aaronjny / deeplearningexamples Goto Github PK

作者你好，我再python eval.py的时候报错，报错内容如下：
Traceback (most recent call last):
File "eval.py", line 13, in
model = keras.models.load_model("best_model.h5")
File "C:\Users\YuQiCode\anaconda3\envs\tf2\lib\site-packages\tensorflow_core\python\keras\saving\save.py", line 146, in load_model
return hdf5_format.load_model_from_hdf5(filepath, custom_objects, compile)
File "C:\Users\YuQiCode\anaconda3\envs\tf2\lib\site-packages\tensorflow_core\python\keras\saving\hdf5_format.py", line 184, in load_model_from_hdf5
training_config, custom_objects))
File "C:\Users\YuQiCode\anaconda3\envs\tf2\lib\site-packages\tensorflow_core\python\keras\saving\saving_utils.py", line 235, in compile_args_from_training_config
sample_weight_mode = training_config['sample_weight_mode']
KeyError: 'sample_weight_mode'

请问是因为什么原因呀，是模型保存出问题了吗

例如输入一句评论，加载训练好的模型来输出对应的标签值

您好,我在在JAVA或者js中使用您的诗词训练代码中生成的模型 来完成我的毕业设计,但是使用网上通用的转换方案 转换过程中都会报 ValueError: Unknown layer: UnifiedLSTM,这个错误,我搜索了很长时间都没有对应的解答,请问您是否知道这个错误是什么意思呢

博主你好，我下载了您的DeepLearningExamples这个文件。但是解压时显示文件损坏，只能解压出前两个文件，找不到tf2-neural-style-transfer这个文件。请问这种情况该怎么办呢

您好~我想问一下图片风格迁移的demo有没有什么可以作为评估指标的呢，还是只有两个loss和肉眼观察吗hhh

WARNING:tensorflow:11 out of the last 11 calls to <function _make_execution_function..distributed_function at 0x000002A1DC21A400> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings is likely due to passing python objects instead of tensors. Also, tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. Please refer to https://www.tensorflow.org/beta/tutorials/eager/tf_function#python_or_tensor_args and https://www.tensorflow.org/api_docs/python/tf/function for more details.

我是gtx3080

how to?

这个项目的模型我用迅雷下好的，放在跟目录
但是他每次启动还是要去download 这个要放哪个路径呢？谢谢
@AaronJny

通过什么参数或者配置能够确定的让模型输出五言诗，七言诗？