Zephyr69

Would this be able to detect true "unseen unknowns"?

2

I've seen many open-set object detection projects that can detect "seen unknowns" (classes that are already present, although unlabeled, in the training pipeline). But I'm looking to detect "unseen unknowns"...

The GAN_feat_loss seems to be calculating MAE between feature maps produced by the discriminator when it is doing forward pass using real and fake images. How does this help with...

System: Ubuntu22.04lts Task: Starting to train a yolov5 model with deep_utils being one of the imported modules (that doesn't do anything during training). Symptom: When trying to import deep_utils, an...

Would there be a dataloader to read handmade img+.txt dataset rather than sql?

What is "PresetAreaHead" for in the model configs?

It works very well for outer cylinder surfaces, but not for inner ones. What needs to be done to make it work on inner surfaces?

Inference Parallelism Issue

1

I'm serving a qwen1.5AWQ model using AutoAWQCausalLM.from_quantized(). The performance is great when there is one client. However, when more than one clients are querying, their generated streams seem to be...

选定工具后无法进行流式输出

6

**问题描述 / Problem Description** 选定工具后无法进行流式输出 **复现问题的步骤 / Steps to Reproduce** 1、启用agent 2、选择一种或多种工具 3、输入prompt并提交 **预期的结果 / Expected Result** 模型输出应以流式输出的形式更新在chatbox中 **实际结果 / Actual Result** 模型输出全部完成后才一次全部更新在chatbox中 **环境信息 / Environment Information** - Langchain-Chatchat 版本...