Hello everyone,
I am currently working on something that involves tracking objects in a video footage using the Gemini 2.5 Flash model. I initially tried using the pre-trained model, but it didn’t worked out of the for my specific task. As a result, I am now looking to fine-tune the model to better suit my needs.
Given the nature of this task, the frames per second (FPS) capability of the model during the fine-tuning process is crucial for me.
However, I have been unable to find any documentation or resources that detail its processing capabilities, particularly in terms of frames per second (FPS) during video processing.
Could anyone provide insights or share their experiences regarding the FPS that Gemini 2.5 Flash can handle while fine-tuning for video tasks? I would greatly appreciate any help.
Thank you in advance!