deeplearn-java

number	project	remark
1	action_rec_djl	MXNet image classification for human action recognition, DJL inference
2	anime_gan	Deploying face anime transformation using ONNXRuntime—AnimeGAN
3	bert_qa_djl	BERT reading comprehension (input paragraph and question, provide answer), DJL inference
4	big_gan_djl	BigGAN image generation, batch image generation by category, DJL inference
5	bise_net	Facial parsing using BiSeNet
6	chexnet	Wu Enda's team pneumonia detection model - CheXNet
7	chinese2english_translation_djl	Translation Chinese => English, Chinese segmentation, then translation, DJL inference
8	chinese_error_recovery_macbert4csc	Load MacBERT model for Chinese spelling correction
9	chinese_nlp_roberta	Chinese word completion prediction with RoBERTa
10	chinese_ocr_lite	The lightest Chinese OCR
11	chinese_segment_lightltp_1	Chinese segmentation with LightLTP, Chinese lexical analysis (segmentation, part-of-speech tagging)
12	chinese_segment_lightltp_2	Chinese segmentation with LightLTP, Chinese lexical analysis (segmentation, part-of-speech tagging => named entity recognition)
13	clip_image_text_compare_djl	CLIP model for image-text understanding (OpenAI), DJL deployment, compare text and images, calculate image-text relevance
14	crowd_density_dec_djl	Crowd density detection (PaddlePaddle-CrowdNet), people counting, crowd density map, DJL inference
15	dbnet_barcode_det	DBNet for barcode detection
16	deeplabv3_obj_segmentation_djl	DeepLabV3 instance segmentation, DJL inference
17	distilbert_sentiment_analysis	DistilBERT sentiment analysis (English text), DJL inference
18	e2_pose_detection	E2Pose human keypoint detection
19	e2_pose_detection_video	E2Pose human keypoint detection
20	english_segment_ner	English named entity recognition with HuggingFace-RoBERTa NER (NLP)
21	face_alignment_mesh_pose	Face detection + alignment (dense point 3D reconstruction, also known as mesh reconstruction)
22	face_det_retina_djl	RetinaFace model for face detection (5 key points), DJL inference
23	face_det_ultra_light_djl	Ultra-Light-Fast model for face detection (5 key points), DJL inference
24	face_feature_extraction_djl	Face feature extraction (512 dimensions), similarity comparison, DJL inference
25	face_land_mark	Face landmark detection, also known as face alignment
26	face_rec_det_insightface_pcn_1	Face detection (InsightFace) + age and gender detection + landmark recognition + feature extraction + face matching
27	face_rec_det_insightface_pcn_2	Face detection (PCN) + age and gender detection + landmark recognition + feature extraction + face matching
28	face_rec_det_insightface_pcn_3	Similarity evaluation face detection => landmark detection => face alignment => feature extraction => similarity calculation
29	face_rec_det_insightface_pcn_4	Face feature extraction => Elasticsearch face retrieval
30	face_rec_det_sface	Face detection and recognition, SFace face detection (Yunet) + face encoding (128 dimensions)
31	first_order_motion_model_jdl	Ant black and white effect, First Order Motion Model using JDL inference
32	french2english_translation_djl	Translation French => English, DJL inference
33	gfp_gan_v1	GFP-GAN V1 for face photo restoration, increases clarity
34	google_move_net_people_key_point	Google MoveNet human 17 key points detection
35	google_move_net_people_key_point_video	Google MoveNet human 17 key points detection
36	hand_3d_landmark	Hand keypoint detection 3D, the attention model needs to combine palm detection, so direct input of palm images is required for keypoint detection
37	hand_3d_landmark_camera	Hand keypoint detection 3D (camera detection)
38	hand_3d_landmark_video	Hand keypoint detection 3D (video detection)
39	hand_palm_detection	Palm detection, annotating the palm area + palm center point + two key points above and below the palm center
40	id_card_licence	Full card text recognition for ID cards
41	id_card_rec_det	Text recognition (high-precision text area detection + text recognition)
42	informative_drawings	Deploying Informative-Drawings to generate sketches using ONNXRuntime
43	mask_rcnn_resnet18_v1b_coco_seg_djl	Mask R-CNN instance segmentation, DJL inference
44	metaai_sam_test_djl	Meta AI SAM for segmentation of all objects, using DJL for inference
45	metaai_sam_test_onnx	Meta AI SAM, segmentation using matting points
46	mod_net	Real-time portrait segmentation model with background replacement
47	mod_net_video	Portrait segmentation + video background replacement
48	m_lsd_line_detect	M-LSD line detection
49	nanodet_plus_object_dec	NanoDet-Plus object detection
50	opencv_selective_search_demo	OpenCV implementation of the RCNN SelectiveSearch algorithm
51	p2p_net_people_count	P2PNet for crowd detection and counting
52	paddlepaddle_mattingv2	Baidu PaddleSeg's real-time portrait segmentation model PP-MattingV2
53	paddle_ocr_djl	Paddle OCR character recognition with DJL inference
54	picodet_object_dec	PicoDet object detection
55	pose_estimation2_djl	Human pose estimation (key points) with ResNet18/ResNet50 models, DJL inference
