智慧教室基于深度学习实现课堂专注度分析及考试作弊检测系统java源码(附有模型和项目使用说明).zip

import ai.djl.Device; import ai.djl.inference.Predictor; import ai.djl.modality.cv.Image; import ai.djl.modality.cv.output.DetectedObjects; import ai.djl.modality.cv.output.Joints; import ai.djl.modality.cv.output.Rectangle; import ai.djl.modality.cv.transform.Normalize; import ai.djl.modality.cv.transform.ToTensor; import ai.djl.modality.cv.translator.YoloV5Translator; import ai.djl.ndarray.NDArray; import ai.djl.ndarray.NDList; import ai.djl.ndarray.NDManager; import ai.djl.ndarray.types.DataType; import ai.djl.ndarray.types.Shape; import ai.djl.repository.zoo.Criteria; import ai.djl.repository.zoo.ModelZoo; import ai.djl.repository.zoo.ZooModel; import ai.djl.translate.Pipeline; import ai.djl.translate.Translator; import ai.djl.util.Pair; import org.junit.Test; import org.opencv.core.CvType; import org.opencv.core.Mat; import org.opencv.core.Scalar; import org.opencv.highgui.HighGui; import xyz.hyhy.scai.AlphaPose; import xyz.hyhy.scai.MainClass; import xyz.hyhy.scai.translator.PureImageTranslator; import xyz.hyhy.scai.translator.PureTranslator; import xyz.hyhy.scai.translator.SPPETranslator; import xyz.hyhy.scai.translator.SimpSPPETranslator; import xyz.hyhy.scai.utils.CVUtils; import xyz.hyhy.scai.utils.ImageUtils; import java.awt.image.BufferedImage; import java.nio.ByteBuffer; import java.util.ArrayList; import java.util.List; import java.util.Objects; public class TestClass extends MainClass { public <IN, OUT> void test(ZooModel<IN, OUT> model, IN inp, int inpNum, int warmupNum) throws Exception { try (Predictor<IN, OUT> predictor = model.newPredictor()) { if (warmupNum > 0) { System.out.printf("预热中(%d次)\n", warmupNum); for (int i = 0; i < warmupNum; i++) { predictor.predict(inp); } } System.out.printf("开始测试(%d次)\n", inpNum); long startTime = System.currentTimeMillis(); for (int i = 0; i < inpNum; i++) { predictor.predict(inp); } long endTime = System.currentTimeMillis(); System.out.printf("处理速度: %f s/img%n\n", (endTime - startTime) / 1000.0 / inpNum); } } public <IN, OUT> void testBatch(ZooModel<IN, OUT> model, IN inp, int inpNum, int warmupNum, int batchSize) throws Exception { List<IN> inputs = new ArrayList<>(batchSize); for (int i = 0; i < batchSize; i++) { inputs.add(inp); } try (Predictor<IN, OUT> predictor = model.newPredictor()) { if (warmupNum > 0) { System.out.printf("预热中(%d次)\n", warmupNum); for (int i = 0; i < warmupNum; i++) { predictor.batchPredict(inputs); } } System.out.printf("开始测试(%d次)\n", inpNum); long startTime = System.currentTimeMillis(); for (int i = 0; i < inpNum; i++) { predictor.batchPredict(inputs); } long endTime = System.currentTimeMillis(); System.out.printf("处理速度: %f s/img%n\n", (endTime - startTime) / 1000.0 / inpNum); } } @Test public void yolov5Test() throws Exception { int imgsNum = 1000; int warmupNum = 50; Scalar white = new Scalar(0, 0, 0); int height = 640, width = 640; Image img = ImageUtils.mat2Image(new Mat(height, width, CvType.CV_8UC3, white)); Translator<Image, DetectedObjects> translator = YoloV5Translator.builder().optSynsetArtifactName("coco.names").build(); Criteria<Image, DetectedObjects> criteria = Criteria.builder() .setTypes(Image.class, DetectedObjects.class) .optDevice(Device.gpu()) .optModelUrls(AlphaPose.class.getResource("/yolov5").getPath()) .optModelName("yolov5s.torchscript.pt") .optTranslator(translator) .optEngine("PyTorch") .build(); test(ModelZoo.loadModel(criteria), img, imgsNum, warmupNum); } @Test public void resnet101Test() throws Exception { int imgsNum = 1000; int warmupNum = 50; Scalar white = new Scalar(0, 0, 0); int height = 640, width = 640; Image img = ImageUtils.mat2Image(new Mat(height, width, CvType.CV_8UC3, white)); Translator<Image, Void> translator = new PureImageTranslator.Builder().build(true); Criteria<Image, Void> criteria = Criteria.builder() .setTypes(Image.class, Void.class) .optDevice(Device.gpu()) .optModelUrls(Objects.requireNonNull(AlphaPose.class.getResource("/others")).getPath()) .optModelName("resnet101.torchscript.pth") .optTranslator(translator) .optEngine("PyTorch") .build(); test(ModelZoo.loadModel(criteria), img, imgsNum, warmupNum); } @Test public void resnet101WithPreprocessTest() throws Exception { int imgsNum = 1000; int warmupNum = 50; Scalar white = new Scalar(0, 0, 0); int height = 640, width = 640; Image img = ImageUtils.mat2Image(new Mat(height, width, CvType.CV_8UC3, white)); Translator<Image, Void> translator = new PureImageTranslator.Builder().build(height, width); Criteria<Image, Void> criteria = Criteria.builder() .setTypes(Image.class, Void.class) .optDevice(Device.gpu()) .optModelUrls(Objects.requireNonNull(AlphaPose.class.getResource("/others")).getPath()) .optModelName("resnet101.torchscript.pth") .optTranslator(translator) .optEngine("PyTorch") .build(); test(ModelZoo.loadModel(criteria), img, imgsNum, warmupNum); } @Test public void resnet18Test() throws Exception { int imgsNum = 1000; int warmupNum = 50; Scalar white = new Scalar(0, 0, 0); int height = 640, width = 640; Image img = ImageUtils.mat2Image(new Mat(height, width, CvType.CV_8UC3, white)); Translator<Image, Void> translator = new PureImageTranslator.Builder().build(height, width); Criteria<Image, Void> criteria = Criteria.builder() .setTypes(Image.class, Void.class) .optDevice(Device.gpu()) .optModelUrls(Objects.requireNonNull(AlphaPose.class.getResource("/others")).getPath()) .optModelName("resnet18.torchscript.pth") .optTranslator(translator) .optEngine("PyTorch") .build(); test(ModelZoo.loadModel(criteria), img, imgsNum, warmupNum); } @Test public void yoloV5WithToTensorTest() throws Exception { int imgsNum = 1000; int warmupNum = 50; Scalar white = new Scalar(0, 0, 0); int height = 640, width = 640; Image img = ImageUtils.mat2Image(new Mat(height, width, CvType.CV_8UC3, white)); Translator<Image, Void> translator = new PureImageTranslator.Builder().build(true); Criteria<Image, Void> criteria = Criteria.builder() .setTypes(Image.class, Void.class) .optDevice(Device.gpu()) .optModelUrls(Objects.requireNonNull(AlphaPose.class.getResource("/yolov5")).getPath()) .optModelName("yolov5s.torchscript.pt") .optTranslator(translator) .optEngine("PyTorch") .build(); test(ModelZoo.loadModel(criteria), img, imgsNum, warmupNum); } @Test public void pureYoloV5Test() throws Exception { int imgsNum = 1000;