Python 我一直收到StyleGAN的断言错误
最近我一直在玩StyleGAN，我已经生成了一个数据集，但当我尝试运行train.py时，我得到了以下结果Python 我一直收到StyleGAN的断言错误,python,tensorflow,deep-learning,generative-adversarial-network,Python,Tensorflow,Deep Learning,Generative Adversarial Network,最近我一直在玩StyleGAN，我已经生成了一个数据集，但当我尝试运行train.py时，我得到了以下结果 2020-01-08 13:33:21.943217: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll WARNING:tensorflow:From C:\Users\MyName\Desktop\Sty
2020-01-08 13:33:21.943217: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll
WARNING:tensorflow:From C:\Users\MyName\Desktop\StyleGan\stylegan-master\dnnlib\tflib\tfutil.py:34: The name tf.Dimension is deprecated. Please use tf.compat.v1.Dimension instead.
WARNING:tensorflow:From C:\Users\MyName\Desktop\StyleGan\stylegan-master\dnnlib\tflib\tfutil.py:74: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.
WARNING:tensorflow:From C:\Users\MyName\Desktop\StyleGan\stylegan-master\dnnlib\tflib\tfutil.py:128: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.
Creating the run dir: results\00003-sgan-datasets-1gpu
Copying files to the run dir
dnnlib: Running training.training_loop.training_loop() on localhost...
WARNING:tensorflow:From C:\Users\MyName\Desktop\StyleGan\stylegan-master\dnnlib\tflib\tfutil.py:97: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.
WARNING:tensorflow:From C:\Users\MyName\Desktop\StyleGan\stylegan-master\dnnlib\tflib\tfutil.py:109: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.
WARNING:tensorflow:From C:\Users\MyName\Desktop\StyleGan\stylegan-master\dnnlib\tflib\tfutil.py:132: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.
2020-01-08 13:33:23.904828: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
2020-01-08 13:33:23.913674: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll
2020-01-08 13:33:23.945149: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: GeForce GTX 1660 Ti major: 7 minor: 5 memoryClockRate(GHz): 1.59
pciBusID: 0000:01:00.0
2020-01-08 13:33:23.951080: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll
2020-01-08 13:33:23.957540: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll
2020-01-08 13:33:23.964398: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_100.dll
2020-01-08 13:33:23.968829: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_100.dll
2020-01-08 13:33:23.975979: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_100.dll
2020-01-08 13:33:23.983341: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_100.dll
2020-01-08 13:33:23.997908: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2020-01-08 13:33:24.002421: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2020-01-08 13:33:24.657141: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-01-08 13:33:24.661322: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0
2020-01-08 13:33:24.663568: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N
2020-01-08 13:33:24.667420: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4627 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1660 Ti, pci bus id: 0000:01:00.0, compute capability: 7.5)
Streaming data using training.dataset.TFRecordDataset...
Traceback (most recent call last):
File "train.py", line 190, in <module>
main()
File "train.py", line 185, in main
dnnlib.submit_run(**kwargs)
File "C:\Users\MyName\Desktop\StyleGan\stylegan-master\dnnlib\submission\submit.py", line 290, in submit_run
run_wrapper(submit_config)
File "C:\Users\MyName\Desktop\StyleGan\stylegan-master\dnnlib\submission\submit.py", line 242, in run_wrapper
util.call_func_by_name(func_name=submit_config.run_func_name, submit_config=submit_config, **submit_config.run_func_kwargs)
File "C:\Users\MyName\Desktop\StyleGan\stylegan-master\dnnlib\util.py", line 257, in call_func_by_name
return func_obj(*args, **kwargs)
File "C:\Users\MyName\Desktop\StyleGan\stylegan-master\training\training_loop.py", line 146, in training_loop
training_set = dataset.load_dataset(data_dir=config.data_dir, verbose=True, **dataset_args)
File "C:\Users\MyName\Desktop\StyleGan\stylegan-master\training\dataset.py", line 234, in load_dataset
dataset = dnnlib.util.get_obj_by_name(class_name)(**adjusted_kwargs)
File "C:\Users\MyName\Desktop\StyleGan\stylegan-master\training\dataset.py", line 70, in __init__
assert os.path.isdir(self.tfrecord_dir)
AssertionError