56	pose_estimation_djl	Human pose estimation (17 key points detection) with DJL inference
57	pp_animals_classification	Animal image classification with ResNet50/MobileNet_V2, DJL inference
58	pp_coco_object_detection_djl	COCO dataset PP open-source model for object detection, DJL inference
59	pp_deep_speech2text_long_djl	Deep Speech (Chinese and English) end-to-end speech recognition model, PP open-source model, DJL inference
60	pp_deep_speech2text_short_djl	Deep Speech (Chinese and English) end-to-end speech recognition model, PP open-source model, DJL inference
61	pp_dish_classification	Dish classification with ResNet50/MobileNet_V2, DJL inference
62	pp_human_seg	PP-HumanSeg portrait segmentation
63	pp_vehicle_detect_djl	Vehicle detection, PP open-source model, DJL inference
64	rapid_asr	Speech to text (speech recognition + punctuation insertion) with Wenet
65	rapid_ocr	Quick OCR - Text region detection + text orientation detection + text recognition
66	real_esrgan	Real-ESRGAN - Image super-resolution restoration
67	retinaface_arcface	Face detection (RetinaFace) + face recognition (ArcFace)
68	robust_video_matting	Video portrait segmentation
69	robust_video_matting_video	Video portrait segmentation
70	safety_helmet_detect_darknet53_djl	Safety helmet detection, Darknet53 model, DJL inference
71	safety_helmet_detect_mobilenet1_djl	Safety helmet detection, MobileNet1.0, DJL inference
72	safety_helmet_detect_mobilenet2_djl	Safety helmet detection, MobileNet0.25, DJL inference
73	stable_diffusion_djl_cpu	Stable Diffusion AI drawing, text-to-image, DJL inference
74	stable_diffusion_djl_gpu	Stable Diffusion AI drawing, text-to-image, DJL inference
75	stable_diffusion_img2img_djl_gpu	Stable Diffusion AI drawing, image-to-image, DJL inference
76	stable_diffusion_onnx	Stable Diffusion AI drawing, supports image-to-image and text-to-image
77	style_gan_cartoon	Using Style-GAN to convert facial portraits to cartoon style
78	style_transfer_djl	Animation style transfer, DJL deployment
79	super_resolution_djl	Super-resolution with ESRGAN-TF2 model, DJL inference
80	torcvision_keypointrcmm_resnet50_fpn_key_point	Keypoint algorithm under PyTorch
81	torcvision_maskrcnn_resnet50_fpn	Torchvision Mask R-CNN ResNet50 instance segmentation
82	tts_mary_us_english	Text to WAV American English female voice (hidden semi-Markov model - provided by Carnegie Mellon University)
83	u2_net	Using ONNX Runtime to deploy U-2-Net for generating facial sketches
84	ultra_fast_lane_detection_v2	Ultra-Fast Lane Detection v2 for lane line detection
85	wav2vec2_speech2text_englinsh_djl	Speech recognition (English) with Wav2Vec2, speech-to-text, DJL inference
86	whisper_speech2text_englinsh_djl	Whisper speech recognition (English), text conversion (an open-source speech recognition translation model released by OpenAI in September)
87	yoloe_pp_hrnet_human_pose_estimation	PP-YOLOE pedestrian detection + HRNet human skeleton keypoint detection, pose estimation
88	yolov3_darknet53_pedestrian_djl	YOLOv3 pedestrian detection, DJL inference
89	yolov3_face_key_point_106	YOLOv3 input 112*112 face images for 106 keypoint detection
90	yolov4_fire_smoke_detect_djl	YOLOv4 smoke and fire detection (Paddle model), DJL inference
91	yolov5_car_plate	License plate detection + license plate character/color recognition
92	yolov5_cpu_gpu_test	Comparison of inference speed using CPU and GPU for object detection
93	yolov5_deepsort	Object tracking with DeepSort + YOLOv5
94	yolov5_djl	YOLOv5 inference testing using DJL
95	yolov5_face_key_point_5	Face keypoint detection (5 points) using YOLOv5
96	yolov5_face_mask_dec_djl	YOLOv5 face mask detection, DJL inference with ONNX engine
97	yolov5_predict	Object detection
98	yolov5_predict_segment	Object detection + instance segmentation in video
99	yolov5_predict_video	Object detection + instance segmentation in video
100	yolov5_reflective_clothes_detect_djl	YOLOv5 reflective clothing + safety helmet detection, safety check, DJL inference
101	yolov5_rotate	YOLOv5 rotational object detection using ONNX Runtime
102	yolov5_safety_helmet_detect_djl	Safety helmet detection, YOLOv5 (S/M/L) model, DJL inference
103	yolov7_face_key_point_5	YOLOv7 face + keypoint detection using ONNX Runtime
104	yolov7_head_detection	YOLOv7 head detection (head density detection)
105	yolovp2_detection_drive_area_line_384_640	YOLOPV2 object detection + drivable area segmentation + lane line segmentation
106	yolovp2_detection_drive_area_line_736_1280	YOLOPV2 object detection + drivable area segmentation + lane line segmentation
107	yolovp2_detection_drive_area_line_video_384_640	YOLOPV2 object detection + drivable area segmentation + lane line segmentation
108	yolovp2_detection_drive_area_line_video_384_640_write	YOLOPV2 object detection + drivable area segmentation + lane line segmentation, then generate a new video
109	yolovp2_detection_drive_area_line_video_736_1280	YOLOPV2 object detection + drivable area segmentation + lane line segmentation