mirror of
https://github.com/deepseek-ai/Janus.git
synced 2026-11-05 00:57:18 +00:00
[GH-ISSUE #215] 如何做批量多模态理解 (how to do batch inference on mutli-modality understanding task) #175
Labels
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/Janus#175
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @rampage-bruce on GitHub (Apr 18, 2025).
Original GitHub issue: https://github.com/deepseek-ai/Janus/issues/215
你好,我想用Janus做批量多模态理解,但不清楚批量conversation 的格式应该是怎么样的,通过在conversation 增加 dic 会导致有些问题可以回答但有些问题回答是空。
@rampage-bruce commented on GitHub (Apr 18, 2025):
Hello, I want to use Janus for batch multimodal understanding, but I don't know what the format of the batch conversation should be. By adding dic to the conversation, some questions can be answered, but some questions have empty answers.
@krennic999 commented on GitHub (Apr 23, 2025):
I also wonder if there is batched-inference code for text-based image synthesis