Software Engineering Courses (SECourses)•16mo ago

@Dr. Furkan Gözükara morning, could you double check this, =10:38:16.887 [Info] Self-Start ComfyUI-

@Dr. Furkan Gözükara morning, could you double check this, =10:38:16.887 [Info] Self-Start ComfyUI-0 unexpectedly exited (if something failed, change setting LogLevel to Debug to see why!)
10:38:16.887 [Info] Self-Start ComfyUI-0 had errors before shutdown:
[ComfyUI-0/STDERR] Traceback (most recent call last):
[ComfyUI-0/STDERR] File "/kaggle/working/SwarmUI/dlbackend/ComfyUI/main.py", line 87, in <module>
[ComfyUI-0/STDERR] import comfy.utils
[ComfyUI-0/STDERR] File "/kaggle/working/SwarmUI/dlbackend/ComfyUI/comfy/utils.py", line 20, in <module>
[ComfyUI-0/STDERR] import torch
[ComfyUI-0/STDERR] File "/kaggle/working/SwarmUI/dlbackend/ComfyUI/venv/lib/python3.10/site-packages/torch/init.py", line 290, in <module>
[ComfyUI-0/STDERR] from torch._C import * # noqa: F403
[ComfyUI-0/STDERR] ImportError: /kaggle/working/SwarmUI/dlbackend/ComfyUI/venv/lib/python3.10/site-packages/torch/lib/../../nvidia/cusparse/lib/libcusparse.so.12: undefined symbol: __nvJitLinkComplete_12_4, version libnvJitLink.so.12, I have experienced a lot these days

Vvirginia @Dr. Furkan Gözükara morning, could you double check this, =10:38:16.887 [Info]...

Furkan Gözükara SECourses•9/3/24, 10:40 AM

kaggle broken due to comfyui update

Furkan Gözükara SECourses•9/3/24, 10:40 AM

i reported to both comfyui developer

Furkan Gözükara SECourses•9/3/24, 10:40 AM

and pytorch

Furkan Gözükara SECourses•9/3/24, 10:40 AM

https://github.com/pytorch/pytorch/issues/134929

GitHub

On Kaggle : libcusparse.so.12: undefined symbol: __nvJitLinkComplet...

Describe the bug I have tried everything but no luck Waiting your inputs to try more I tried torch 2.4.0, 2.5 - dev, cu 118, cu121 and cu124 - all same error This below code - I got the same erro...

Furkan Gözükara SECourses•9/3/24, 10:40 AM

no solution yet

Tacite•9/3/24, 11:00 AM

@Dr. Furkan Gözükara I just downloaded your JoyCaption V12 zip file. Inside is the V11 and also got the NumPy error

TTacite @Dr. Furkan Gözükara I just downloaded your JoyCaption V12 zip file. Inside is t...

Furkan Gözükara SECourses•9/3/24, 11:03 AM

pythonm mismatch very likely

Furkan Gözükara SECourses•9/3/24, 11:03 AM

what is ypur default python

Tacite•9/3/24, 11:04 AM

it works fine it's just a warning

virginiaOP•9/3/24, 11:04 AM

okay thanks a lot

Tacite•9/3/24, 11:04 AM

I have 3.10.14

Tacite•9/3/24, 11:05 AM

ah no, it says finished but theres no file

TTacite ah no, it says finished but theres no file

Furkan Gözükara SECourses•9/3/24, 11:06 AM

check outputs folder

TTacite I have 3.10.14

Furkan Gözükara SECourses•9/3/24, 11:06 AM

it should work

Tacite•9/3/24, 11:07 AM

Process Process-2:
Traceback (most recent call last):
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\feature_extraction_utils.py", line 183, in convert_to_tensors
    tensor = as_tensor(value)
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\feature_extraction_utils.py", line 142, in as_tensor
    return torch.tensor(value)
RuntimeError: Could not infer dtype of numpy.float32

Process Process-2:
Traceback (most recent call last):
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\feature_extraction_utils.py", line 183, in convert_to_tensors
    tensor = as_tensor(value)
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\feature_extraction_utils.py", line 142, in as_tensor
    return torch.tensor(value)
RuntimeError: Could not infer dtype of numpy.float32

