English | 简体中文
Image (212) | Text (130) | Audio (15) | Video (8) | Industrial Application (1) |
---|---|---|---|---|
Image Classification (108) | Text Generation (17) | Voice Cloning (2) | Video Classification (5) | Meter Detection (1) |
Image Generation (26) | Word Embedding (62) | Text to Speech (5) | Video Editing (1) | - |
Keypoint Detection (5) | Machine Translation (2) | Automatic Speech Recognition (5) | Multiple Object tracking (2) | - |
Semantic Segmentation (25) | Language Model (30) | Audio Classification (3) | - | - |
Face Detection (7) | Sentiment Analysis (7) | - | - | - |
Text Recognition (17) | Syntactic Analysis (1) | - | - | - |
Image Editing (8) | Simultaneous Translation (5) | - | - | - |
Instance Segmentation (1) | Lexical Analysis (2) | - | - | - |
Object Detection (13) | Punctuation Restoration (1) | - | - | - |
Depth Estimation (2) | Text Review (3) | - | - | - |
expand
module | Network | Dataset | Introduction |
---|---|---|---|
DriverStatusRecognition | MobileNetV3_small_ssld | Drivers | |
mobilenet_v2_animals | MobileNet_v2 | Animals | |
repvgg_a1_imagenet | RepVGG | ImageNet-2012 | |
repvgg_a0_imagenet | RepVGG | ImageNet-2012 | |
resnext152_32x4d_imagenet | ResNeXt | ImageNet-2012 | |
resnet_v2_152_imagenet | ResNet V2 | ImageNet-2012 | |
resnet50_vd_animals | ResNet50_vd | Animals | |
food_classification | ResNet50_vd_ssld | dishes | |
mobilenet_v3_large_imagenet_ssld | Mobilenet_v3_large | ImageNet-2012 | |
resnext152_vd_32x4d_imagenet | |||
ghostnet_x1_3_imagenet_ssld | GhostNet | ImageNet-2012 | |
rexnet_1_5_imagenet | ReXNet | ImageNet-2012 | |
resnext50_64x4d_imagenet | ResNeXt | ImageNet-2012 | |
resnext101_64x4d_imagenet | ResNeXt | ImageNet-2012 | |
efficientnetb0_imagenet | EfficientNet | ImageNet-2012 | |
efficientnetb1_imagenet | EfficientNet | ImageNet-2012 | |
mobilenet_v2_imagenet_ssld | Mobilenet_v2 | ImageNet-2012 | |
resnet50_vd_dishes | ResNet50_vd | dishes | |
pnasnet_imagenet | PNASNet | ImageNet-2012 | |
rexnet_2_0_imagenet | ReXNet | ImageNet-2012 | |
SnakeIdentification | ResNet50_vd_ssld | snakes | |
hrnet40_imagenet | HRNet | ImageNet-2012 | |
resnet_v2_34_imagenet | ResNet V2 | ImageNet-2012 | |
mobilenet_v2_dishes | MobileNet_v2 | dishes | |
resnext101_vd_32x4d_imagenet | ResNeXt | ImageNet-2012 | |
repvgg_b2g4_imagenet | RepVGG | ImageNet-2012 | |
fix_resnext101_32x48d_wsl_imagenet | ResNeXt | ImageNet-2012 | |
vgg13_imagenet | VGG | ImageNet-2012 | |
se_resnext101_32x4d_imagenet | SE_ResNeXt | ImageNet-2012 | |
hrnet30_imagenet | HRNet | ImageNet-2012 | |
ghostnet_x1_3_imagenet | GhostNet | ImageNet-2012 | |
dpn107_imagenet | DPN | ImageNet-2012 | |
densenet161_imagenet | DenseNet | ImageNet-2012 | |
vgg19_imagenet | vgg19_imagenet | ImageNet-2012 | |
mobilenet_v2_imagenet | Mobilenet_v2 | ImageNet-2012 | |
resnet50_vd_10w | ResNet_vd | private | |
resnet_v2_101_imagenet | ResNet V2 101 | ImageNet-2012 | |
