ML Model Respository from Pinto0309

ML Model Repository from Pinto0309

Introduction

Using AI we can solve many kinds of tasks for this input can be text, structured data, image, video, audio, time-series, etc. To solve these problems we need to training model. These models may be computer vision, NLP, or traditional machine learning kind. There are hundreds of architectures and algorithms to solve business problems and create models. There a hundreds of different datasets that can be along with a particular architecture or algorithm to solve the problem. If you have any of these tasks then you can explore using these pre-trained models to solve your problem. There is a GitHub user “Katsuya Hyodo” with GitHub account “PINTO0309”. He has trained hundreds of models and created these pre-trained models for the community. You can scan and explore them from there. From there you can download the pre-trained models.

Supported Formats

• WQ = Weight Quantization
• OV = OpenVINO IR
• CM = CoreML
• DQ = Dynamic Range Quantization
• FP32 = Floating Point 32
• FP16 = Floating Point 16
• INT8 = Integer
• TPU = Tensor Processing Unit
• TFJS = Tensorlfow javascript
• TF-TRT = ensorFlow-Tensor Run Time
• ONNX = Open Neural Network Exchange

1. Image Classification

Number in the tables below is from the main repository

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
4	Efficientnet	✔️	✔️
10	Mobilenetv3	✔️	✔️
11	Mobilenetv2	✔️	✔️	✔️
16	Efficientnet-lite	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
70	age-gender-recognition	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
83	Person_Reidentification	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
87	DeepSort	✔️	✔️	✔️	✔️	✔️	✔️	✔️
124	person-attributes-recognition-crossroad-0230	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
125	person-attributes-recognition-crossroad-0234	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
126	person-attributes-recognition-crossroad-0238	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
175	face-recognition-resnet100-arcface-onnx	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
187	vehicle-attributes-recognition-barrier-0039	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
188	vehicle-attributes-recognition-barrier-0042	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
191	anti-spoof-mn3	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
192	open-closed-eye-0001	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
194	face_recognizer_fast	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
195	person_reid_youtu	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
199	NSFW	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
244	FINNger	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
256	SFace	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
257	PiCANet	✔️
259	Emotion_FERPlus	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
290	AdaFace	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
317	MobileOne
346	facial_expression_recognition_mobilefacenet	✔️	✔️	✔️	✔️	✔️
379	PP-LCNetV2	✔️	✔️

2. 2D Object Detection

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
2	Mobilenetv3-SSD	✔️	✔️	✔️
6	Mobilenetv2-SSDlite	✔️	✔️	✔️
8	Mask_RCNN_Inceptionv2	✔️	✔️
18	EfficientDet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
23	Yolov3-nano	✔️	✔️	✔️
24	Yolov3-lite	✔️	✔️	✔️	✔️	✔️
31	Yolov4	✔️	✔️	✔️	✔️	✔️
34	SSD_Mobilenetv2_mnasfpn	✔️	✔️	✔️	✔️	✔️
38	SSDlite_MobileDet_edgetpu	✔️	✔️	✔️	✔️	✔️	✔️	✔️
39	SSDlite_MobileDet_cpu	✔️	✔️	✔️
42	Centernet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
45	SSD_Mobilenetv2_oid_v4	✔️	✔️	✔️	✔️	✔️
46	Yolov4-tiny	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
47	SpineNetMB_49	✔️	✔️	✔️	✔️
51	East_Text_Detection	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
54	KNIFT	✔️	✔️	✔️	✔️	✔️
56	TextBoxes++ with dense blocks, separable convolution and Focal Loss	✔️	✔️	✔️	✔️	✔️	✔️	✔️
58	keras-retinanet	✔️	✔️	✔️	✔️	✔️	✔️
59	Yolov5	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
72	NanoDet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
73	RetinaNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
74	Yolact	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
85	Yolact_Edge	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
89	DETR	✔️	✔️	✔️	✔️
103	EfficientDet_lite	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
116	DroNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
123	YOLOR	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
132	YOLOX	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
143	RAPiD	✔️	✔️	✔️	✔️	✔️
145	text_detection_db	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
151	object_detection_mobile_object_localizer	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
169	spaghettinet_edgetpu	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
174	PP-PicoDet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
178	vehicle-detection-0200	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
1	person-detection-0202	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
180	YOLOv5-Lite	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
183	pedestrian-detection-adas-0002	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
184	pedestrian-and-vehicle-detector-adas-0001	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
185	person-vehicle-bike-detection-crossroad-0078	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
186	person-vehicle-bike-detection-crossroad-1016	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
189	vehicle-license-plate-detection-barrier-0106	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
190	person-detection-asl-0001	✔️	✔️	✔️	✔️	✔️	✔️
197	yolact-resnet50-fpn	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
198	YOLOF	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
221	YOLACT-PyTorch	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
226	CascadeTableNet	✔️	✔️	✔️	✔️	✔️
262	ByteTrack
264	object_localization_network
307	YOLOv7	✔️	✔️	✔️	✔️	✔️	✔️	✔️
308	FastestDet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
329	YOLOX-PAI
331	YOLOv5L6_Ball
332	CrowdDet
334	DAMO-YOLO
336	PP-YOLOE-Plus
337	FreeYOLO
341	YOLOv6	✔️	✔️	✔️	✔️	✔️
356	EdgeYOLO
376	RT-DETR
386	naruto_handsign_detection	✔️	✔️	✔️	✔️

