Open Gltton opened 1 year ago
The inference script will save preprocessing results in ./temp
folder. When the input video has been preprocessed, the key points are loaded directly from the folder to save inference time.
Did you test two videos with the same name? This can cause the loaded data to be inconsistent with the input video.
You can try deleting ./temp
folder or adding the parameter --re_preprocess
.
landmark Det:: 1%|▏ | 1/135 [00:05<12:15, 5.49s/it]
Traceback (most recent call last):
File "inference.py", line 342, in
Same error here...
(video_retalking) C:\Users\chlyw\Desktop\video-retalking>python inference.py --face examples/Carlin.mp4 --audio examples/Carlin.wav --outfile results/Carlin.mp4 [Info] Using cuda for inference. [Step 0] Number of frames available for inference: 168 [Step 1] Landmarks Extraction in Video. Downloading: "https://www.adrianbulat.com/downloads/python-fan/2DFAN4-cd938726ad.zip" to C:\Users\chlyw/.cache\torch\hub\checkpoints\2DFAN4-cd938726ad.zip 100%|██████████████████████████████████████████████████████████████████████████████| 91.9M/91.9M [00:11<00:00, 8.70MB/s] landmark Det:: 1%|▍ | 1/168 [00:06<16:55, 6.08s/it]nvrtc: error: invalid value for --gpu-architecture (-arch)
nvrtc compilation failed:
template
template
extern "C" global void fused_cat_cat(float tinput0_42, float tinput0_46, float tout3_67, float tinput0_60, float tinput0_52, float tout3_71, float aten_cat, float aten_cat_1) { { if (blockIdx.x<512 ? 1 : 0) { aten_cat_1[512 blockIdx.x + threadIdx.x] = ((((512 blockIdx.x + threadIdx.x) / 1024) % 256<192 ? 1 : 0) ? ((((512 blockIdx.x + threadIdx.x) / 1024) % 256<128 ? 1 : 0) ? __ldg(tinput0_60 + (512 blockIdx.x + threadIdx.x) % 262144) : ldg(tinput0_52 + (512 blockIdx.x + threadIdx.x) % 262144 - 131072)) : __ldg(tout3_71 + (512 blockIdx.x + threadIdx.x) % 262144 - 196608)); } aten_cat[512 blockIdx.x + threadIdx.x] = ((((512 blockIdx.x + threadIdx.x) / 4096) % 256<192 ? 1 : 0) ? ((((512 blockIdx.x + threadIdx.x) / 4096) % 256<128 ? 1 : 0) ? __ldg(tinput0_42 + (512 blockIdx.x + threadIdx.x) % 1048576) : ldg(tinput0_46 + (512 blockIdx.x + threadIdx.x) % 1048576 - 524288)) : __ldg(tout3_67 + (512 blockIdx.x + threadIdx.x) % 1048576 - 786432)); } }
landmark Det:: 1%|▍ | 1/168 [00:06<17:30, 6.29s/it]
Traceback (most recent call last):
File "inference.py", line 342, in
(video_retalking) C:\Users\chlyw\Desktop\video-retalking>python inference.py --face examples/Carlin.mp4 --audio examples/Carlin.wav --outfile results/Carlin.mp4 --re_preprocess [Info] Using cuda for inference. [Step 0] Number of frames available for inference: 168 [Step 1] Landmarks Extraction in Video. landmark Det:: 1%|▍ | 1/168 [00:06<16:52, 6.07s/it]nvrtc: error: invalid value for --gpu-architecture (-arch)
nvrtc compilation failed:
template
template
extern "C" global void fused_cat_cat(float tinput0_42, float tinput0_46, float tout3_67, float tinput0_60, float tinput0_52, float tout3_71, float aten_cat, float aten_cat_1) { { if (blockIdx.x<512 ? 1 : 0) { aten_cat_1[512 blockIdx.x + threadIdx.x] = ((((512 blockIdx.x + threadIdx.x) / 1024) % 256<192 ? 1 : 0) ? ((((512 blockIdx.x + threadIdx.x) / 1024) % 256<128 ? 1 : 0) ? __ldg(tinput0_60 + (512 blockIdx.x + threadIdx.x) % 262144) : ldg(tinput0_52 + (512 blockIdx.x + threadIdx.x) % 262144 - 131072)) : __ldg(tout3_71 + (512 blockIdx.x + threadIdx.x) % 262144 - 196608)); } aten_cat[512 blockIdx.x + threadIdx.x] = ((((512 blockIdx.x + threadIdx.x) / 4096) % 256<192 ? 1 : 0) ? ((((512 blockIdx.x + threadIdx.x) / 4096) % 256<128 ? 1 : 0) ? __ldg(tinput0_42 + (512 blockIdx.x + threadIdx.x) % 1048576) : ldg(tinput0_46 + (512 blockIdx.x + threadIdx.x) % 1048576 - 524288)) : __ldg(tout3_67 + (512 blockIdx.x + threadIdx.x) % 1048576 - 786432)); } }
landmark Det:: 1%|▍ | 1/168 [00:06<17:30, 6.29s/it]
Traceback (most recent call last):
File "inference.py", line 342, in
Good lord. I had to.
