Last active
October 12, 2023 23:11
-
-
Save atabakd/e4fa20c23f7a6059dac794a82dccfb38 to your computer and use it in GitHub Desktop.
Differing results in cpu/cuda compared to mps
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import numpy as np | |
import torch | |
from PIL import Image | |
def gather(consts: torch.Tensor, t: torch.Tensor): | |
"""Gather consts for $t$ and reshape to feature map shape""" | |
c = consts.gather(-1, t) | |
return c.reshape(-1, 1, 1, 1) | |
def img_to_tensor(im): | |
return ( | |
torch.tensor(np.array(im.convert("RGB")) / 255, dtype=torch.float32) | |
.permute(2, 0, 1) | |
.unsqueeze(0) | |
* 2 | |
- 1 | |
) | |
def tensor_to_image(t): | |
return Image.fromarray( | |
np.array(((t.squeeze().permute(1, 2, 0) + 1) / 2).clip(0, 1) * 255).astype( | |
np.uint8 | |
) | |
) | |
def q_xt_xtminus1(xtm1, t, beta): | |
mean = gather(1.0 - beta, t) ** 0.5 * xtm1 | |
var = gather(beta, t) | |
eps = torch.randn_like(xtm1) # Noise shaped like xtm1 | |
return mean + (var**0.5) * eps | |
def add_noise(x, num_steps, device, save_every=1): | |
x = x.to(device) | |
beta = torch.linspace(0.0001, 0.04, num_steps).to(device) | |
out_imgs = list() | |
for t in range(num_steps): | |
if t % save_every == 0: | |
out_imgs.append(tensor_to_image(x.cpu())) | |
t = torch.tensor(t, dtype=torch.long).to(device) | |
x = q_xt_xtminus1(x, t, beta) | |
return out_imgs | |
if __name__ == "__main__": | |
num_steps = 100 | |
save_every = 20 | |
assert num_steps % save_every == 0, "num_steps must be divisible by save_every" | |
# Download a sample from cifar10 dataset | |
if not os.path.exists("cifar10.png"): | |
os.system( | |
"curl 'https://raw.githubusercontent.com/YoongiKim/CIFAR-10-images/master/train/horse/0003.jpg' > cifar10.png" | |
) | |
# Load image and convert to tensor of size 32x32 | |
im = Image.open("cifar10.png").resize((32, 32)) | |
x = img_to_tensor(im) | |
mps_images = add_noise(x, num_steps, "mps", save_every) | |
del x, im | |
torch.cuda.empty_cache() | |
######### clear cache ######### | |
im = Image.open("cifar10.png").resize((32, 32)) | |
x = img_to_tensor(im) | |
cpu_images = add_noise(x, num_steps, "cpu", save_every) | |
# Save images | |
image = Image.new("RGB", (32 * num_steps // save_every, 32 * 2)) | |
for i, (cpu_im, mps_im) in enumerate(zip(cpu_images, mps_images)): | |
image.paste(cpu_im, (32 * i, 0)) | |
image.paste(mps_im, (32 * i, 32)) | |
image.save("cpu_mps.png") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment