` 环境：Ubuntu 20.04 Python 3.8.10，前面安装等执行都正常 python3 general_demo.py --human ./file/input/test.mp4 --output output.mp4 --text 各位开发者大家好，欢迎使用飞桨。

Building prefix dict from the default dictionary ... [2022-01-09 21:51:25] [DEBUG] [init.py:113] Building prefix dict from the default dictionary ... Loading model from cache /tmp/jieba.cache [2022-01-09 21:51:25] [DEBUG] [init.py:132] Loading model from cache /tmp/jieba.cache Loading model cost 0.539 seconds. [2022-01-09 21:51:25] [DEBUG] [init.py:164] Loading model cost 0.539 seconds. Prefix dict has been built successfully. [2022-01-09 21:51:25] [DEBUG] [init.py:166] Prefix dict has been built successfully. /usr/local/lib/python3.8/dist-packages/paddle/fluid/dygraph/math_op_patch.py:251: UserWarning: The dtype of left and right variables are not the same, left dtype is paddle.int64, but right dtype is paddle.int32, the right dtype will convert to paddle.int64 warnings.warn( Traceback (most recent call last): File "general_demo.py", line 18, in video = wav2lip(args.human,wavfile,args.output) #将音频合成到唇形视频 File "/root/PaddleBoBo/PaddleTools/GAN.py", line 11, in wav2lip wav2lip_predictor.run(input_video, input_audio, output) File "/usr/local/lib/python3.8/dist-packages/ppgan/apps/wav2lip_predictor.py", line 176, in run raise ValueError( ValueError: --face argument must be a valid path to video/image file `

Traceback (most recent call last): File "news_app.py", line 35, in TTS = TTSExecutor() TypeError: init() missing 1 required positional argument: 'config'

我租了一台8个GPU、单GPU 84G显存的tesla 100，使用缺省头像生成是没问题的。如果使用自动定义头像（我自己的照片，7MB），创建虚拟角色的步骤没有问题（就是生成这个me.mp4)，但在生成demo video的时候失败了，报CUDNN_STATUS_NOT_SUPPORTED