3. 3D Object Detection

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
36	Objectron	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
63	3D BoundingBox estimation for autonomous driving	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
107	SFA3D	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
263	EgoNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
321	DID-M3D
363	YOLO-6D-Pose	✔️	✔️

4. 2D/3D Face Detection

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
25	Head_Pose_Estimation	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
30	BlazeFace	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
32	FaceMesh	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
40	DSFD_vgg	✔️	✔️
41	DBFace	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
43	Face_Landmark	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
49	Iris_Landmark	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
95	CenterFace	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
96	RetinaFace	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
106	WHENet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
129	SCRFD	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
130	YOLOv5_Face	✔️	✔️	✔️	✔️	✔️	✔️
134	head-pose-estimation-adas-0001	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
144	YuNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
227	face-detection-adas-0001	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
250	Face-Mask-Detection	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
282	face_landmark_with_attention	✔️	✔️	✔️	✔️	✔️	✔️	✔️
289	face-detection-0100	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
293	Lightweight-Head-Pose-Estimation	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
300	6DRepNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️
301	YOLOv4_Face
302	SLPT
303	FAN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
304	SynergyNet
305	DMHead
311	HHP-Net	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
319	ACR-Loss	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
322	YOLOv7_Head
345	YOLOv8
383	DirectMHP	✔️	✔️
387	YuNetV2	✔️	✔️	✔️	✔️
390	BlendshapeV2	✔️	✔️
399	RetinaFace_MobileNetv2
410	FaceMeshV2	✔️	✔️	✔️	✔️	✔️

5. 2D/3D Hand Detection

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
27	Minimal-Hand	✔️	✔️	✔️	✔️	✔️	✔️	✔️
33	Hand_Detection_and_Tracking	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
94	hand_recrop	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
403	trt_pose_hand

6. 2D/3D Human/Animal Pose Estimation

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
3	Posenet	✔️	✔️	✔️	✔️	✔️
7	Mobilenetv2_Pose_Estimation	✔️	✔️	✔️	✔️	✔️	✔️	✔️
29	Human_Pose_Estimation_3D	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
53	BlazePose	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
65	ThreeDPoseUnityBarracuda	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
80	tf_pose_estimation	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
84	EfficientPose	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
88	Mobilenetv3_Pose_Estimation	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
115	MoveNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
137	MoveNet_MultiPose	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
156	MobileHumanPose	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
157	3DMPPE_POSENET	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
265	PoseAug	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
268	Lite-HRNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
269	Higher-HRNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
271	HRNet
333	E2Pose	✔️	✔️	✔️	✔️
350	P-STMO
355	MHFormer	✔️	✔️
365	HTNet	✔️	✔️
392	STCFormer	✔️	✔️
393	RTMPose_WholeBody	✔️	✔️	✔️	✔️
394	RTMPose_Animal	✔️	✔️	✔️	✔️
402	trt_pose
412	pytorch_cpn	✔️	✔️

7. Depth Estimation from Monocular/Stereo Images

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
9	Multi-Scale Local Planar Guidance for Monocular Depth Estimation
14	tf-monodepth2	✔️	✔️	✔️	✔️	✔️	✔️	✔️
28	struct2depth	✔️	✔️	✔️
64	Dense Depth	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
66	Footprints	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
67	MiDaS	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
81	MiDaS v2	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
135	CoEx	✔️
142	HITNET	✔️	✔️	✔️
146	FastDepth	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
147	PackNet-SfM	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
148	LapDepth	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
149	depth_estimation	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
150	MobileStereoNet
153	MegaDepth	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
158	HR-Depth	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
159	EPCDepth	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
160	msg_chn_wacv20	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
162	PyDNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
164	MADNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️
165	RealtimeStereo	✔️	✔️	✔️	✔️	✔️	✔️	✔️
166	Insta-DM	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
167	DPT	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
173	MVDepthNet	✔️
202	stereoDNN	✔️	✔️	✔️	✔️	✔️	✔️	✔️
203	SRHNet
210	SC_Depth_pl	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
211	Lac-GwcNet
219	StereoNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️
235	W-Stereo-Disp
236	A-TVSNet	✔️	✔️	✔️	✔️
239	CasStereoNet
245	GLPDepth	✔️
258	TinyHITNet	✔️
266	ACVNet	✔️
280	GASDA
284	CREStereo
292	Graft-PSMNet
294	FSRE-Depth	✔️
296	MGNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️
312	NeWCRFs
313	PyDNet2	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
327	EMDC
338	Fast-ACVNet
358	CGI-Stereo	✔️	✔️
362	ZoeDepth
364	IGEV
371	Lite-Mono
384	TCMonoDepth
397	MiDaSv3.1

8. Semantic Segmentation

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
1	deeplabv3	✔️
15	Faster-Grad-CAM	✔️	✔️
20	EdgeTPU-Deeplab	✔️	✔️	✔️
21	EdgeTPU-Deeplab-slim	✔️	✔️	✔️
26	Mobile-Deeplabv3-plus	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
35	BodyPix	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
57	BiSeNetV2	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
60	Hair Segmentation	✔️	✔️	✔️	✔️
61	U^2-Net	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
69	ENet	✔️	✔️	✔️	✔️	✔️
75	ERFNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
78	MODNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
82	MediaPipe_Meet_Segmentation	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
104	DeeplabV3-plus	✔️	✔️	✔️	✔️	✔️	✔️	✔️
109	Selfie_Segmentation	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
136	road-segmentation-adas-0001	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
138	BackgroundMattingV2	✔️	✔️	✔️	✔️
181	models_edgetpu_checkpoint_and_tflite_vision_segmentation-edgetpu_tflite_default_argmax	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
182	models_edgetpu_checkpoint_and_tflite_vision_segmentation-edgetpu_tflite_fused_argmax	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
196	human_segmentation_pphumanseg	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
201	CityscapesSOTA	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
206	Matting	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
228	Fast-SCNN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
238	SUIM-Net	✔️	✔️	✔️	✔️	✔️	✔️	✔️
242	RobustVideoMatting	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
246	SqueezeSegV3	✔️	✔️	✔️	✔️	✔️	✔️	✔️
267	LIOT	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
287	Topformer	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
295	SparseInst	✔️
299	DGNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
313	IS-Net
335	PIDNet
343	PP-MattingV2	✔️	✔️
347	RGBX_Semantic_Segmentation
369	Segment_Anything
380	Skin-Clothes-Hair-Segmentation-using-SMP	✔️	✔️
391	MagicTouch	✔️	✔️	✔️
405	Ear_Segmentation

9. Anomaly Detection

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
5	One_Class_Anomaly_Detection	✔️	✔️	✔️
99	Efficientnet_Anomaly_Detection_Segmentation	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️

10. Artistic

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
17	Artistic-Style-Transfer	✔️	✔️	✔️	✔️	✔️	✔️	✔️
19	White-box-Cartoonization	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
37	First_Neural_Style_Transfer	✔️	✔️
44	Selfie2Anime	✔️	✔️	✔️	✔️	✔️	✔️
50	AnimeGANv2	✔️	✔️	✔️	✔️	✔️	✔️	✔️
62	Facial Cartoonization	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
68	Colorful_Image_Colorization	✔️	✔️	✔️	✔️	✔️	✔️
101	arbitrary_image_stylization	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
113	Anime2Sketch	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
161	EigenGAN-Tensorflow	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
193	CoCosNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️

