Comments (9)
from onnxstream.
from onnxstream.
from onnxstream.
I get the same (or similar) segmentation error, a fresh build as of 7th April 2024;
On a raspberry Pi 5; I dont believe its a memory issue either; I did note the build returned a number of warning messages
free command shows
total used free shared buff/cache available
Mem: 8241616 256128 426704 5616 7663600 7985488
Swap: 102384 0 102384
time ./sd --turbo --rpi --models-path $baseDir/stable-diffusion-xl-turbo-1.0-onnxstream --prompt "An astronaut riding a horse" --steps 1 --output astronaut.png
----------------[start]------------------
positive_prompt: An astronaut riding a horse
SDXL turbo doesn't support negative_prompts
output_png_path: astronaut.png
steps: 1
seed: 526336
----------------[prompt]------------------
Token: "A"
Token: "n"
Token: "astronaut"
Token: "riding"
Token: "a"
Token: "horse"
----------------[diffusion]---------------
step:0 101016ms
----------------[decode]------------------
Segmentation fault
real 3m47.597s
user 9m8.696s
sys 0m33.962s
Warning messages shown on compilation :-
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c: In function ‘cpuinfo_arm_linux_decode_chipset’:
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c:3931:25: warning: ‘cpuinfo_arm_fixup_raspberry_pi_chipset’ reading 64 bytes f rom a region of size 9 [-Wstringop-overread]
3931 | cpuinfo_arm_fixup_raspberry_pi_chipset(&chipset, revision);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c:3931:25: note: referencing argument 2 of type ‘const char[64]’
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c:3855:14: note: in a call to function ‘cpuinfo_arm_fixup_raspberry_pi_chipset’
3855 | void cpuinfo_arm_fixup_raspberry_pi_chipset(
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c:3931:25: warning: ‘cpuinfo_arm_fixup_raspberry_pi_chipset’ reading 64 bytes f rom a region of size 9 [-Wstringop-overread]
3931 | cpuinfo_arm_fixup_raspberry_pi_chipset(&chipset, revision);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c:3931:25: note: referencing argument 2 of type ‘const char[64]’
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c:3855:14: note: in a call to function ‘cpuinfo_arm_fixup_raspberry_pi_chipset’
3855 | void cpuinfo_arm_fixup_raspberry_pi_chipset(
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c: In function ‘cpuinfo_arm_linux_decode_chipset’:
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c:3931:25: warning: ‘cpuinfo_arm_fixup_raspberry_pi_chipset’ reading 64 bytes f rom a region of size 9 [-Wstringop-overread]
3931 | cpuinfo_arm_fixup_raspberry_pi_chipset(&chipset, revision);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c:3931:25: note: referencing argument 2 of type ‘const char[64]’
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c:3855:14: note: in a call to function ‘cpuinfo_arm_fixup_raspberry_pi_chipset’
3855 | void cpuinfo_arm_fixup_raspberry_pi_chipset(
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c:3931:25: warning: ‘cpuinfo_arm_fixup_raspberry_pi_chipset’ reading 64 bytes f rom a region of size 9 [-Wstringop-overread]
3931 | cpuinfo_arm_fixup_raspberry_pi_chipset(&chipset, revision);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c:3931:25: note: referencing argument 2 of type ‘const char[64]’
/home/pi/onxx-stream/XNNPACK/build/cpuinfo-source/src/arm/linux/chipset.c:3855:14: note: in a call to function ‘cpuinfo_arm_fixup_raspberry_pi_chipset’
3855 | void cpuinfo_arm_fixup_raspberry_pi_chipset(
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
from onnxstream.
Same error as before this time without the --rpi parm
pi@raspberrypi:~/onxx-stream/OnnxStream/src/build $ time ./sd --turbo --models-path $baseDir/stable-diffusion-xl-turbo-1.0-onnxstream --prompt "An astronaut riding a horse on mars" --steps 1 --output astronaut.png
----------------[start]------------------
positive_prompt: An astronaut riding a horse on mars
SDXL turbo doesn't support negative_prompts
output_png_path: astronaut.png
steps: 1
seed: 0
----------------[prompt]------------------
Token: "A"
Token: "n"
Token: "astronaut"
Token: "riding"
Token: "a"
Token: "horse"
Token: "on"
Token: "mars"
----------------[diffusion]---------------
step:0 67418ms
----------------[decode]------------------
Segmentation fault
real 3m31.399s
user 7m33.962s
sys 0m22.208s
pi@raspberrypi:~/onxx-stream/OnnxStream/src/build $
I will try this on a PI Zero 2, as soon as I can find it
from onnxstream.
from onnxstream.
let me try that, I found my Zero2 and been trying to get that working; different problems!
cant get it to complete build, forget running the sd command; no matter you learn more when it fails :)
Thanks for you help
from onnxstream.
Same error; same with and without --rpi parameter
pi@raspberrypi:~/onxx-stream/OnnxStream/src/build $ time ./sd --turbo --not-tiled --models-path $baseDir/stable-diffusion-xl-turbo-1.0-onnxstream --prompt "an astronaut riding a horse on mars" --steps 1 --output astronaut.png
----------------[start]------------------
positive_prompt: an astronaut riding a horse on mars
SDXL turbo doesn't support negative_prompts
output_png_path: astronaut.png
steps: 1
seed: 882688
----------------[prompt]------------------
Token: "an"
Token: "astronaut"
Token: "riding"
Token: "a"
Token: "horse"
Token: "on"
Token: "mars"
----------------[diffusion]---------------
step:0 35758ms
----------------[decode]------------------
Segmentation fault
real 2m3.277s
user 4m11.563s
sys 0m16.113s
pi@raspberrypi:~/onxx-stream/OnnxStream/src/build $
I also tried and failed to get it working on PI Zero 2 (see screenshot),
it go so far into the build and got stuck filtering content 15% 406/2640; left it running overnight and did not progress further, could not break out of it had to pull the power out
I will take a break and follow the instructions u shared previously, the steps are a little different; I will keep everyone posted
from onnxstream.
Thanks Vito, appreciate the feedback, I found myself going round in circles and each turn was a failure; I'm taking a breather and will try again over the weekend. the livinglinux example you shared the website lists a command which downloaded a windows package, which threw me somewhat when it failed. ill do a clean build later to ensure I dont get any errors from the past installs
from onnxstream.
Related Issues (20)
- Error build HOT 8
- [feature request] Whisper with openblas HOT 3
- [question] your Mistral-to-ONNX export script HOT 2
- [question] why to convert model from ONNX to TXT format? HOT 1
- Username and password required? HOT 1
- How open are you to code-refactoring Pull Requests? HOT 2
- Stable Diffisuon 1.5 installation from? HOT 3
- changing image size HOT 2
- UnsupportedOperatorError: Exporting the operator ::_transformer_encoder_layer_fwd to ONNX opset HOT 2
- Tensor memory layout HOT 7
- Add support for 1 step diffusion (DMD) HOT 1
- vae_decoder_qu8/range_data.txt value generation HOT 1
- Pi Zero 2w 32bit build of xnnpack failing HOT 7
- Onnxstream won't build HOT 2
- 403 error HOT 1
- Safetensors? HOT 4
- Any updates in generating dynamic shape images? HOT 3
- Is there some methods to directly load the negative prompt embedding? HOT 2
- Is there an error in "Cast" operator? HOT 2
- Change resolution? HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from onnxstream.