# python general_demo.py     --human ./file/input/me.mp4     --output me.mp4     --text 各位开发者大家好，我是您的专属虚拟主播，很高兴能为您服务。

/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/librosa/core/constantq.py:1059: DeprecationWarning: `np.complex` is a deprecated alias for the builtin `complex`. To silence this warning, use `complex` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.complex128` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  dtype=np.complex,
[01/05 02:11:00] ppgan INFO: Found /root/.cache/ppgan/GPEN-512.pdparams
W0105 02:11:01.451380 57662 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 8.0, Driver API Version: 11.5, Runtime API Version: 11.2
W0105 02:11:01.453052 57662 device_context.cc:465] device: 0, cuDNN Version: 8.1.
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/tensor/creation.py:130: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if data.dtype == np.object:
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_0. generator.noises.noise_0 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_1. generator.noises.noise_1 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_2. generator.noises.noise_2 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_3. generator.noises.noise_3 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_4. generator.noises.noise_4 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_5. generator.noises.noise_5 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_6. generator.noises.noise_6 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_7. generator.noises.noise_7 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_8. generator.noises.noise_8 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_9. generator.noises.noise_9 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_10. generator.noises.noise_10 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_11. generator.noises.noise_11 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_12. generator.noises.noise_12 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_13. generator.noises.noise_13 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for generator.noises.noise_14. generator.noises.noise_14 is not found in the provided dict.
  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
[2022-01-05 02:11:02,854] [    INFO] [log.py] [L57] - File /root/.paddlespeech/models/fastspeech2_csmsc-zh/fastspeech2_nosil_baker_ckpt_0.4.zip md5 checking...
[2022-01-05 02:11:03,674] [    INFO] [log.py] [L57] - File /root/.paddlespeech/models/pwgan_csmsc-zh/pwg_baker_ckpt_0.4.zip md5 checking...
encoder_type is transformer
decoder_type is transformer
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/framework/io.py:415: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3, and in 3.10 it will stop working
  if isinstance(obj, collections.Iterable) and not isinstance(obj, (
Building prefix dict from the default dictionary ...
[2022-01-05 02:11:06] [DEBUG] [__init__.py:113] Building prefix dict from the default dictionary ...
Loading model from cache /tmp/jieba.cache
[2022-01-05 02:11:06] [DEBUG] [__init__.py:132] Loading model from cache /tmp/jieba.cache
Loading model cost 0.470 seconds.
[2022-01-05 02:11:07] [DEBUG] [__init__.py:164] Loading model cost 0.470 seconds.
Prefix dict has been built successfully.
[2022-01-05 02:11:07] [DEBUG] [__init__.py:166] Prefix dict has been built successfully.
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/math_op_patch.py:251: UserWarning: The dtype of left and right variables are not the same, left dtype is paddle.int64, but right dtype is paddle.int32, the right dtype will convert to paddle.int64
  warnings.warn(
Reading video frames...
Number of frames available for inference: 300
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/librosa/util/utils.py:2099: DeprecationWarning: `np.float` is a deprecated alias for the builtin `float`. To silence this warning, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  np.dtype(np.float): np.complex,
/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/librosa/util/utils.py:2099: DeprecationWarning: `np.complex` is a deprecated alias for the builtin `complex`. To silence this warning, use `complex` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.complex128` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  np.dtype(np.float): np.complex,
Length of mel chunks: 157
[2022-01-05 02:11:13,369] [    INFO] - unique_endpoints {''}
[2022-01-05 02:11:13,370] [    INFO] - Found /root/.cache/paddle/hapi/weights/wav2lip_hq.pdparams
Model loaded
  0%|                                                                                                                                                                                 | 0/2 [00:00
    video = wav2lip(args.human,wavfile,args.output) #将音频合成到唇形视频
  File "/root/PaddleBoBo/PaddleTools/GAN.py", line 11, in wav2lip
    wav2lip_predictor.run(input_video, input_audio, output)
  File "/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/ppgan/apps/wav2lip_predictor.py", line 257, in run
    for i, (img_batch, mel_batch, frames, coords) in enumerate(
  File "/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/tqdm/std.py", line 1180, in __iter__
    for obj in iterable:
  File "/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/ppgan/apps/wav2lip_predictor.py", line 118, in datagen
    face_det_results = self.face_detect(
  File "/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/ppgan/apps/wav2lip_predictor.py", line 74, in face_detect
    detector.get_detections_for_batch(
  File "/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/ppgan/faceutils/face_detection/api.py", line 73, in get_detections_for_batch
    detected_faces = self.face_detector.detect_from_batch(images.copy())
  File "/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/ppgan/faceutils/face_detection/detection/sfd/sfd_detector.py", line 56, in detect_from_batch
    bboxlists = batch_detect(self.face_detector, images)
  File "/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/ppgan/faceutils/face_detection/detection/sfd/detect.py", line 76, in batch_detect
    olist = net(imgs)
  File "/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py", line 914, in __call__
    outputs = self.forward(*inputs, **kwargs)
  File "/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/ppgan/faceutils/face_detection/detection/sfd/net_s3fd.py", line 133, in forward
    h = F.relu(self.conv1_1(x))
  File "/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py", line 914, in __call__
    outputs = self.forward(*inputs, **kwargs)
  File "/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/nn/layer/conv.py", line 665, in forward
    out = F.conv._conv_nd(
  File "/root/anaconda3/envs/paddle_env/lib/python3.9/site-packages/paddle/nn/functional/conv.py", line 123, in _conv_nd
    pre_bias = getattr(_C_ops, op_type)(x, weight, *attrs)
OSError: (External) CUDNN error(9), CUDNN_STATUS_NOT_SUPPORTED.
  [Hint: 'CUDNN_STATUS_NOT_SUPPORTED'.  The functionality requested is not presently supported by cuDNN.  ] (at /paddle/paddle/fluid/platform/cudnn_desc.h:171)
  [operator < conv2d > error]

