小编Ahm*_*ium的帖子

当我尝试安装tensorflowjs_converter以将其转换model.h5为 json 文件时，它没有安装它，我曾经pip3 install tensorflowjs安装过它，但它返回以下错误消息：

\n

错误：不可能解决：如需帮助，请访问https://pip.pypa.io/en/latest/user_guide/#fixing-conflicting-dependencies

\n

这是错误出现之前发生的情况：

Collecting tensorflowjs\n  Using cached tensorflowjs-3.0.0-py3-none-any.whl (63 kB)\nCollecting h5py<3,>=2.8.0\n  Using cached h5py-2.10.0.tar.gz (301 kB)\nCollecting tensorflowjs\n  Using cached tensorflowjs-2.8.5-py3-none-any.whl (63 kB)\n  Using cached tensorflowjs-2.8.4-py3-none-any.whl (63 kB)\n  Using cached tensorflowjs-2.8.3-py3-none-any.whl (63 kB)\n  Using cached tensorflowjs-2.8.2-py3-none-any.whl (63 kB)\n  Using cached tensorflowjs-2.8.1-py3-none-any.whl (63 kB)\n  Using cached tensorflowjs-2.8.0-py3-none-any.whl (63 kB)\n  Using cached tensorflowjs-2.7.0-py3-none-any.whl (62 kB)\n  Using cached tensorflowjs-2.6.0-py3-none-any.whl (61 kB)\n  Using cached tensorflowjs-2.5.0-py3-none-any.whl (61 kB)\n  Using cached …

我有一个像这样的训练数据集（主列表中的项目数为 211，每个数组中的数字数为 185）：

[np.array([2, 3, 4, ... 5, 4, 6]) ... np.array([3, 4, 5, ... 3, 4, 5])]

我使用此代码来训练模型：

def create_model():
model = keras.Sequential([
    keras.layers.Flatten(input_shape=(211, 185), name="Input"), 
    keras.layers.Dense(211, activation='relu', name="Hidden_Layer_1"), 
    keras.layers.Dense(185, activation='relu', name="Hidden_Layer_2"), 
    keras.layers.Dense(1, activation='softmax', name="Output"),
])

model.compile(optimizer='adam',
          loss='sparse_categorical_crossentropy',
          metrics=['accuracy'])

return model

但每当我这样安装时：

model.fit(x=training_data, y=training_labels, epochs=10, validation_data = [training_data,training_labels])

它返回此错误：

ValueError: Layer sequential expects 1 inputs, but it received 211 input tensors.

可能是什么问题？