Skip to main content
Stack Overflow
  1. About
  2. For Teams
Filter by
Sorted by
Tagged with
0 votes
0 answers
21 views

How can I run the inference on the HunyuanImage-3.0 model?

I follow the instructions on https://github.com/Tencent-Hunyuan/HunyuanImage-3.0: conda create -y -n hunyuan312 python=3.12 conda activate hunyuan312 # 1. First install PyTorch (CUDA 12.8 Version) ...
-7 votes
0 answers
34 views

Looking for assistance in promotion and development [closed]

I have been developing a Social Network platform https://misocial.net based off Symfony framework and I am looking to integrate AI for handling marking content as NSFW automatically. The network is a ...
-4 votes
0 answers
32 views

AI agent adk for google [closed]

How can I solve this I try to get a nice output Chat ai google agent I need an interactive Chat but not what I get so any help for next it will be nice to move on i did run adk web but the results it’...
-2 votes
0 answers
70 views

How to get the location of tables in PDFs? [closed]

I am developing an automated pipeline to extract tables from pdfs. The tables are often complex matrices with nonstandardized formats. As an example, the tables often times will be vertical on the ...
2 votes
1 answer
34 views

Matching PyTorch and ONNX outputs layer-wise for debugging inference drift

I want to debug layer-by-layer to see where the ONNX model starts deviating from the PyTorch model outputs. I can extract intermediate outputs in PyTorch using forward hooks, like: def get_activation(...
0 votes
0 answers
22 views

Transformer model outputs degrade after ONNX export — what could be causing this?

I’ve exported a fine-tuned BERT-based QA model to ONNX for faster inference, but I’m noticing that the predictions from the ONNX model are consistently less accurate than those from the original ...
-2 votes
0 answers
53 views

why i can't connect github in gemini? [closed]

I'm trying to connect my GitHub account to Gemini (Google's AI assistant) so I can use my repositories inside a chat. When I click the "Connect" button, it opens a small window for authorization. ...
-2 votes
0 answers
45 views

ESPCN model shows negative PSNR/SSIM improvement over bicubic interpolation [closed]

I'm working on an embedded video super-resolution project using a pre-trained ESPCN model to restore detail on low-bitrate video streams. Here is the GitHub link for the pre-trained model I used:ESPCN-...
0 votes
4 answers
3k views

Google Generative AI: 404 "models/gemini-1.5-flash is not found" error when calling generateContent

I have a Flask application that integrates with Google Generative AI (Gemini) and Google Calendar. It used to work fine, but recently I started running into two issues: Model not found (404) error ...
0 votes
1 answer
91 views

Getting "Sizes of tensors must match" error when using ComfyUI WanVideoWrapper (wan2.2) to generate video

I am trying to generate a video using Wan 2.2. My goal is to take a motion sequence from an input video and a single reference image, and then generate a new video where the character in the reference ...
1 vote
1 answer
140 views

How can I remove "Generate Commit Message" and other AI features in 1.102.0 and onward?

VS Code added a button to AI-generate commit messages. I don't want nor need this feature. Is there any way to remove the button from the UI entirely? I have already chosen "Hide Copilot" in ...
2 votes
1 answer
84 views

Langchain-based model memory

I am referring to the official documentation of langchain to learn how to build a simple agent. But the model don't have memory even though I have used MemeorySaver the link of official document is ...
1 vote
1 answer
47 views

How to vectorize PDF content for semantic search?

I am exploring the use of Weaviate for building a RAG model where I want to create vector database which can store content from a PDF file. It's a one or two page PDF, having sections like: Policy ...
0 votes
2 answers
102 views

LangGraph agent, built using create_react_agent, ignores the outputs from callable tools

Here is an example from the LangGraph offical tutorial def add(a: float, b: float): """Add two numbers.""" return a + b def multiply(a: float, b: float): &...
0 votes
0 answers
39 views

Flet python dialog close and Save is not working

im using flet to make a UI for an API app and i get a gray box when i try to click a button to open a pop up but when i close or save the pop up it dose not close but add a new pop up that can not go ...

15 30 50 per page
1
2 3 4 5
...
585

AltStyle によって変換されたページ (->オリジナル) /