运行general_demo.py报错如下： D:\InstallPath\Develop\Anaconda3\2020.07\envs\PaddleBoBo_Py3.7\python.exe G:/Project/AIBroadcast/PaddleBoBo/general_demo.py Traceback (most recent call last): File "G:/Project/AIBroadcast/PaddleBoBo/general_demo.py", line 6, in from PaddleTools.TTS import TTSExecutor File "G:\Project\AIBroadcast\PaddleBoBo\PaddleTools\TTS.py", line 11, in from paddlespeech.cli.utils import MODEL_HOME ImportError: cannot import name 'MODEL_HOME' from 'paddlespeech.cli.utils' (D:\InstallPath\Develop\Anaconda3\2020.07\envs\PaddleBoBo_Py3.7\lib\site-packages\paddlespeech\cli\utils.py)

[01/10 10:12:33] ppgan INFO: Found /root/.cache/ppgan/GPEN-512.pdparams Traceback (most recent call last): File "/usr/local/lib/python3.7/dist-packages/paddle/framework/io.py", line 936, in load load_result = pickle.load(f) _pickle.UnpicklingError: pickle data was truncated

#python general_demo.py --human ./file/input/test.mp4 --output ../output.mp4 --text 各位开发者大家好，我是您的专属虚拟主播，很高兴能为您服务。

结果告诉我内存不足，Out of memory error on GPU 0. Cannot allocate 4.722656GB memory on GPU 0, 13.023560GB memory has been allocated and available memory is only 2.975952GB.

我的机器是3080，16G显存，不管这句话多长都是分配这么多内存，配置建议多少啊？

Traceback (most recent call last):
  File "E:/Graduate/PaddleBoBo-develop/create_virtual_human.py", line 23, in <module>
    cvh = FOM(GAN_Config['FOM_INPUT_IMAGE'],GAN_Config['FOM_DRIVING_VIDEO'],GAN_Config['FOM_OUTPUT_VIDEO'])
  File "E:\Graduate\PaddleBoBo-develop\PaddleTools\GAN.py", line 24, in FOM
    first_order_predictor.run(source_image, driving_video)
  File "E:\Python\environment\lib\site-packages\ppgan\apps\first_order_predictor.py", line 184, in run
    bboxes = self.extract_bbox(source_image.copy())
  File "E:\Python\environment\lib\site-packages\ppgan\apps\first_order_predictor.py", line 324, in extract_bbox
    predictions = detector.get_detections_for_image(np.array(frame))
  File "E:\Python\environment\lib\site-packages\ppgan\faceutils\face_detection\api.py", line 90, in get_detections_for_image
    detected_faces = self.face_detector.detect_from_batch(images.copy())
  File "E:\Python\environment\lib\site-packages\ppgan\faceutils\face_detection\detection\sfd\sfd_detector.py", line 56, in detect_from_batch
    bboxlists = batch_detect(self.face_detector, images)
  File "E:\Python\environment\lib\site-packages\ppgan\faceutils\face_detection\detection\sfd\detect.py", line 76, in batch_detect
    olist = net(imgs)
  File "E:\Python\environment\lib\site-packages\paddle\fluid\dygraph\layers.py", line 917, in __call__
    return self._dygraph_call_func(*inputs, **kwargs)
  File "E:\Python\environment\lib\site-packages\paddle\fluid\dygraph\layers.py", line 907, in _dygraph_call_func
    outputs = self.forward(*inputs, **kwargs)
  File "E:\Python\environment\lib\site-packages\ppgan\faceutils\face_detection\detection\sfd\net_s3fd.py", line 133, in forward
    h = F.relu(self.conv1_1(x))
  File "E:\Python\environment\lib\site-packages\paddle\fluid\dygraph\layers.py", line 917, in __call__
    return self._dygraph_call_func(*inputs, **kwargs)
  File "E:\Python\environment\lib\site-packages\paddle\fluid\dygraph\layers.py", line 907, in _dygraph_call_func
    outputs = self.forward(*inputs, **kwargs)
  File "E:\Python\environment\lib\site-packages\paddle\nn\layer\conv.py", line 665, in forward
    out = F.conv._conv_nd(
  File "E:\Python\environment\lib\site-packages\paddle\nn\functional\conv.py", line 123, in _conv_nd
    pre_bias = getattr(_C_ops, op_type)(x, weight, *attrs)
SystemError: (Fatal) Operator conv2d raises an struct paddle::memory::allocation::BadAlloc exception.
The exception content is
:ResourceExhaustedError: 

