Detection output
#2
by nguyenpbui - opened
Dear authors,
Congrats on the great work!
I am trying the detection ability of your method with the given instructions (8B-Next model). However, it cannot detect anything in either fundus or chest xray. It seems like the output from my side is different from yours. What do you think?
Best regards.
Hey!
Thanks a lot for your interest.
You can use this:
messages = [
{
"role": "user",
"content": [
{"type": "image", "image": image_path},
{
"type": "text",
"text": (
"localize any visible diseases or abnormalities in this X-ray image. "
"For each detected finding, provide the bounding box "
"as [[x_min, y_min, x_max, y_max]]."
),
},
],
}
]
Because sometimes it detects the finding but only outputs the disease name. Please include localization as well for chest X-Ray dataset.
ankanmbz changed discussion status to closed