cudacanvas : PyTorch Tensor Image Display in CUDA

(Real-time PyTorch Tensor Image Visualisation in CUDA, Eliminating CPU Transfer)

CudaCanvas is a simple Python module that eliminates CPU transfer for Pytorch tensors for displaying and rendering images in the training or evaluation phase, ideal for machine learning scientists and engineers.

Simplified version that directly displays the image without explicit window creation (cudacanvas >= v1.0.1)

import torch
import cudacanvas


#REPLACE THIS with you training loop
while (True):

    #REPLACE THIS with you training code and generation of data
    noise_image = torch.rand((4, 500, 500), device="cuda")

    #Visualise your data in real-time
    cudacanvas.im_show(noise_image)

    #OPTIONAL: Terminate training when the window is closed
    if cudacanvas.should_close():
        cudacanvas.clean_up()
        #end process if the window is closed
        break

You can visualise the latent of Stable Diffusion during sampling in real-time whilst waiting for the steps to finish

import warnings
warnings.filterwarnings("ignore")
from diffusers import StableDiffusionPipeline
import torch
import cudacanvas

def display_tensors(pipe, step, timestep, callback_kwargs):
    latents = callback_kwargs["latents"]

    with torch.no_grad():
        image = pipe.vae.decode(latents / pipe.vae.config.scaling_factor, return_dict=False)[0]
        image = image - image.min()
        image = image / image.max()
    
    cudacanvas.im_show(image.squeeze(0))
    
    if cudacanvas.should_close():
        cudacanvas.clean_up()
        pipe._interrupt = True
    
    return callback_kwargs

pipeline = StableDiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-2-1-base",
    torch_dtype=torch.float16,
    variant="fp16"
).to("cuda")

image = pipeline(
    prompt="A croissant shaped like a cute bear.",
    negative_prompt="Deformed, ugly, bad anatomy",
    callback_on_step_end=display_tensors,
    callback_on_step_end_tensor_inputs=["latents"],
).images[0]

cudacanvas.clean_up()

Installation

Before instllation make sure you have torch with cuda support already installed on your machine

We aligned pytorch and cuda version with our package the supporting packages are torch (2.0.1, 2.1.2 and 2.2.2) and (11.8 and 12.1)

Identify your current torch and cuda version

import torch
torch.__version__

Depending on your torch and cuda you can install the relevant cudacanvas package, for the latest one matching the latest pytorch package you can simply download the latest package

pip install cudacanvas

For other torch and cuda packages put the torch and cuda version after that cudacanvas version for example for 2.1.2+cu118 the Cudacanvas package you require is 1.0.1.post212118

pip install cudacanvas==1.0.1.post212118 --force-reinstall

Support

Also support my channel ☕ ☕ : https://www.buymeacoffee.com/outofai

Metadata

Release files for cudacanvas 1.0.1.post260126

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for cudacanvas 1.0.1.post260126
File	Interpreter	ABI	Platform	Reset
cudacanvas-1.0.1.post260126-cp311-cp311-win_amd64.whl 101.8 kB Jan 30, 2025	CPython 3.11	CPython 3.11	Windows x86-64	Details
cudacanvas-1.0.1.post260126-cp311-cp311-manylinux2014_x86_64.whl 90.7 kB Jan 30, 2025	CPython 3.11	CPython 3.11	Linux glibc 2.17+ x86-64	Details
cudacanvas-1.0.1.post260126-cp310-cp310-win_amd64.whl 100.6 kB Jan 30, 2025	CPython 3.10	CPython 3.10	Windows x86-64	Details
cudacanvas-1.0.1.post260126-cp310-cp310-manylinux2014_x86_64.whl 89.0 kB Jan 30, 2025	CPython 3.10	CPython 3.10	Linux glibc 2.17+ x86-64	Details
cudacanvas-1.0.1.post260126-cp39-cp39-win_amd64.whl 101.1 kB Jan 30, 2025	CPython 3.9	CPython 3.9	Windows x86-64	Details
cudacanvas-1.0.1.post260126-cp39-cp39-manylinux2014_x86_64.whl 88.3 kB Jan 30, 2025	CPython 3.9	CPython 3.9	Linux glibc 2.17+ x86-64	Details

