Comments (15)
@l-bat Can you check, please?
from openvino_notebooks.
@l-bat Yes
from openvino_notebooks.
I tried to use another Machine type
on Google Cloud: before I was using e2-highmem-8
but after I changed to n2-highmem-8
it all worked. Also, I used the last version of the tutorial Notebook.
from openvino_notebooks.
@MarkYav, Thanks for reporting the problem. Unfortunately, I'm not able reproduce provided error. Maybe there is something additional specific details?
which datasets
, controlnet-aux
, pytorch
, transformers
and diffusers
version do you use?
from openvino_notebooks.
@l-bat Thank you for your prompt reply!
On Kaggle:
datasets 2.17.1
controlnet_aux 0.0.7
pytorch-ignite 0.4.13
pytorch-lightning 2.1.3
transformers 4.37.0
diffusers 0.26.3
The full list could be found here: https://pastebin.com/WGGLrYT5
Also, it runs on Colab Enterprise with installed libs (see the list mentioned below). But the problem is that after quantization the generated image is bad (see photo).
It extracts the pose correctly, tho:
Installed libs Colab Enterprise: https://pastebin.com/U0GtqC4r
from openvino_notebooks.
@MarkYav, what inference device do you use? Looks like a problem with the calibration data or with device.
from openvino_notebooks.
@l-bat I use Colab Enterprise on Google Cloud. There are details:
from openvino_notebooks.
@MarkYav, do you use CPU
here?
from openvino_notebooks.
@MarkYav, could you please try downloading the unet_calibration_data.pkl and loading it into notebook instead of preparing a calibration dataset? This will help me to understand if there is problem with data preparation.
import pickle
with open('unet_calibration_data.pkl', 'rb') as f:
unet_calibration_data = pickle.load(f)
from openvino_notebooks.
@l-bat I tried to run the notebook using the code provided.
I changed:
%%skip not $to_quantize.value
CONTROLNET_INT8_OV_PATH = Path("controlnet-pose_int8.xml")
UNET_INT8_OV_PATH = Path("unet_controlnet_int8.xml")
# These are commented lines:
# if not (CONTROLNET_INT8_OV_PATH.exists() and UNET_INT8_OV_PATH.exists()):
# unet_calibration_data = collect_calibration_data(ov_pipe, subset_size=subset_size)
# These are new inserted lines:
import pickle
with open('unet_calibration_data.pkl', 'rb') as f:
unet_calibration_data = pickle.load(f)
And I got an error in the next cell:
I checked the code and the length of the downloaded unet_calibration_data
is 20:
In this cell the prev_idx
is initially set to 0, and in the loop goes from 0 to 19. But the problem is that later we set prev_idx += num_inference_steps
and now prev_idx
is 20 and will go from 20 to 39 -- here we have a list index out of range
exception. See photos:
Thus, I assume there is a bug in the calibration dataset preparation OR usage.
from openvino_notebooks.
@MarkYav, I uploaded small subset of unet_calibration_data
, which contains 20 samples.
I forgot to mention that you should also change size of subset_size
to 20 (instead of 200) to align input_data
with unet_calibration_data
from openvino_notebooks.
@l-bat I tried to run it but got the same output:
Right after that I generated a picture using the NOT quantized model and got this:
I was using ov_pipe(prompt, pose, 20, negative_prompt=negative_prompt)
. Also, I am surprised that the generated image is square.
from openvino_notebooks.
@MarkYav, if you can provide cat /proc/cpuinfo
maybe I can find a suitable configuration to reproduce the error
from openvino_notebooks.
@MarkYav could we close the issue?
from openvino_notebooks.
@l-bat Yes, please.
from openvino_notebooks.
Related Issues (20)
- Is LLama3 model (int4) compiled for NPU compatible to connect Langchain based RAG system HOT 2
- Unable to compile Llama3 8B model for NPU using Openvino (we have latest NPU drivers - April 2024 version) HOT 2
- [Issue]: KeyError: "phi3 is not supported yet for transformers. HOT 1
- There is a problem with openvino's yolov8 tutorial. HOT 5
- Pip install intel-extension-for-pytorch does not work. HOT 2
- LLM-chatbot llama3 model issue HOT 1
- setuptools version error
- [GH Pages] Any buttons on notebook cards will open its document anyway instead of doing it's expected action
- llm-rag-langchain answer wrongly when using llama-3-8b-instruct HOT 5
- notebooks\hello-npu return error HOT 25
- Issue running Yolov8 segmentation example HOT 4
- Why not python sample code instead of Colab? HOT 2
- iGPU memory usage problem HOT 8
- supplementary_materials /qwen2 have api HOT 2
- Cannot create StringTensorUnpack layer StringTensorUnpack_220719 id:5 from unsupported opset: extension HOT 2
- Custom AI Assistant recipe fails to convert and optimize model HOT 2
- llm-chatbot-generate-api notebook fails during pip / git install routine HOT 3
- openVINO2024.3.0 gave RuntimeError:[GPU] ProgramBuilder build failed! at notebook:3D-segmentation-point-clouds, when using Integrated GPU HOT 2
- Problem with openvino's yolov8-keypoint-detection tutorial HOT 3
- RuntimeError: probability tensor contains either `inf`, `nan` or element < 0 when running parler-tts-text-to-speech.ipynb HOT 1
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 openvino_notebooks.