inferece.py 推理出错

[iiinsight]

(mimicmotion) PS D:\profile_me\BUPT\baoyan\THUSZ\MimicMotion-main> python inference.py --inference_config configs/test.yaml
Cannot initialize model with low cpu memory usage because accelerate was not found in the environment. Defaulting to low_cpu_mem_usage=False. It is strongly recommended to install accelerate for faster and less memory-intense model loading. You can do so with:

pip install accelerate

.
E:\Anaconda3\envs\mimicmotion\Lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py:69: UserWarning: Specified provider 'CUDAExecutionProvider' is not in available provider names.Available providers: 'AzureExecutionProvider, CPUExecutionProvider'
warnings.warn(
DWPose: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████| 530/530 [07:10<00:00, 1.23it/s]
0%|▌ | 1/200 [16:24<54:26:51, 984.98s/it]
Traceback (most recent call last):
File "D:\profile_me\BUPT\baoyan\THUSZ\MimicMotion-main\inference.py", line 182, in
parser.add_argument("--output_dir", type=str, default="outputs/", help="path to output")
^^^^^^^^^^
File "E:\Anaconda3\envs\mimicmotion\Lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "D:\profile_me\BUPT\baoyan\THUSZ\MimicMotion-main\inference.py", line 146, in main
########################################### Run MimicMotion pipeline ###########################################
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\profile_me\BUPT\baoyan\THUSZ\MimicMotion-main\inference.py", line 102, in run_pipeline
frames = pipeline(
^^^^^^^^^
File "E:\Anaconda3\envs\mimicmotion\Lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "D:\profile_me\BUPT\baoyan\THUSZ\MimicMotion-main\mimicmotion\pipelines\pipeline_mimicmotion.py", line 582, in call
_noise_pred = self.unet(
^^^^^^^^^^
File "E:\Anaconda3\envs\mimicmotion\Lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\profile_me\BUPT\baoyan\THUSZ\MimicMotion-main\mimicmotion\modules\unet.py", line 489, in forward
sample = upsample_block(
^^^^^^^^^^^^^^^
File "E:\Anaconda3\envs\mimicmotion\Lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Anaconda3\envs\mimicmotion\Lib\site-packages\diffusers\models\unets\unet_3d_blocks.py", line 2277, in forward
hidden_states = resnet(
^^^^^^^
File "E:\Anaconda3\envs\mimicmotion\Lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Anaconda3\envs\mimicmotion\Lib\site-packages\diffusers\models\resnet.py", line 713, in forward
hidden_states = self.temporal_res_block(hidden_states, temb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Anaconda3\envs\mimicmotion\Lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Anaconda3\envs\mimicmotion\Lib\site-packages\diffusers\models\resnet.py", line 617, in forward
hidden_states = self.nonlinearity(hidden_states)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Anaconda3\envs\mimicmotion\Lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Anaconda3\envs\mimicmotion\Lib\site-packages\torch\nn\modules\activation.py", line 396, in forward
return F.silu(input, inplace=self.inplace)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\Anaconda3\envs\mimicmotion\Lib\site-packages\torch\nn\functional.py", line 2059, in silu
return torch._C._nn.silu(input)
^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: CUDA error: out of memory
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

(base) PS D:\profile_me\BUPT\baoyan\THUSZ\MimicMotion-main> nvidia-smi
Fri Aug 16 22:24:34 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 551.76 Driver Version: 551.76 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 4060 ... WDDM | 00000000:01:00.0 Off | N/A |
| N/A 50C P0 12W / 60W | 7493MiB / 8188MiB | 100% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 51440 C ...aconda3\envs\mimicmotion\python.exe N/A |
+-----------------------------------------------------------------------------------------+

[CatDroid]

CUDA error: out of memory ? 内存不够了吧 8GB的显存 跑不起来
4090 24G显存的ok

[heiheiheibj]

CUDA error: out of memory ? 内存不够了吧 8GB的显存 跑不起来 4090 24G显存的ok

我的是3070 8G能跑的，把test.yaml里num_frames: 72改为num_frames: 16