search

menyifang / DCT-Net

Official implementation of "DCT-Net: Domain-Calibrated Translation for Portrait Stylization", SIGGRAPH 2022 (TOG); Multi-style cartoonization
Apache License 2.0
734 stars 74 forks source link

Cannot run with GPU,it Works with CPU. #64

Closed ghost-woods closed 8 months ago

ghost-woods commented 8 months ago

I had a problem and asked for help.

(DCTNet_3_7) E:\WorkProject\DCT-Net\DCT-Net-main>python run.py
2023-11-09 15:46:06.950963: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll
2023-11-09 15:46:09,588 - modelscope - INFO - PyTorch version 1.13.1 Found.
2023-11-09 15:46:09,592 - modelscope - INFO - Loading ast index from C:\Users\ZhuoJin_Woods\.cache\modelscope\ast_indexer
2023-11-09 15:46:09,673 - modelscope - INFO - Loading done! Current index file version is 1.3.2, with md5 d37107262696ad2684b11874ef67dff7 and a total number of 754 components indexed
2023-11-09 15:46:09.783053: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
2023-11-09 15:46:09.786209: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library nvcuda.dll
2023-11-09 15:46:09.805638: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: NVIDIA GeForce RTX 3060 major: 8 minor: 6 memoryClockRate(GHz): 1.777
pciBusID: 0000:01:00.0
2023-11-09 15:46:09.805730: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll
2023-11-09 15:46:09.808113: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll
2023-11-09 15:46:09.810447: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_100.dll
2023-11-09 15:46:09.811517: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_100.dll
2023-11-09 15:46:09.815245: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_100.dll
2023-11-09 15:46:09.817922: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_100.dll
2023-11-09 15:46:09.825303: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2023-11-09 15:46:09.825456: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2023-11-09 15:50:43.355045: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2023-11-09 15:50:43.355178: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165]      0
2023-11-09 15:50:43.355304: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0:   N
2023-11-09 15:50:43.355570: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2457 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 3060, pci bus id: 0000:01:00.0, compute capability: 8.6)
2023-11-09 15:50:43.487275: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: NVIDIA GeForce RTX 3060 major: 8 minor: 6 memoryClockRate(GHz): 1.777
pciBusID: 0000:01:00.0
2023-11-09 15:50:43.487440: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll
2023-11-09 15:50:43.487557: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll
2023-11-09 15:50:43.487670: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_100.dll
2023-11-09 15:50:43.487773: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_100.dll
2023-11-09 15:50:43.487857: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_100.dll
2023-11-09 15:50:43.487943: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_100.dll
2023-11-09 15:50:43.488075: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2023-11-09 15:50:43.488218: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2023-11-09 15:50:43.488359: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2023-11-09 15:50:43.488482: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165]      0
2023-11-09 15:50:43.488605: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0:   N
2023-11-09 15:50:43.488784: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2457 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 3060, pci bus id: 0000:01:00.0, compute capability: 8.6)
2023-11-09 15:50:43.770491: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: NVIDIA GeForce RTX 3060 major: 8 minor: 6 memoryClockRate(GHz): 1.777
pciBusID: 0000:01:00.0
2023-11-09 15:50:43.770685: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll
2023-11-09 15:50:43.770780: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll
2023-11-09 15:50:43.770900: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_100.dll
2023-11-09 15:50:43.771012: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_100.dll
2023-11-09 15:50:43.771085: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_100.dll
2023-11-09 15:50:43.771220: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_100.dll
2023-11-09 15:50:43.771298: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2023-11-09 15:50:43.771448: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2023-11-09 15:50:43.771596: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2023-11-09 15:50:43.771697: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165]      0
2023-11-09 15:50:43.771796: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0:   N
2023-11-09 15:50:43.771994: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2457 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 3060, pci bus id: 0000:01:00.0, compute capability: 8.6)
loading model from damo/cv_unet_person-image-cartoon-3d_compound-models\cartoon_h.pb
load model damo/cv_unet_person-image-cartoon-3d_compound-models\cartoon_h.pb done.
2023-11-09 15:50:43.889482: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties:
name: NVIDIA GeForce RTX 3060 major: 8 minor: 6 memoryClockRate(GHz): 1.777
pciBusID: 0000:01:00.0
2023-11-09 15:50:43.889587: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll
2023-11-09 15:50:43.889700: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll
2023-11-09 15:50:43.889813: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cufft64_100.dll
2023-11-09 15:50:43.889918: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library curand64_100.dll
2023-11-09 15:50:43.889992: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusolver64_100.dll
2023-11-09 15:50:43.890066: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cusparse64_100.dll
2023-11-09 15:50:43.890151: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2023-11-09 15:50:43.890263: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2023-11-09 15:50:43.890349: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2023-11-09 15:50:43.890412: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165]      0
2023-11-09 15:50:43.890476: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0:   N
2023-11-09 15:50:43.890603: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2457 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce RTX 3060, pci bus id: 0000:01:00.0, compute capability: 8.6)
loading model from damo/cv_unet_person-image-cartoon-3d_compound-models\cartoon_bg.pb
load model damo/cv_unet_person-image-cartoon-3d_compound-models\cartoon_bg.pb done.
2023-11-09 15:50:44.123981: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudnn64_7.dll
2023-11-09 16:06:57.236153: W tensorflow/stream_executor/cuda/redzone_allocator.cc:312] Internal: Invoking ptxas not supported on Windows
Relying on driver to perform ptx compilation. This message will be only logged once.
2023-11-09 16:06:57.276485: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cublas64_100.dll
100
No face detected!
finished!

error:"Internal: Invoking ptxas not supported on Windows"

python 3.7.12/tensorflow-gpu 1.15.0/CUDA 10.0/cuDNN 7.6.5.32 RTX 3060 driver version：471.41 or 546.01 neither work

Do I need a newer graphics card or an older graphics card？Such as 20 series or 40 series?

Chinese: 报错："Internal: Invoking ptxas not supported on Windows" cuda/cudnn都能正确加载，ptxas报错我不知道是为什么，我是不是需要换20系或者40系的显卡试试，搜索到的一些解决方案说是换了显卡，或者降低tf版本，但是DCT-Net需要>=1.15.0的版本 何解？