Tacite•9/3/24, 11:07 AM

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Program Files\Python310\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Program Files\Python310\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "E:\Joy_Caption_v12\app.py", line 335, in process_gpu_batch
    images = clip_processor(images=batch_images, return_tensors='pt', padding=True).pixel_values.to(device)
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\models\siglip\processing_siglip.py", line 113, in __call__
    image_features = self.image_processor(images, return_tensors=return_tensors)
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\image_processing_utils.py", line 41, in __call__
    return self.preprocess(images, **kwargs)
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\models\siglip\image_processing_siglip.py", line 259, in preprocess
    return BatchFeature(data=data, tensor_type=return_tensors)
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\feature_extraction_utils.py", line 79, in __init__
    self.convert_to_tensors(tensor_type=tensor_type)
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\feature_extraction_utils.py", line 189, in convert_to_tensors
    raise ValueError(
ValueError: Unable to create tensor, you should probably activate padding with 'padding=True' to have batched tensors with the same length.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Program Files\Python310\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Program Files\Python310\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "E:\Joy_Caption_v12\app.py", line 335, in process_gpu_batch
    images = clip_processor(images=batch_images, return_tensors='pt', padding=True).pixel_values.to(device)
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\models\siglip\processing_siglip.py", line 113, in __call__
    image_features = self.image_processor(images, return_tensors=return_tensors)
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\image_processing_utils.py", line 41, in __call__
    return self.preprocess(images, **kwargs)
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\models\siglip\image_processing_siglip.py", line 259, in preprocess
    return BatchFeature(data=data, tensor_type=return_tensors)
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\feature_extraction_utils.py", line 79, in __init__
    self.convert_to_tensors(tensor_type=tensor_type)
  File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\feature_extraction_utils.py", line 189, in convert_to_tensors
    raise ValueError(
ValueError: Unable to create tensor, you should probably activate padding with 'padding=True' to have batched tensors with the same length.

Tacite•9/3/24, 11:08 AM

i will try to downgrade numpy

TTacite ```Process Process-2: Traceback (most recent call last): File "E:\Joy_Caption_...

Furkan Gözükara SECourses•9/3/24, 11:08 AM

let me reinstlal

Furkan Gözükara SECourses•9/3/24, 11:08 AM

this shouldnt happen

Tacite•9/3/24, 11:09 AM

i will pip freeze to check if I'm exactly same as yours

Furkan Gözükara SECourses•9/3/24, 11:09 AM

i am also reinstalling

Tacite•9/3/24, 11:10 AM

ah yeah in your requirements.txt there's no numpy so it downloaded the 2.1.0 automatically

FFurkan Gözükara SECourses Click to see attachment

GomezBro•9/3/24, 11:11 AM

even FLUX with no Lora already does a good job imo

TTacite ah yeah in your requirements.txt there's no numpy so it downloaded the 2.1.0 aut...

Furkan Gözükara SECourses•9/3/24, 11:12 AM

i am testing rigfht now

GGomezBro even FLUX with no Lora already does a good job imo

Furkan Gözükara SECourses•9/3/24, 11:12 AM

yep

Furkan Gözükara SECourses•9/3/24, 11:12 AM

but this is for training your consistent style

Tacite•9/3/24, 11:12 AM

solved by doing pip install numpy==1.26.4 in the venv

Tacite•9/3/24, 11:12 AM

i have the .txt captions now

TTacite solved by doing pip install numpy==1.26.4 in the venv

Furkan Gözükara SECourses•9/3/24, 11:12 AM

i will change requirements :d

Furkan Gözükara SECourses•9/3/24, 11:12 AM

you found from pip freeze?_

Tacite•9/3/24, 11:13 AM

yes!

