Jason Banner

MOEA/D-AWA needs build new B(i) after Add new subproblems

1

In MOEAD/D-AWA Paper Pseudocode **Algorithm 4 MOEA/D-AWA**, Line 4.4 says > for i 1, ... , N, find the T closest weights to Ai and build the new B (i)....

Thanks for this project. In the original paper, it was mentioned that \'scaling all training images to a resolution of 128\*128 pixels\'. But the current website can produce 256\*256 pictures....

I found that every time I estimate the label probability of the same image, the result is different. That is, for the same picture (for example, the picture you provided...

SOTA Model for Text Prompt Segmentation

7

I am looking for a state-of-the-art (SOTA) model for **text prompt** segmentation. Currently, I am aware of two choices: [Grounded-Segment-Anything](https://github.com/IDEA-Research/Grounded-Segment-Anything) and [SEEM](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once). However, both of these models fail to meet...

[Proposal] Allows custom seed for automatic reset in VectorEnv

1

### Proposal **Allows custom seed for automatic reset in VectorEnv.** (Suitable for gym version 0.26.1.) When we make vertorized env like, ``` envs = gym.vector.make("CartPole-v1", num_envs=3) ``` We know that...

Upload local files to multiple servers at once.

6

This is a similar request as #127, but I'm trying to make it as clear as possible. ```json { "name": "xxx", "protocol": "sftp", "port": 22, "username": "xxx", "remotePath": "xxx", "privateKeyPath":...

Grounding-DINO occupies the majority of Grounded-SAM's processing time.

3

Thank you for your excellent work on the Grounded-Segment-Anything project. I've noticed that developers have recently incorporated various advanced SAM models, such as Efficient-SAM and RepViT-SAM. However, it appears that...

I am looking for a state-of-the-art (SOTA) model for **text prompt** segmentation. Currently, I am aware of two choices: [Grounded-Segment-Anything](https://github.com/IDEA-Research/Grounded-Segment-Anything) and [SEEM](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once). However, both of these models fail to meet...

Key Differences Between Text-Prompt with Automatic Tracking and Invoking Grounded-SAM/Lang-SAM Per Frame

4

Thank you for the wonderful project. I observed that it features text-prompt and automatic Tracking Mode, allowing me to obtain the segment mask for each frame based on the pre-provided...

Script does not support ARM architecture servers

1

Hi, I encountered an issue when using the `lamp.sh` script to install the LAMP stack on an ARM architecture server (e.g., aarch64). The script does not account for ARM architecture,...