English | 简体中文
Version: 1.0.0
Category: Object Detection
Algorithm: Swift-YOLO
Dataset: Digital Meter Electricity
Class: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, -
The model is a Swift-YOLO model trained on the Digital Meter Water dataset, which can detect the water meter number.
| Type | Batch | Shape | Remark | |
|---|---|---|---|---|
| Input | image | 1 | [192, 192, 3] | The input image should be resized to 192x192 pixels. |
| Output | bbox | 1 | [2268, 15] | The output is a 2268x15 tensor, where 2268 is the number of candidate boxes and 15 is [x, y, w, h, score, [class]] |
| Backend | Precision | mAP(%) | MACs(MB) | Params(M) | Peek RAM(MB) | Inference(ms) | Download | Author |
|---|---|---|---|---|---|---|---|---|
| PyTorch | FLOAT32 | 95.30 | 91.8 | 0.67 | - | - | Link | Seeed Studio |
| ONNX | FLOAT32 | 91.80 | - | 0.67 | 1.2 | - | Link | Seeed Studio |
| TFLite | FLOAT32 | 91.80 | 89.0 | - | 1.2 | - | Link | Seeed Studio |
| TFLite | INT8 | 88.30 | 89.0 | - | 0.35 | 691.0(1) | Link | Seeed Studio |
| TFLite(vela) | INT8 | 88.30 | 89.0 | - | 0.35 | 49(2) | Link | Seeed Studio |
Table Notes:
- Evaluation Parameters: Confidence Threshold: 0.001, IoU Threshold: 0.55, mAP Eval IoU: 0.50..
- Backend: The deep learning framework used to infer the model.
- Precision: The numerical precision used for training the model.
- Metrics: The metrics used to evaluate the model.
- Inference(ms): The inference time of the model in milliseconds.
- 1: xiao_esp32s3.
- 2: grove_vision_ai_we2.
- Link: The link to the model.
- Author: The author of the model.
MIT