2020-01-08 13:33:21.943217:I tensorflow/stream_executor/platform/default/dso_loader.cc:44]已成功打开动态库cudart64_100.dll
警告：tensorflow:From C:\Users\MyName\Desktop\StyleGan\StyleGan master\dnnlib\tflib\tfutil.py:34:不推荐使用名称tf.Dimension。请改用tf.compat.v1.Dimension。
警告：tensorflow:From C:\Users\MyName\Desktop\StyleGan\StyleGan master\dnnlib\tflib\tfutil.py:74:不推荐使用名称tf.variable\u范围。请改用tf.compat.v1.variable\u作用域。
警告：tensorflow:From C:\Users\MyName\Desktop\StyleGan\StyleGan master\dnnlib\tflib\tfutil.py:128:不推荐使用名称tf.Session。请改用tf.compat.v1.Session。
创建运行目录：results\00003-sgan-datasets-1gpu
将文件复制到运行目录
dnnlib:在本地主机上运行training.training\u loop.training\u loop（）。。。
警告：tensorflow:From C:\Users\MyName\Desktop\StyleGan\StyleGan master\dnnlib\tflib\tfutil.py:97:不推荐使用名称tf.get\u default\u session。请改用tf.compat.v1.get_default_会话。
警告：tensorflow:From C:\Users\MyName\Desktop\StyleGan\StyleGan master\dnnlib\tflib\tfutil.py:109:不推荐使用名称tf.set\u random\u seed。请改用tf.compat.v1.set_random_seed。
警告：tensorflow:From C:\Users\MyName\Desktop\StyleGan\StyleGan master\dnnlib\tflib\tfutil.py:132:不推荐使用名称tf.ConfigProto。请改用tf.compat.v1.ConfigProto。
2020-01-08 13:33:23.904828:I tensorflow/core/platform/cpu\u feature\u guard.cc:142]您的cpu支持该tensorflow二进制文件未编译为使用的指令：AVX2
2020-01-08 13:33:23.913674:I tensorflow/stream_executor/platform/default/dso_loader.cc:44]已成功打开动态库nvcuda.dll
2020-01-08 13:33:23.945149:I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618]找到了具有以下属性的设备0：
名称：GeForce GTX 1660 Ti大调：7小调：5记忆锁定率（GHz）：1.59
pciBusID:0000:01:00.0
2020-01-08 13:33:23.951080:I tensorflow/stream_executor/platform/default/dso_loader.cc:44]已成功打开动态库cudart64_100.dll
2020-01-08 13:33:23.957540:I tensorflow/stream_executor/platform/default/dso_loader.cc:44]已成功打开动态库cublas64_100.dll
2020-01-08 13:33:23.964398:I tensorflow/stream_executor/platform/default/dso_loader.cc:44]已成功打开动态库cufft64_100.dll
2020-01-08 13:33:23.968829:I tensorflow/stream_executor/platform/default/dso_loader.cc:44]已成功打开动态库库库和64_100.dll
2020-01-08 13:33:23.975979:I tensorflow/stream_executor/platform/default/dso_loader.cc:44]已成功打开动态库cusolver64_100.dll
2020-01-08 13:33:23.983341:I tensorflow/stream_executor/platform/default/dso_loader.cc:44]已成功打开动态库cusparse64_100.dll
2020-01-08 13:33:23.999908:I tensorflow/stream_executor/platform/default/dso_loader.cc:44]已成功打开动态库cudnn64_7.dll
2020-01-08 13:33:24.002421:I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746]添加可见gpu设备：0
2020-01-08 13:33:24.657141:I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159]设备互连拖缆执行器与强度1边缘矩阵：
2020-01-08 13:33:24.661322:I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165]0
2020-01-08 13:33:24.663568:I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178]0:N
2020-01-08 13:33:24.667420:I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304]创建tensorflow设备（/job:localhost/replica:0/task:0/device:gpu:0，内存4627MB）->物理gpu（设备：0，名称：GeForce GTX 1660TI，pci总线id:0000:01:00.0，计算能力：7.5）
正在使用training.dataset.TFRecordDataset流式处理数据。。。
回溯（最近一次呼叫最后一次）：
文件“train.py”，第190行，在
main（）
文件“train.py”，第185行，在main中
dnnlib.提交运行（**kwargs）
文件“C:\Users\MyName\Desktop\StyleGan\StyleGan master\dnnlib\submission\submit.py”，第290行，处于提交运行状态
运行\u包装（提交\u配置）
文件“C:\Users\MyName\Desktop\StyleGan\StyleGan master\dnnlib\submission\submit.py”，第242行，在run\U包装中
util.call_func_by_name（func_name=submit_config.run_func_name，submit_config=submit_config，**submit_config.run_func_kwargs）
文件“C:\Users\MyName\Desktop\StyleGan\StyleGan master\dnnlib\util.py”，第257行，按名称调用函数
返回函数对象（*args，**kwargs）
文件“C:\Users\MyName\Desktop\StyleGan\StyleGan master\training\training\u loop.py”，第146行，在training\u loop中
training\u set=dataset.load\u dataset（数据\u dir=config.data\u dir，verbose=True，**数据集\u参数）
文件“C:\Users\MyName\Desktop\StyleGan\StyleGan master\training\dataset.py”，第234行，在load\U数据集中
dataset=dnnlib.util.get_obj_by_name（class_name）（**调整后的_kwargs）
文件“C:\Users\MyName\Desktop\StyleGan\StyleGan master\training\dataset.py”，第70行，在\uuu init中__
断言os.path.isdir（self.tfrecord\u dir）
断言错误
我已经修改了Train.py文件以适应我的单个GPU和数据集目录。正如@Chrispresso在这个问题的评论中所回答的，我在下一行中引用的目录无效，必须将其设置为有效目录
# Dataset.
desc += '-dataset'; dataset = EasyDict(tfrecord_dir='dataset', resolution=128); train.mirror_augment = False
（这是StyleGAN中包含的train.py的第36行）我得到了同样的错误。您最终在哪里存储数据集并命名它
编辑：哦，我修好了。如果其他人有此问题，请确保您的数据集位于名为datasets的目录中。查看断言。它告诉你，在self.tfrecord\u dir中保存的任何东西都不是目录。它需要beHey@Chrispresso感谢您的快速响应，这个