You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This is very cool, I always wanted to use "CUDA only" software in other hardware like though Vulkan.
I've installed Tencent's ncnn for python (had to clone and compile, pip couldn't find ncnn wheel) but have no idea how to adapt the transformations in your C code example for python
This is very cool, I always wanted to use "CUDA only" software in other hardware like though Vulkan.
I've installed Tencent's ncnn for python (had to clone and compile, pip couldn't find ncnn wheel) but have no idea how to adapt the transformations in your C code example for python
`
import sys
import cv2
import numpy as np
import ncnn
net = ncnn.Net()
#net.opt.use_vulkan_compute = net.use_gpu
net.load_param("deoldify.256.param")
net.load_model("deoldify.256.bin")
path = 'image.png'
input=cv2.imread(path,cv2.IMREAD_GRAYSCALE)
mat_in = ncnn.Mat.from_pixels_resize(input,ncnn.Mat.PixelType.PIXEL_BGR2RGB,input.shape[1],input.shape[0],256,256)
ex = net.create_extractor()
ex.input("input",mat_in)
mat_out = ncnn.Mat()
ret, mat_out = ex.extract("out")
`
after this I'm unsure about the transformations needed to write a valid image
The text was updated successfully, but these errors were encountered: