deepseek-ai/Janus

Fork 0

mirror of https://github.com/deepseek-ai/Janus.git synced 2026-11-05 00:57:18 +00:00

[GH-ISSUE #54] 怎么进行多图联合推理 #44

New issue

Open

opened 2026-10-26 21:10:41 +00:00 by bsakaguchi · 3 comments

bsakaguchi commented

2026-10-26 21:10:41 +00:00

Owner

Originally created by @LiLiLiam on GitHub (Jan 28, 2025).
Original GitHub issue: https://github.com/deepseek-ai/Janus/issues/54

我需要在一个question中对多张图进行联合推理，以下是我的部分代码：
content_images = []
for idx in range(len(image_files)):
# content.append({"type": "image", "image": image_files[idx]})
content_images.append("data:image,{}".format(image_to_base64(image_files[idx], max_size=1024)))

conversation = [
    {
        "role": "<|User|>",
        "content": f"<image_placeholder>\n{query}",
        "images": content_images,
    },
    {"role": "<|Assistant|>", "content": ""},
]

目前会提示问题：
RuntimeError: The expanded size of the tensor (1) must match the existing size (2) at non-singleton dimension 0. Target sizes: [1, 3, 384, 384]. Tensor sizes: [2, 3, 384, 384]
要如何改进我的代码，使其可以实现多图联合推理

Originally created by @LiLiLiam on GitHub (Jan 28, 2025). Original GitHub issue: https://github.com/deepseek-ai/Janus/issues/54 我需要在一个question中对多张图进行联合推理，以下是我的部分代码： content_images = [] for idx in range(len(image_files)): # content.append({"type": "image", "image": image_files[idx]}) content_images.append("data:image,{}".format(image_to_base64(image_files[idx], max_size=1024))) conversation = [ { "role": "<|User|>", "content": f"<image_placeholder>\n{query}", "images": content_images, }, {"role": "<|Assistant|>", "content": ""}, ] 目前会提示问题： RuntimeError: The expanded size of the tensor (1) must match the existing size (2) at non-singleton dimension 0. Target sizes: [1, 3, 384, 384]. Tensor sizes: [2, 3, 384, 384] 要如何改进我的代码，使其可以实现多图联合推理

bsakaguchi commented

2026-10-26 21:10:42 +00:00

Author

Owner

@liziming5353 commented on GitHub (Jan 28, 2025):

同问，请问您解决了吗

@liziming5353 commented on GitHub (Jan 28, 2025): 同问，请问您解决了吗

bsakaguchi commented

2026-10-26 21:10:43 +00:00

Author

Owner

@xwgnick commented on GitHub (Feb 6, 2025):

解决了，记得用多个"<image_placeholder>, 有几张图就用几个，like：
conversation = [ { "role": "<|User|>", "content": f"<image_placeholder>\n<image_placeholder>\n{question}", "images": ["./test_images/test_1.jpg", "./test_images/test_2.jpg"], }, {"role": "<|Assistant|>", "content": ""}, ]

@xwgnick commented on GitHub (Feb 6, 2025): 解决了，记得用多个"<image_placeholder>, 有几张图就用几个，like： `conversation = [ { "role": "<|User|>", "content": f"<image_placeholder>\n<image_placeholder>\n{question}", "images": ["./test_images/test_1.jpg", "./test_images/test_2.jpg"], }, {"role": "<|Assistant|>", "content": ""}, ]`

bsakaguchi commented

2026-10-26 21:10:43 +00:00

Author

Owner

@wuming027 commented on GitHub (Feb 12, 2025):

遍历选定的图像文件并加载图像

image_paths = [os.path.join(data_folder, filename) for filename in selected_images]
# print(f"Processing image: {image_paths}")

# 构建提示内容
conversation = [
    {
        "role": "<|User|>",
        "content": f"<image_placeholder>\n{question}",
        "images": image_paths,
    },
    {"role": "<|Assistant|>", "content": ""},

我这样的话会报错，请问应该如何解决

@wuming027 commented on GitHub (Feb 12, 2025): # 遍历选定的图像文件并加载图像 image_paths = [os.path.join(data_folder, filename) for filename in selected_images] # print(f"Processing image: {image_paths}") # 构建提示内容 conversation = [ { "role": "<|User|>", "content": f"<image_placeholder>\n{question}", "images": image_paths, }, {"role": "<|Assistant|>", "content": ""}, 我这样的话会报错，请问应该如何解决

No labels

pull-request

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

deepseek-ai/Janus#44

No description provided.

Rows
Columns