Furkan Gözükara SECourses•9/3/24, 11:13 AM

that is why i include

Furkan Gözükara SECourses•9/3/24, 11:13 AM

open source community doesnt do that which sucks so bad

Tacite•9/3/24, 11:13 AM

and beware, the web page still says V11

Furkan Gözükara SECourses•9/3/24, 11:13 AM

ye it is fine

FFurkan Gözükara SECourses i am also reinstalling

GomezBro•9/3/24, 11:13 AM

Please tag me when you release the 4 GPU video bro. Also, I am going to do 10,000 images with captions this time. How long will it take to train since you are familiar with the 4 A6000 GPU and iterations. I figure 10 EPOCH or less will do it. Saving every Epoch. This way I will know more or less how much it will cost me. Please do tell me the calculation based on the 10K images, thank you Doc. And have a GN its 4am here im dead.... haha

Furkan Gözükara SECourses•9/3/24, 11:13 AM

will update v13 now :d

GGomezBro Please tag me when you release the 4 GPU video bro. Also, I am going to do 10,0...

Furkan Gözükara SECourses•9/3/24, 11:13 AM

editing right now :d

Furkan Gözükara SECourses•9/3/24, 11:13 AM

Furkan Gözükara SECourses•9/3/24, 11:13 AM

will announce as @ everyone tagging

Tacite•9/3/24, 11:17 AM

Did you try the "FP16" option on your joycaptioner? Does it work? Is it better?

TTacite Did you try the "FP16" option on your joycaptioner? Does it work? Is it better?

Furkan Gözükara SECourses•9/3/24, 11:18 AM

i didnt try

Furkan Gözükara SECourses•9/3/24, 11:19 AM

or maybe tried dont remember :d

Tacite•9/3/24, 11:20 AM

ok will try

Tacite•9/3/24, 11:22 AM

ok, only the very last sentence was slightly changed, and it means exactly the same, so useless

Furkan Gözükara SECourses•9/3/24, 11:22 AM

fixed : https://www.patreon.com/posts/110613301

Patreon

JoyCaption : Amazing Image Captioner - Batch Processing Included - ...

Get more from SECourses: Tutorials, Guides, Resources, Training, FLUX, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözü on Patreon

TTacite ok, only the very last sentence was slightly changed, and it means exactly the s...

Furkan Gözükara SECourses•9/3/24, 11:22 AM

probably

Furkan Gözükara SECourses•9/3/24, 11:50 AM

new update

Neo•9/3/24, 12:08 PM

yeah that got me too, you are ontop of this stuff haha

Furkan Gözükara SECourses•9/3/24, 12:13 PM

testing 100 new prompts from gpt4

Process Process-2: Traceback (most recent call last): File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\feature_extraction_utils.py", line 183, in convert_to_tensors tensor = as_tensor(value) File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\feature_extraction_utils.py", line 142, in as_tensor return torch.tensor(value) RuntimeError: Could not infer dtype of numpy.float32

During handling of the above exception, another exception occurred: Traceback (most recent call last): File "C:\Program Files\Python310\lib\multiprocessing\process.py", line 314, in _bootstrap self.run() File "C:\Program Files\Python310\lib\multiprocessing\process.py", line 108, in run self._target(*self._args, **self._kwargs) File "E:\Joy_Caption_v12\app.py", line 335, in process_gpu_batch images = clip_processor(images=batch_images, return_tensors='pt', padding=True).pixel_values.to(device) File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\models\siglip\processing_siglip.py", line 113, in __call__ image_features = self.image_processor(images, return_tensors=return_tensors) File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\image_processing_utils.py", line 41, in __call__ return self.preprocess(images, **kwargs) File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\models\siglip\image_processing_siglip.py", line 259, in preprocess return BatchFeature(data=data, tensor_type=return_tensors) File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\feature_extraction_utils.py", line 79, in __init__ self.convert_to_tensors(tensor_type=tensor_type) File "E:\Joy_Caption_v12\venv\lib\site-packages\transformers\feature_extraction_utils.py", line 189, in convert_to_tensors raise ValueError( ValueError: Unable to create tensor, you should probably activate padding with 'padding=True' to have batched tensors with the same length.

@Dr. Furkan Gözükara morning, could you double check this, =10:38:16.887 [Info] Self-Start ComfyUI-

Similar Threads

@Dr. Furkan Gözükara morning, could you double check this, =10:38:16.887 [Info] Self-Start ComfyUI-