11. Super Resolution

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
12	Fast_Accurate_and_Lightweight_Super-Resolution	✔️	✔️
22	Learning_to_See_Moving_Objects_in_the_Dark	✔️	✔️	✔️
71	Noise2Noise	✔️	✔️	✔️	✔️	✔️
76	Deep_White_Balance	✔️	✔️	✔️	✔️	✔️	✔️	✔️
77	ESRGAN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
79	MIRNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
86	Defocus Deblurring Using Dual-Pixel	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
90	Ghost-free_Shadow_Removal	✔️	✔️	✔️	✔️	✔️	✔️
111	SRN-Deblur	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
112	DeblurGANv2	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
114	Two-branch-dehazing	✔️	✔️	✔️	✔️	✔️	✔️	✔️
133	Real-ESRGAN	✔️	✔️	✔️	✔️	✔️	✔️	✔️
152	DeepLPF	✔️	✔️	✔️	✔️
170	Learning-to-See-in-the-Dark	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
171	Fast-SRGAN	✔️	✔️	✔️	✔️	✔️	✔️	✔️
172	Real-Time-Super-Resolution	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
176	StableLLVE	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
200	AGLLNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️
204	HINet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
205	MBLLEN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
207	GLADNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
208	SAPNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
209	MSBDN-DFF	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
212	GFN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
213	TBEFN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
214	EnlightenGAN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
215	AOD-Net	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
216	Zero-DCE-TF	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
217	RUAS	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
218	DSLR	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
220	HEP	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
222	LFT
223	DA_dahazing	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
224	Y-net	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
225	DRBL	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
230	Single-Image-Desnowing-HDCWNet	✔️	✔️	✔️	✔️	✔️
231	DRBL	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
232	MIMO-UNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
234	FBCNN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
240	BSRGAN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
241	SCL-LLE	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
243	Zero-DCE-improved	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
249	Real-CUGAN	✔️
251	AU-GAN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
253	TransWeather	✔️
261	EfficientDerain
270	HWMNet
275	FD-GAN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
277	EDN-GTM	✔️	✔️	✔️	✔️	✔️	✔️	✔️
281	IMDN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
283	UIE-WD
285	Decoupled-Low-light-Image-Enhancement
286	SCI	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
315	Illumination-Adaptive-Transformer
316	night_enhancement
320	Dehamer
323	Stripformer
325	DehazeFormer
344	XYDeblur
348	Bread
348	PMN
351	RFDN
352	MAXIM	✔️	✔️
353	ShadowFormer
354	DEA-Net	✔️	✔️
359	MSPFN	✔️	✔️
361	KBNet
367	FLW-Net
368	C2PNet
370	Semantic-Guided-Low-Light-Image-Enhancement
372	URetinex-Net
375	SCANet
377	DRSformer
385	PairLIE
389	WGWS-Net
396	MixDehazeNet
400	CSRNet
404	HDR-Transformer
409	nighttime_dehaze
411	UDR-S2Former_deraining

12. Sound Classifier

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
13	ml-sound-classifier	✔️	✔️	✔️	✔️	✔️	✔️
97	YAMNet	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
98	SPICE	✔️	✔️	✔️	✔️	✔️
118	Speech-enhancement	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
120	FRILL	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
177	BirdNET-Lite	✔️	✔️	✔️	✔️	✔️
381	Whisper
382	Light-SERNet	✔️	✔️

13. Natural Language Processing

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
48	Mobile_BERT	✔️	✔️	✔️	✔️	✔️	✔️
121	GPT2/DistillGPT2	✔️	✔️	✔️	✔️	✔️	✔️	✔️
122	DistillBert	✔️	✔️	✔️	✔️	✔️	✔️	✔️

14. Text Recognition

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
52	Handwritten_Text_Recognition	✔️	✔️
55	Handwritten_Japanese_Recognition	✔️	✔️	✔️	✔️	✔️	✔️	✔️
93	ocr_japanese	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️

15. Action Recognition

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
92	weld-porosity-detection-0001	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
247	PoseC3D
248	MS-G3D

16. Inpainting

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
100	HiFill	✔️	✔️	✔️	✔️
163	MST_inpainting	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
273	OPN(Onion-Peel Networks)
274	DeepFillv2	✔️	✔️	✔️	✔️	✔️

