From 23d180fd8dcb3acc399e3d0ea61b6dad08520ed6 Mon Sep 17 00:00:00 2001 From: Xintao Date: Thu, 5 May 2022 22:46:17 +0800 Subject: [PATCH] Update FAQ Error "slow_conv2d_cpu" not implemented for 'Half' --- docs/FAQ.md | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/docs/FAQ.md b/docs/FAQ.md index 0f5fc85..843f4dd 100644 --- a/docs/FAQ.md +++ b/docs/FAQ.md @@ -1,7 +1,10 @@ # FAQ -1. **How to select models?**
+1. **Q: How to select models?**
A: Please refer to [docs/model_zoo.md](docs/model_zoo.md) -1. **Can `face_enhance` be used for anime images/animation videos?**
+1. **Q: Can `face_enhance` be used for anime images/animation videos?**
A: No, it can only be used for real faces. It is recommended not to use this option for anime images/animation videos to save GPU memory. + +1. **Q: Error "slow_conv2d_cpu" not implemented for 'Half'**
+A: In order to save GPU memory consumption and speed up inference, Real-ESRGAN uses half precision (fp16) during inference by default. However, some operators for half inference are not implemented in CPU mode. You need to add **`--fp32` option** for the commands. For example, `python inference_realesrgan.py -n RealESRGAN_x4plus.pth -i inputs --fp32`.