TypeError: Value passed to parameter 'shape' has DataType float32 not in list of allowed values: int32, int64

[FankLi]

运行这个（021-文章标题的自动生成.py）的时候报错，如题 我的环境是python3.6,tensorflow==1.8.0,keras==2.2.4 期待你的回复，谢谢

[FankLi]

是运行到这一行报的错：

编码 两层双向的LSTM

x = Bidirectional(LSTM(char_size / 2, return_sequences=True))(x)

[shawroad]

是运行到这一行报的错：

编码 两层双向的LSTM

x = Bidirectional(LSTM(char_size / 2, return_sequences=True))(x)

能不能把报错说详细点？　　不知道你什么意思

[FankLi]

是运行到这一行报的错：

编码 两层双向的LSTM

x = Bidirectional(LSTM(char_size / 2, return_sequences=True))(x)

能不能把报错说详细点？　　不知道你什么意思

报错详情如下： Traceback (most recent call last): File "/Users/xiaoli/PycharmProjects/NLP-Project/021-文章标题的自动生成.py", line 145, in <module> x = Bidirectional(LSTM(char_size / 2, return_sequences=True))(x) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/layers/wrappers.py", line 427, in __call__ return super(Bidirectional, self).__call__(inputs, **kwargs) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/engine/base_layer.py", line 431, in __call__ self.build(unpack_singleton(input_shapes)) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/layers/wrappers.py", line 567, in build self.forward_layer.build(input_shape) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/layers/recurrent.py", line 493, in build self.cell.build(step_input_shape) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/layers/recurrent.py", line 1868, in build constraint=self.kernel_constraint) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper return func(*args, **kwargs) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/engine/base_layer.py", line 249, in add_weight weight = K.variable(initializer(shape), File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/initializers.py", line 218, in __call__ dtype=dtype, seed=self.seed) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 4139, in random_uniform dtype=dtype, seed=seed) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/tensorflow/python/ops/random_ops.py", line 247, in random_uniform rnd = gen_random_ops.random_uniform(shape, dtype, seed=seed1, seed2=seed2) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/tensorflow/python/ops/gen_random_ops.py", line 820, in random_uniform name=name) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 630, in _apply_op_helper param_name=input_name) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 60, in _SatisfiesTypeConstraint ", ".join(dtypes.as_dtype(x).name for x in allowed_list))) TypeError: Value passed to parameter 'shape' has DataType float32 not in list of allowed values: int32, int64

[shawroad]

是运行到这一行报的错：

编码 两层双向的LSTM

x = Bidirectional(LSTM(char_size / 2, return_sequences=True))(x)

能不能把报错说详细点？　　不知道你什么意思

报错详情如下： Traceback (most recent call last): File "/Users/xiaoli/PycharmProjects/NLP-Project/021-文章标题的自动生成.py", line 145, in <module> x = Bidirectional(LSTM(char_size / 2, return_sequences=True))(x) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/layers/wrappers.py", line 427, in __call__ return super(Bidirectional, self).__call__(inputs, **kwargs) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/engine/base_layer.py", line 431, in __call__ self.build(unpack_singleton(input_shapes)) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/layers/wrappers.py", line 567, in build self.forward_layer.build(input_shape) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/layers/recurrent.py", line 493, in build self.cell.build(step_input_shape) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/layers/recurrent.py", line 1868, in build constraint=self.kernel_constraint) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper return func(*args, **kwargs) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/engine/base_layer.py", line 249, in add_weight weight = K.variable(initializer(shape), File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/initializers.py", line 218, in __call__ dtype=dtype, seed=self.seed) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 4139, in random_uniform dtype=dtype, seed=seed) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/tensorflow/python/ops/random_ops.py", line 247, in random_uniform rnd = gen_random_ops.random_uniform(shape, dtype, seed=seed1, seed2=seed2) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/tensorflow/python/ops/gen_random_ops.py", line 820, in random_uniform name=name) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 630, in _apply_op_helper param_name=input_name) File "/anaconda3/envs/NLP-Project/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 60, in _SatisfiesTypeConstraint ", ".join(dtypes.as_dtype(x).name for x in allowed_list))) TypeError: Value passed to parameter 'shape' has DataType float32 not in list of allowed values: int32, int64

这是可能是数据的类型有问题吧。。 你去keras_learning_process这个仓库中去看标题生成的代码。。这个代码应该没问题吧。。 最近很忙，没时间帮你调代码。。

[FankLi]

感谢你抽空的回复，keras_learning_process这个跑通了，infer的结果很不理想，如下所示，请问你的结果怎么样呢？

Epoch 100/100 。。。。。。。。 1000/1000 [==============================] - 2213s 2s/step - loss: 0.8461 复活天快天负！还发射不能复出请回射及副业长 1月0日战中，方式8LMML光，报争开脸

[shawroad]

不好意思，我最近特别忙 。。没有时间跑代码给你排错

发件人：FankLi [email protected] 发送时间：2019年7月22日(星期一) 09:31 收件人：shawroad/NLP-Project [email protected] 抄　送：shawroad [email protected]; Comment [email protected] 主　题：Re: [shawroad/NLP-Project] TypeError: Value passed to parameter 'shape' has DataType float32 not in list of allowed values: int32, int64 (#4)

感谢你抽空的回复，keras_learning_process这个跑通了，infer的结果很不理想，如下所示，请问你的结果怎么样呢？ Epoch 100/100 。。。。。。。。 1000/1000 [==============================] - 2213s 2s/step - loss: 0.8461 复活天快天负！还发射不能复出请回射及副业长 1月0日战中，方式8LMML光，报争开脸 — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or mute the thread.

[shawroad]

感谢你抽空的回复，keras_learning_process这个跑通了，infer的结果很不理想，如下所示，请问你的结果怎么样呢？

Epoch 100/100 。。。。。。。。 1000/1000 [==============================] - 2213s 2s/step - loss: 0.8461 复活天快天负！还发射不能复出请回射及副业长 1月0日战中，方式8LMML光，报争开脸

其实，这只适合学习。。实际项目中，这样做还是远远不够的。。 建议你在增加数据集。。因为我的数据集太小。。。