Tensorflow 在个人系统上训练VAE模型时出错
在我的系统上使用OpenAI gym的“CarRacing-v0”环境训练VAE时调用.fit函数时出错。同样的模式在google Colab上运行良好 错误如下所示:Tensorflow 在个人系统上训练VAE模型时出错,tensorflow,machine-learning,Tensorflow,Machine Learning,在我的系统上使用OpenAI gym的“CarRacing-v0”环境训练VAE时调用.fit函数时出错。同样的模式在google Colab上运行良好 错误如下所示: Track generation: 1077..1354 -> 277-tiles track EPISODE: 0 --------------------------------------------------------------------------- ValueError
Track generation: 1077..1354 -> 277-tiles track
EPISODE: 0
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-22-c9f30896c44b> in <module>
14
15 vae_train_data = batch(STORAGE)
---> 16 vae.fit(vae_train_data, vae_train_data, batch_size=step, epochs =1)
17 STORAGE.clear()
18
~\anaconda3\envs\new\lib\site-packages\tensorflow_core\python\keras\engine\training.py in
fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle,
class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq,
max_queue_size, workers, use_multiprocessing, **kwargs)
726 max_queue_size=max_queue_size,
727 workers=workers,
--> 728 use_multiprocessing=use_multiprocessing)
729
730 def evaluate(self,
~\anaconda3\envs\new\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in
fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data,
shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps,
validation_freq, **kwargs)
222 validation_data=validation_data,
223 validation_steps=validation_steps,
--> 224 distribution_strategy=strategy)
225
226 total_samples = _get_total_number_of_samples(training_data_adapter)
~\anaconda3\envs\new\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in _
process_training_inputs(model, x, y, batch_size, epochs, sample_weights, class_weights,
steps_per_epoch, validation_split, validation_data, validation_steps, shuffle, distribution_strategy,
max_queue_size, workers, use_multiprocessing)
545 max_queue_size=max_queue_size,
546 workers=workers,
--> 547 use_multiprocessing=use_multiprocessing)
548 val_adapter = None
549 if validation_data:
~\anaconda3\envs\new\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in
_process_inputs(model, x, y, batch_size, epochs, sample_weights, class_weights, shuffle, steps,
distribution_strategy, max_queue_size, workers, use_multiprocessing)
592 batch_size=batch_size,
593 check_steps=False,
--> 594 steps=steps)
595 adapter = adapter_cls(
596 x,
~\anaconda3\envs\new\lib\site-packages\tensorflow_core\python\keras\engine\training.py in
_standardize_user_data(self, x, y, sample_weight, class_weight, batch_size, check_steps, steps_name,
steps, validation_split, shuffle, extract_tensors_from_dataset)
2517 shapes=None,
2518 check_batch_axis=False, # Don't enforce the batch size.
-> 2519 exception_prefix='target')
2520
2521 # Generate sample-wise weight values given the `sample_weight` and
~\anaconda3\envs\new\lib\site-packages\tensorflow_core\python\keras\engine\training_utils.py in
standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
487 raise ValueError(
488 'Error when checking model ' + exception_prefix + ': '
--> 489 'expected no data, but got:', data)
490 return []
491 if data is None:
ValueError: ('Error when checking model target: expected no data, but got:', array([[[[0.
, 0. , 0. ],
[0. , 0. , 0. ],
[0. , 0. , 0. ],
...,
轨迹生成:1077..1354->277平铺轨迹
插曲:0
---------------------------------------------------------------------------
ValueError回溯(最近一次调用上次)
在里面
14
15车辆系列数据=批次(存储)
--->16阀配合(阀组数据、阀组数据、批量大小=步长、历元=1)
17.clear()的存储
18
中的~\anaconda3\envs\new\lib\site packages\tensorflow\u core\python\keras\engine\training.py
拟合(自我、x、y、批量大小、年代、详细信息、回调、验证拆分、验证数据、洗牌、,
类别权重、样本权重、初始历元、每历元步长、验证步长、验证频率、,
最大队列大小,工人,使用多处理,**kwargs)
726最大队列大小=最大队列大小,
727名工人=工人,
-->728使用多处理=使用多处理)
729
730 def评估(自我,
~\anaconda3\envs\new\lib\site packages\tensorflow\u core\python\keras\engine\training\u v2.py in
拟合(自我、模型、x、y、批量大小、年代、详细、回调、验证拆分、验证数据、,
洗牌、等级权重、样本权重、初始历元、每历元步骤、验证步骤、,
验证频率,**kwargs)
222验证数据=验证数据,
223验证步骤=验证步骤,
-->224分销(策略=策略)
225
226总样本数=\u获取\u总样本数\u(训练\u数据\u适配器)
~\anaconda3\envs\new\lib\site packages\tensorflow\u core\python\keras\engine\training\u v2.py in\u
过程训练输入(模型、x、y、批量、年代、样本权重、类别权重、,
每个历元的步骤、验证拆分、验证数据、验证步骤、洗牌、分发策略、,
最大队列大小、工人、使用(多处理)
545最大队列大小=最大队列大小,
546名工人=工人,
-->547使用\多处理=使用\多处理)
548 val_适配器=无
549如果验证数据:
~\anaconda3\envs\new\lib\site packages\tensorflow\u core\python\keras\engine\training\u v2.py in
_处理输入(模型、x、y、批次大小、年代、样本权重、类别权重、混洗、步骤、,
分布策略、最大队列大小、工人、使用(多处理)
592批次大小=批次大小,
593检查步骤=错误,
-->594步=步)
595适配器=适配器(
596 x,
中的~\anaconda3\envs\new\lib\site packages\tensorflow\u core\python\keras\engine\training.py
_标准化用户数据(自身、x、y、样本重量、类别重量、批次大小、检查步骤、步骤名称、,
步骤、验证(拆分、洗牌、从数据集中提取张量)
2517个形状=无,
2518检查_batch_axis=False,#不强制执行批大小。
->2519例外情况(前缀=“目标”)
2520
2521#根据“样本权重”生成样本权重值,以及
中的~\anaconda3\envs\new\lib\site packages\tensorflow\u core\python\keras\engine\training\u utils.py
标准化输入数据(数据、名称、形状、检查批处理轴、异常前缀)
487提升值错误(
488“检查模型“+异常前缀+”时出错::”
-->489'应无数据,但得到:',数据)
490返回[]
491如果数据为无:
ValueError:('Error when check model target:应无数据,但已获取:',数组([[0]。
, 0. , 0. ],
[0. , 0. , 0. ],
[0. , 0. , 0. ],
...,
我很好奇:这个问题是否与使用不同版本的tensorflow有关。我使用的是tensorflow gpu 2.0