Out of memory error on GPU 0. Cannot allocate 297.650635MB memory on GPU 0, 1.821357GB memory has been allocated and available memory is only 182.805861MB.

Please check whether there is any other process using GPU 0.
1. If yes, please stop them, or start PaddlePaddle on another GPU.
2. If no, please decrease the batch size of your model. 

 (at ..\paddle\fluid\memory\allocation\cuda_allocator.cc:79)
. (at ..\paddle\fluid\imperative\tracer.cc:221)

提示GPU内存不够 然后提供了两种解决方案：

• 一是在另外一个GPU运行，我尝试过 import os os.environ['CUDA_VISIBLE_DEVICES'] = '1' 但还是相同的报错
• 二是减少batch_size，我尽可能搜索网站信息没有找到如何改变batch_size的帖子，在这个项目里面我没有找到batch_size的关键词，后来我又在项目外（paddle中搜索）结果也不尽人意，尝试过很多比如直接添加batch_size=1，运行无果。甚至Out of memory error on GPU 0. Cannot allocate 297.650635MB memory on GPU 0, 1.821357GB memory has been allocated and available memory is only 182.805861MB.这些数值都没有改变。 小白在线求大佬们解惑~！

我的环境： paddlepaddle-gpu :2.3.2 ppgan 2.1.0 paddlespeech 1.0.1 paddleaudio 1.0.2

/content/drive/MyDrive/Virtual_broadcast /usr/local/lib/python3.7/dist-packages/librosa/core/constantq.py:1059: DeprecationWarning: np.complex is a deprecated alias for the builtin complex. To silence this warning, use complex by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use np.complex128 here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations dtype=np.complex, Traceback (most recent call last): File "general_demo.py", line 6, in from PaddleTools.TTS import TTSExecutor File "/content/drive/MyDrive/Virtual_broadcast/PaddleTools/TTS.py", line 10, in from paddlespeech.cli.utils import download_and_decompress File "/usr/local/lib/python3.7/dist-packages/paddlespeech/cli/init.py", line 24, in from .vector import VectorExecutor File "/usr/local/lib/python3.7/dist-packages/paddlespeech/cli/vector/init.py", line 14, in from .infer import VectorExecutor File "/usr/local/lib/python3.7/dist-packages/paddlespeech/cli/vector/infer.py", line 25, in from paddleaudio.backends import load as load_audio ImportError: cannot import name 'load' from 'paddleaudio.backends' (/usr/local/lib/python3.7/dist-packages/paddleaudio/backends/init.py)

Traceback (most recent call last): File "general_demo.py", line 18, in video = wav2lip(args.human,wavfile,args.output) #将音频合成到唇形视频 File "/Users/apple/Downloads/PaddleBoBo-develop/PaddleTools/GAN.py", line 12, in wav2lip wav2lip_predictor.run(input_video, input_audio, output) File "/Users/apple/miniconda3/envs/py37/lib/python3.7/site-packages/ppgan/apps/wav2lip_predictor.py", line 177, in run '--face argument must be a valid path to video/image file') ValueError: --face argument must be a valid path to video/image file

