]]
2019-12-17 14:15:28.290841: W tensorflow/core/framework/op_kernel.cc:1192] Invalid argument: Input to reshape is a tensor with 1024 values, but the requested shape has 5120
[[Node: decoder/Reshape_4 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](decoder/AttentionWrapperZeroState/zeros_1, decoder/concat_4)]]
Traceback (most recent call last):
File "/home/zsq/anaconda3/envs/tf1.4/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1323, in _do_call
return fn(*args)
File "/home/zsq/anaconda3/envs/tf1.4/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1302, in _run_fn
status, run_metadata)
File "/home/zsq/anaconda3/envs/tf1.4/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 473, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 1024 values, but the requested shape has 5120
[[Node: decoder/Reshape_4 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](decoder/AttentionWrapperZeroState/zeros_1, decoder/concat_4)]]
[[Node: encoder/rnn/All/_55 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_69_encoder/rnn/All", tensor_type=DT_BOOL, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
不是tf的问题，训练和预测时不要用beam_search（beam_search=False）
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#49?email_source=notifications&email_token=AGXLCIRC6VPUKAIADZNTX3DQZCJNTA5CNFSM4JI3OYM2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEHBVY3I#issuecomment-566451309>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AGXLCIVYI6IZVSSJR2ZID3TQZCJNTANCNFSM4JI3OYMQ>
.
--
Best regards,
Shengqiang
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
发现一些小错啊？
比如：
train.py 中的
“model.restore(sess, ckpt.model_checkpoint_path)”
应改为：
"model.saver.restore(sess, ckpt.model_checkpoint_path)"
predict.py 中的
from data_helpers import loadDataset, getBatches, sentence2enco
应改为：
from data_loader import loadDataset, getBatches, sentence2enco
predict跑起来还有其它一屏又一屏的错，我只是想问一下楼主，是否真能跑起来？
The text was updated successfully, but these errors were encountered: