SSD output structure

[0xSynapse]

Given an output shape of (1, 1, 100, 7), let's break down each dimension:
Batch Size (1):
In this context, the batch size is 1, indicating that the model is processing one input image at a time. This is common for inference on single images.
Number of Detections (1):
This represents the number of detected objects or bounding boxes. In your case, it seems to be set to 1. Each detection provides information about an object in the image.
Maximum Number of Detections (100):
This represents the maximum number of detections that the model can produce. Even if only a few objects are present in the image, the model might predict up to 100 bounding boxes.
Information for Each Detection (7):
For each detected object, there are 7 values representing different attributes:
Batch ID (0): The index of the batch to which the detection belongs. Since the batch size is 1, this is always 0.
Class ID (1): The index or label of the detected object's class. It indicates what type of object the model thinks it is.
Confidence Score (0.5, for example): The confidence or probability score associated with the detection. It indicates how certain the model is about the detected object being of a particular class.
Bounding Box Coordinates (left, top, right, bottom): The coordinates of the bounding box specifying the location of the detected object in the image. These values are often normalized (0 to 1) and need to be scaled according to the actual image dimensions.

-- is this structure correct?!