ImportError: cannot import name 'MODEL_HOME' from 'paddlespeech.cli.utils' (/root/anaconda3/envs/pdpd_py37_xnr/lib/python3.7/site-packages/paddlespeech/cli/utils.py)

各位老板有报这个错的么？？？

Traceback (most recent call last): File "D:\jellyfin\PaddleBoBo\general_demo.py", line 18, in video = wav2lip(args.human,wavfile,args.output) #将音频合成到唇形视频 File "D:\jellyfin\PaddleBoBo\PaddleTools\GAN.py", line 11, in wav2lip wav2lip_predictor.run(input_video, input_audio, output) File "C:\Users\ycy\AppData\Roaming\Python\Python39\site-packages\ppgan\apps\wav2lip_predictor.py", line 290, in run subprocess.call(command, shell=platform.system() != 'Windows') File "C:\Program Files\Python39\lib\subprocess.py", line 349, in call with Popen(*popenargs, **kwargs) as p: File "C:\Program Files\Python39\lib\subprocess.py", line 951, in init self._execute_child(args, executable, preexec_fn, close_fds, File "C:\Program Files\Python39\lib\subprocess.py", line 1420, in _execute_child hp, ht, pid, tid = _winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] 系统找不到指定的文件。

如果大家在运行中发现了问题，那一般是库的版本问题，我自己看了看paddlespeech的库，我终于发现了他的改动，在之前的时候，<=1.0的时候，这个都是正确的。但是如果paddlespeech默认下载了1.1或者1.2的版本，在PaddleTools中的TTS.py的11行的MODEL_HOME中，MODEL_HOME就会出现问题，这是因为换位置了，所以我们需要将其换为，

from paddlespeech.utils.env import MODEL_HOME

亲测有效，或者安装paddlespeech为<=1.0的版本也可以，就直接不用改代码了

您好， 执行python general_demo.py 报错。麻烦这个问题如何解决，谢谢 Traceback (most recent call last): File "general_demo.py", line 6, in from PaddleTools.TTS import TTSExecutor File "/data/hwpang/2020_dev/gan/PaddleBoBo/PaddleTools/TTS.py", line 11, in from paddlespeech.cli.utils import MODEL_HOME ImportError: cannot import name 'MODEL_HOME' from 'paddlespeech.cli.utils' (/root/anaconda3/envs/paddle/lib/python3.8/site-packages/paddlespeech/cli/utils.py)

Traceback (most recent call last): File "create_virtual_human.py", line 13, in cvh = FOM(GAN_Config['FOM_INPUT_IMAGE'],GAN_Config['FOM_DRIVING_VIDEO'],GAN_Config['FOM_OUTPUT_VIDEO']) File "E:\python_project\PaddleBoBo\PaddleTools\GAN.py", line 23, in FOM first_order_predictor.run(source_image, driving_video) File "C:\Users\13277.conda\envs\virtual_human\lib\site-packages\ppgan\apps\first_order_predictor.py", line 190, in run face_image = cv2.resize(face_image, (self.image_size, self.image_size)) / 255.0 cv2.error: OpenCV(4.6.0) D:\a\opencv-python\opencv-python\opencv\modules\imgproc\src\resize.cpp:4052: error: (-215:Assertion failed) !ssize.empty() in function 'cv::resize'

各位老师好，目前wav2lip官方的模型（基于LRS2）训练的，应用到其他人脸（例如亚洲人脸），嘴型驱动部分存在很强的模糊，并且嘴型很多时候是错误的。基于此，我想在自己的专人数据集上训练此wav2lip模型。我的数据为两个小时的专人视频，在训练Lip-sync Expert嘴型和音频同步网络时候，loss一直不下降，卡在0.6左右。请问老师们能给我一点建议吗 谢谢