diff --git a/lite/docs/source_en/image_classification.md b/lite/docs/source_en/image_classification.md new file mode 100644 index 0000000000000000000000000000000000000000..017d659f0e6a0790c6738c0188a24b3ed2c0549b --- /dev/null +++ b/lite/docs/source_en/image_classification.md @@ -0,0 +1,33 @@ +# Image classification + + + +## Image classification introduction + +Image classification is to identity what an image represents, to predict the object list and the probabilites. For example，the classification results of the following figure after model prediction are shown in the following table： + +![image_classification](images/image_classification_result.png) + +| Category | probalilites | +| ---------- | ------------ | +| plant | 0.9359 | +| flower | 0.8641 | +| tree | 0.8584 | +| houseplant | 0.7867 | + +Using MindSpot Lite to realize image classification [example](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/lite/image_classification). + +## Image classification model list + +The following table shows the data of some image classification models using MindSpore Lite inference. + +> The performance of the table below is tested on the mate30. + +| model name | link | size | precision | CPU 4 thread delay | +|-----------------------|----------|----------|----------|-----------| +| MobileNetV2 | | | | | +| LeNet | | | | | +| AlexNet | | | | | +| GoogleNet | | | | | +| ResNext50 | | | | | + diff --git a/lite/docs/source_en/images/image_classification_result.png b/lite/docs/source_en/images/image_classification_result.png new file mode 100644 index 0000000000000000000000000000000000000000..a7cc49f582440e31b6b5b14dbba5131bfed2a4b4 Binary files /dev/null and b/lite/docs/source_en/images/image_classification_result.png differ diff --git a/lite/docs/source_en/images/object_detection.jpg b/lite/docs/source_en/images/object_detection.jpg new file mode 100644 index 0000000000000000000000000000000000000000..1f66390fafaa0a7636b0129135228ceb56cc9b49 Binary files /dev/null and b/lite/docs/source_en/images/object_detection.jpg differ diff --git a/lite/docs/source_en/object_detection.md b/lite/docs/source_en/object_detection.md new file mode 100644 index 0000000000000000000000000000000000000000..966245af08ed5c917fd04ad1cfbab25501962f8b --- /dev/null +++ b/lite/docs/source_en/object_detection.md @@ -0,0 +1,29 @@ +# Object detection + + + +## Object dectectin introduction + +Object detection can identify the object in the image and its position in the image. For the following figure, the output of the object detection model is shown in the following table. The rectangular box is used to identify the position of the object in the graph and the probability of the object category is marked. The four numbers in the coordinates are Xmin, Ymin, Xmax, Ymax; the probability represents the probility of the detected object. + +![object_detectiontion](images/object_detection.jpg) + +| 类别 | 概率 | 坐标 | +| ----- | ---- | ---------------- | +| mouse | 0.78 | [10, 25, 35, 43] | + +Using mindspot Lite to implement object detection [example](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/lite/object_detection). + +## Object detection model list + +The following table shows the data of some object detection models using MindSpore Lite inference。 + +> The performance of the table below is tested on the mate30. + +| model name | link | size | precision | CPU 4 thread delay | +|-----------------------|----------|----------|----------|-----------| +| SSD | | | | | +| Faster_RCNN | | | | | +| Yolov3_Darknet | | | | | +| Mask_RCNN | | | | | + diff --git a/lite/docs/source_zh_cn/image_classification.md b/lite/docs/source_zh_cn/image_classification.md new file mode 100644 index 0000000000000000000000000000000000000000..0d64c033bd5904b2281483bb7e0eb7debdfc9db8 --- /dev/null +++ b/lite/docs/source_zh_cn/image_classification.md @@ -0,0 +1,33 @@ +# 图像分类 + + + +## 图像分类介绍 + +图像分类模型可以预测图片中出现哪些物体，识别出图片中出现物体列表及其概率。 比如下图经过模型推理的分类结果为下表： + +![image_classification](images/image_classification_result.png) + +| 类别 | 概率 | +| ---------- | ------ | +| plant | 0.9359 | +| flower | 0.8641 | +| tree | 0.8584 | +| houseplant | 0.7867 | + +使用MindSpore Lite实现图像分类的[示例代码](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/lite/image_classification)。 + +## 图像分类模型列表 + +下表是使用MindSpore Lite推理的部分图像分类模型的数据。 + +> 下表的性能是在mate30手机上测试的 + +| 模型名称 | 模型链接 | 大小 | 精度 | CPU 4线程时延 | +|-----------------------|----------|----------|----------|-----------| +| MobileNetV2 | | | | | +| LeNet | | | | | +| AlexNet | | | | | +| GoogleNet | | | | | +| ResNext50 | | | | | + diff --git a/lite/docs/source_zh_cn/images/image_classification_result.png b/lite/docs/source_zh_cn/images/image_classification_result.png new file mode 100644 index 0000000000000000000000000000000000000000..a7cc49f582440e31b6b5b14dbba5131bfed2a4b4 Binary files /dev/null and b/lite/docs/source_zh_cn/images/image_classification_result.png differ diff --git a/lite/docs/source_zh_cn/images/object_detection.jpg b/lite/docs/source_zh_cn/images/object_detection.jpg new file mode 100644 index 0000000000000000000000000000000000000000..1f66390fafaa0a7636b0129135228ceb56cc9b49 Binary files /dev/null and b/lite/docs/source_zh_cn/images/object_detection.jpg differ diff --git a/lite/docs/source_zh_cn/object_detection.md b/lite/docs/source_zh_cn/object_detection.md new file mode 100644 index 0000000000000000000000000000000000000000..19c06ffbe16d7cc8f0a6ed2c29662be1f6143b52 --- /dev/null +++ b/lite/docs/source_zh_cn/object_detection.md @@ -0,0 +1,29 @@ +# 对象检测 + + + +## 对象检测介绍 + +对象检测可以识别出图片中的对象和该对象在图片中的位置。 如：对下图使用对象检测模型的输出如下表所示，使用矩形框识别图中对象的位置并且标注出对象类别的概率，其中坐标中的4个数字分别为Xmin, Ymin, Xmax, Ymax；概率表示反应被检测物理的可信程度。 + +![object_detectiontion](images/object_detection.jpg) + +| 类别 | 概率 | 坐标 | +| ----- | ---- | ---------------- | +| mouse | 0.78 | [10, 25, 35, 43] | + +使用MindSpore Lite实现对象检测的[示例代码](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/lite/object_detection)。 + +## 对象检测模型列表 + +下表是使用MindSpore Lite推理的部分对象检测模型的数据。 + +> 下表的性能是在mate30手机上测试的 + +| 模型名称 | 模型链接 | 大小 | 精度 | CPU 4线程时延 | +|-----------------------|----------|----------|----------|-----------| +| SSD | | | | | +| Faster_RCNN | | | | | +| YoloV3_Darknet53 | | | | | +| Mask_RCNN | | | | | +