Uninstall Torch. Re-install Torch with Cuda (latest) (Through Conda not Pip) Install Numba Finally it worked.
Package Version
absl-py 1.4.0 addict 2.4.0 aiofiles 23.1.0 aiohttp 3.8.4 aiosignal 1.3.1 altair 5.0.1 anyio 3.7.0 async-timeout 4.0.2 attrs 23.1.0 audioread 3.0.0 basicsr 1.4.2 cachetools 5.3.1 certifi 2023.5.7 cffi 1.15.1 charset-normalizer 3.1.0 click 8.1.3 colorama 0.4.6 contourpy 1.1.0 cycler 0.11.0 decorator 5.1.1 dlib 19.24.0 einops 0.4.1 exceptiongroup 1.1.1 face-alignment 1.3.5 facexlib 0.2.5 fastapi 0.97.0 ffmpy 0.3.0 filelock 3.12.2 filterpy 1.4.5 fonttools 4.40.0 frozenlist 1.3.3 fsspec 2023.6.0 future 0.18.3 google-auth 2.20.0 google-auth-oauthlib 1.0.0 gradio 3.35.2 gradio_client 0.2.7 grpcio 1.54.2 h11 0.14.0 httpcore 0.17.2 httpx 0.24.1 huggingface-hub 0.15.1 idna 3.4 imageio 2.31.1 importlib-metadata 6.6.0 importlib-resources 5.12.0 Jinja2 3.1.2 joblib 1.2.0 jsonschema 4.17.3 kiwisolver 1.4.4 kornia 0.5.1 lazy_loader 0.2 librosa 0.9.2 linkify-it-py 2.0.2 llvmlite 0.40.1rc1 lmdb 1.4.1 Markdown 3.4.3 markdown-it-py 2.2.0 MarkupSafe 2.1.3 matplotlib 3.7.1 mdit-py-plugins 0.3.3 mdurl 0.1.2 multidict 6.0.4 networkx 3.1 ninja 1.10.2.3 numba 0.57.0 numpy 1.23.1 oauthlib 3.2.2 opencv-contrib-python 4.7.0.72 opencv-python 4.7.0.72 orjson 3.9.1 packaging 23.1 pandas 2.0.2 Pillow 9.5.0 pip 23.1.2 pkgutil_resolve_name 1.3.10 platformdirs 3.5.3 pooch 1.7.0 protobuf 4.23.3 pyasn1 0.5.0 pyasn1-modules 0.3.0 pycparser 2.21 pydantic 1.10.9 pydub 0.25.1 Pygments 2.15.1 pyparsing 3.0.9 pyrsistent 0.19.3 python-dateutil 2.8.2 python-multipart 0.0.6 pytz 2023.3 PyWavelets 1.4.1 PyYAML 6.0 requests 2.31.0 requests-oauthlib 1.3.1 resampy 0.4.2 rsa 4.9 scikit-image 0.21.0 scikit-learn 1.2.2 scipy 1.10.1 semantic-version 2.10.0 setuptools 67.8.0 six 1.16.0 sniffio 1.3.0 soundfile 0.12.1 starlette 0.27.0 tb-nightly 2.14.0a20230616 tensorboard-data-server 0.7.1 threadpoolctl 3.1.0 tifffile 2023.4.12 tomli 2.0.1 toolz 0.12.0 torch 1.13.0+cu117 torchvision 0.14.0+cu117 tqdm 4.65.0 typing_extensions 4.6.3 tzdata 2023.3 uc-micro-py 1.0.2 urllib3 1.26.16 uvicorn 0.22.0 websockets 11.0.3 Werkzeug 2.3.6 wheel 0.38.4 yapf 0.40.0 yarl 1.9.2 zipp 3.15.0
升级一下cuda117 的,我用的是4070TI的,升级后,就可以了。
第33行 keypoints.append(current_kp[-1]) 报错 list index out of range ,用的你们的例子我想请问一下是代码有问题吗谢谢