Total release size: 571.4 kB

Release files / cudacanvas-1.0.1.post260126-cp311-cp311-win_amd64.whl

Download URL	cudacanvas-1.0.1.post260126-cp311-cp311-win_amd64.whl
Size	101.8 kB
Tags	CPython 3.11 Windows x86-64
SHA-256 checksum How to use checksums	`b68b28e13fbb1957a5e119bac3d7cf5bced6e7abe9c180633e2e7a150eb2f94c`
BLAKE2b-256 checksum How to use checksums	`8105afc2751ada3c8f23b798e6437c31ed92cb0fb63daeebba655fc450481217`
Upload date	Jan 30, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.2 CPython/3.10.11`

Release files / cudacanvas-1.0.1.post260126-cp311-cp311-manylinux2014_x86_64.whl

Download URL	cudacanvas-1.0.1.post260126-cp311-cp311-manylinux2014_x86_64.whl
Size	90.7 kB
Tags	CPython 3.11 Linux glibc 2.17+ x86-64
SHA-256 checksum How to use checksums	`98c32064358b8a521504f8f47c58e3db5e2768a2162bd7914b31a4cec50a1684`
BLAKE2b-256 checksum How to use checksums	`ad28436338254198d44b0f15328d0a77cfec8b489636b4b82108c3409972b1d6`
Upload date	Jan 30, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.2 CPython/3.10.11`

Release files / cudacanvas-1.0.1.post260126-cp310-cp310-win_amd64.whl

Download URL	cudacanvas-1.0.1.post260126-cp310-cp310-win_amd64.whl
Size	100.6 kB
Tags	CPython 3.10 Windows x86-64
SHA-256 checksum How to use checksums	`a988bc720b9d8b3ade47ed05c548182c2d647c74f9dee58258ba5bd5cc5c2911`
BLAKE2b-256 checksum How to use checksums	`6f9fd7faa4e7a08d04708743ff750a98948a1a2f8cc2a16a6846d0752c1e949f`
Upload date	Jan 30, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.2 CPython/3.10.11`

Release files / cudacanvas-1.0.1.post260126-cp310-cp310-manylinux2014_x86_64.whl

Download URL	cudacanvas-1.0.1.post260126-cp310-cp310-manylinux2014_x86_64.whl
Size	89.0 kB
Tags	CPython 3.10 Linux glibc 2.17+ x86-64
SHA-256 checksum How to use checksums	`5ceccd1f2b974f52d0bec887b0a7e6d8817db7c7bb0a94e2c45c5f615e99161d`
BLAKE2b-256 checksum How to use checksums	`1586aa1436dd89eba94baf2d55d6f2dcc53b0112e32f12f6edc7617851f45e9d`
Upload date	Jan 30, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.2 CPython/3.10.11`

Release files / cudacanvas-1.0.1.post260126-cp39-cp39-win_amd64.whl

Download URL	cudacanvas-1.0.1.post260126-cp39-cp39-win_amd64.whl
Size	101.1 kB
Tags	CPython 3.9 Windows x86-64
SHA-256 checksum How to use checksums	`4eabf742a2def065140abbe82e91f7c5c3d6766c23bee09eba71627291f1dc67`
BLAKE2b-256 checksum How to use checksums	`807f285f9605ea0973b91ffaf50cc8f996b93a0b13fba5b971051637d99c073a`
Upload date	Jan 30, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.2 CPython/3.10.11`

Release files / cudacanvas-1.0.1.post260126-cp39-cp39-manylinux2014_x86_64.whl

Download URL	cudacanvas-1.0.1.post260126-cp39-cp39-manylinux2014_x86_64.whl
Size	88.3 kB
Tags	CPython 3.9 Linux glibc 2.17+ x86-64
SHA-256 checksum How to use checksums	`3187d9218b3c93d5246553c30e7225fb9d14137f7c087d65c15886a573ab824d`
BLAKE2b-256 checksum How to use checksums	`80165049214f22c7394706315bf51c0096ca93e0b71da7e50568a9b835137971`
Upload date	Jan 30, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.2 CPython/3.10.11`