Closed NavdeepD2 closed 11 months ago
This is an out of memory error, as clearly stated in the error report. Get a bigger GPU or use a smaller model, or follow one of these remedial steps:
https://forum.faceswap.dev/app.php/faqpage?sid=c6e8313d10e2337cd3f53f966ec88875#f3r9
Either way, this is not a bug.
When doing Train, facing following error:
No algorithm worked! Error messages: Profiling failure on CUDNN engine 1#TC: RESOURCE_EXHAUSTED: Out of memory while trying to allocate 95420720 bytes. Profiling failure on CUDNN engine 1: RESOURCE_EXHAUSTED: Out of memory while trying to allocate 95420432 bytes. Profiling failure on CUDNN engine 0#TC: RESOURCE_EXHAUSTED: Out of memory while trying to allocate 16777216 bytes. Profiling failure on CUDNN engine 0: RESOURCE_EXHAUSTED: Out of memory while trying to allocate 16777216 bytes. [[{{node gradient_tape/original/encoder/upscale_512_0_conv2d_conv2d/Conv2D_1/Conv2DBackpropInput}}]] [Op:__inference_train_function_7782] 10/15/2023 03:11:20 CRITICAL An unexpected crash has occurred. Crash report written to 'C:\Users\navde\faceswap\crash_report.2023.10.15.031116815608.log'. You MUST provide this file if seeking assistance. Please verify you are running the latest version of faceswap before reporting Process exited.
My system: OS Name Microsoft Windows 11 Home Single Language Version 10.0.22621 Build 22621 Processor 12th Gen Intel(R) Core(TM) i5-12500H Physical Memory (RAM) 16.0 GB GPU NVIDIA GeForce RTX 3050 Laptop GPU