MagicSource

OOM on GTX1080ti with 128 image size

1

I fixed my trained model load problem and the weight seems load successfully. But when inference I got OOM, here is my config and inference code: ```python """ Generate random...

Can you teach me what your code is doing?

2

Hi, I am new to StyleGAN. I want write a simple inference demo to generate a single image using a simple noise latent vector by random. I am currently got...

Nice work! Any GPU memory consume suggestions?

3

Original version train a 1024 input size model on 8 GPUs, will OOM. I have 4 GPUs, all with 10G memory, what's the max input size I can train?

Hi, I am showing a mesh like this: ``` mesh = trimesh.Trimesh(vertices=frame_verts, faces=renderer.faces) mesh.show() ``` the values of verts and faces like this: but I got error when showing: ```...

any demo voice result?

No result

15

I convert pynb to python but I got no output: ```python from trt_pose.parse_objects import ParseObjects from trt_pose.draw_objects import DrawObjects import PIL.Image import torchvision.transforms as transforms import cv2 import time from...

what's the model of it ?

1

It's topdown model or bottom up model? Needs a detector or not?

ttf supported?

Does the mask error really because of BitMask?

2

Hi, I recently found original SparseInst code fails to visualize as well which I totally don't why, but I investigated a little, maybe same with your found bug, I want...

efficientnet with FPN can not be run

4

efficient output shape are: ``` EEE: 0 torch.Size([4, 16, 512, 400]) EEE: 1 torch.Size([4, 24, 256, 200]) EEE: 2 torch.Size([4, 80, 64, 50]) EEE: 3 torch.Size([4, 112, 64, 50]) ```...