17. GAN

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
105	MobileStyleGAN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
310	attentive-gan-derainnet	✔️	✔️	✔️	✔️	✔️	✔️	✔️

18. Transformer

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
127	dino	✔️	✔️	✔️	✔️	✔️	✔️

19. Others

No.	Model Name	FP32	FP16	INT8	TPU	DQ	WQ	OV	CM	TFJS	TF-TRT	ONNX
91	gaze-estimation-adas-0002	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
102	Coconet	✔️	✔️	✔️
108	HAWP
110	L-CNN
117	DTLN	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
119	M-LSD	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
131	CFNet
139	PSD-Principled-Synthetic-to-Real-Dehazing-Guided-by-Physical-Priors	✔️	✔️	✔️	✔️	✔️	✔️	✔️
140	Ultra-Fast-Lane-Detection	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
141	lanenet-lane-detection	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
154	driver-action-recognition-adas-0002-encoder	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
155	driver-action-recognition-adas-0002-decoder	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
167	LSTR	✔️	✔️	✔️	✔️	✔️	✔️
229	DexiNed	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
233	HRNet-for-Fashion-Landmark-Estimation	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
237	piano_transcription	✔️				✔️
254	FullSubNet-plus				✔️	✔️	✔️	✔️	✔️	✔️	✔️
260	KP2D	✔️	✔️	✔️	✔️	✔️
272	CSFlow
276	HybridNets	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
278	DWARF	✔️	✔️	✔️	✔️	✔️	✔️	✔️	✔️
279	F-Clip	✔️	✔️	✔️	✔️	✔️	✔️	✔️
288	perceptual-reflection-removal	✔️	✔️	✔️	✔️	✔️	✔️	✔️
291	SeAFusion	✔️	✔️	✔️	✔️	✔️	✔️
297	GazeNet
298	DEQ-Flow
306	GMFlowNet
309	ImageForensicsOSN	✔️	✔️	✔️	✔️	✔️	✔️	✔️
318	pips
324	Ultra-Fast-Lane-Detection-v2
326	YOLOPv2	✔️	✔️	✔️	✔️	✔️
328	Stable_Diffusion
339	DeepLSD
342	ALIKE	✔️	✔️	✔️	✔️	✔️
357	Unimatch	✔️	✔️
360	PARSeq	✔️	✔️
366	text_recognition_CRNN	✔️	✔️
373	LiteTrack	✔️	✔️
374	LaneSOD
378	P2PNet_tfkeras	✔️	✔️
388	LightGlue
398	L2CS-Net	✔️	✔️	✔️	✔️
401	CLRerNet
406	DeDoDe	✔️	✔️
407	Generalizing_Gaze_Estimation	✔️	✔️
408	UAED
413	DocShadow	✔️

4. Reference articles

1. Pinto Model Zoo
2. [deeplab] what’s the parameters of the mobilenetv3 pretrained model?
3. When you want to fine-tune DeepLab on other datasets, there are a few cases
4. [deeplab] Training deeplab model with ADE20K dataset
5. Running DeepLab on PASCAL VOC 2012 Semantic Segmentation Dataset
6. Quantize DeepLab model for faster on-device inference
7. https://github.com/tensorflow/models/blob/main/research/deeplab/g3doc/model_zoo.md
8. https://github.com/tensorflow/models/blob/main/research/deeplab/g3doc/quantize.md
9. the quantized form of Shape operation is not yet implemented
10. Post-training quantization
11. Converter command line reference
12. Quantization-aware training
13. Converting a .pb file to .meta in TF 1.3
14. Minimal code to load a trained TensorFlow model from a checkpoint and export it with SavedModelBuilder
15. How to restore Tensorflow model from .pb file in python?
16. Error with tag-sets when serving model using tensorflow_model_server tool
17. ValueError: No ‘serving_default’ in the SavedModel’s SignatureDefs. Possible values are ‘name_of_my_model’
18. Configure input_map when importing a tensorflow model from metagraph file
19. TFLite Model Benchmark Tool
20. How to install Ubuntu 19.10 aarch64 (64bit) on RaspberryPi4
21. https://github.com/rwightman/posenet-python.git
22. https://github.com/sayakpaul/Adventures-in-TensorFlow-Lite.git