darknet53_imagenet | DarkNet | ImageNet-2012 | |
se_resnext50_32x4d_imagenet | SE_ResNeXt | ImageNet-2012 | |
se_hrnet64_imagenet_ssld | HRNet | ImageNet-2012 | |
resnext101_32x16d_wsl | ResNeXt_wsl | ImageNet-2012 | |
hrnet18_imagenet | HRNet | ImageNet-2012 | |
spinalnet_res101_gemstone | resnet101 | gemstone | |
densenet264_imagenet | DenseNet | ImageNet-2012 | |
resnext50_vd_32x4d_imagenet | ResNeXt_vd | ImageNet-2012 | |
SpinalNet_Gemstones | |||
spinalnet_vgg16_gemstone | vgg16 | gemstone | |
xception71_imagenet | Xception | ImageNet-2012 | |
repvgg_b2_imagenet | RepVGG | ImageNet-2012 | |
dpn68_imagenet | DPN | ImageNet-2012 | |
alexnet_imagenet | AlexNet | ImageNet-2012 | |
rexnet_1_3_imagenet | ReXNet | ImageNet-2012 | |
hrnet64_imagenet | HRNet | ImageNet-2012 | |
efficientnetb7_imagenet | EfficientNet | ImageNet-2012 | |
efficientnetb0_small_imagenet | EfficientNet | ImageNet-2012 | |
efficientnetb6_imagenet | EfficientNet | ImageNet-2012 | |
hrnet48_imagenet | HRNet | ImageNet-2012 | |
rexnet_3_0_imagenet | ReXNet | ImageNet-2012 | |
shufflenet_v2_imagenet | ShuffleNet V2 | ImageNet-2012 | |
ghostnet_x0_5_imagenet | GhostNet | ImageNet-2012 | |
inception_v4_imagenet | Inception_V4 | ImageNet-2012 | |
resnext101_vd_64x4d_imagenet | ResNeXt_vd | ImageNet-2012 | |
densenet201_imagenet | DenseNet | ImageNet-2012 | |
vgg16_imagenet | VGG | ImageNet-2012 | |
mobilenet_v3_small_imagenet_ssld | Mobilenet_v3_Small | ImageNet-2012 | |
hrnet18_imagenet_ssld | HRNet | ImageNet-2012 | |
resnext152_64x4d_imagenet | ResNeXt | ImageNet-2012 | |
efficientnetb3_imagenet | EfficientNet | ImageNet-2012 | |
efficientnetb2_imagenet | EfficientNet | ImageNet-2012 | |
repvgg_b1g4_imagenet | RepVGG | ImageNet-2012 | |
resnext101_32x4d_imagenet | ResNeXt | ImageNet-2012 | |
resnext50_32x4d_imagenet | ResNeXt | ImageNet-2012 | |
repvgg_a2_imagenet | RepVGG | ImageNet-2012 | |
resnext152_vd_64x4d_imagenet | ResNeXt_vd | ImageNet-2012 | |
xception41_imagenet | Xception | ImageNet-2012 | |
googlenet_imagenet | GoogleNet | ImageNet-2012 | |
resnet50_vd_imagenet_ssld | ResNet_vd | ImageNet-2012 | |
repvgg_b1_imagenet | RepVGG | ImageNet-2012 | |
repvgg_b0_imagenet | RepVGG | ImageNet-2012 | |
resnet_v2_50_imagenet | ResNet V2 | ImageNet-2012 | |
rexnet_1_0_imagenet | ReXNet | ImageNet-2012 | |
resnet_v2_18_imagenet | ResNet V2 | ImageNet-2012 | |
resnext101_32x8d_wsl | ResNeXt_wsl | ImageNet-2012 | |
efficientnetb4_imagenet | EfficientNet | ImageNet-2012 | |
efficientnetb5_imagenet | EfficientNet | ImageNet-2012 | |
repvgg_b1g2_imagenet | RepVGG | ImageNet-2012 | |
resnext101_32x48d_wsl | ResNeXt_wsl | ImageNet-2012 | |
resnet50_vd_wildanimals | ResNet_vd | IFAW wild animals | |
nasnet_imagenet | NASNet | ImageNet-2012 | |
se_resnet18_vd_imagenet | |||
spinalnet_res50_gemstone | resnet50 | gemstone | |
resnext50_vd_64x4d_imagenet | ResNeXt_vd | ImageNet-2012 | |
resnext101_32x32d_wsl | ResNeXt_wsl | ImageNet-2012 | |
dpn131_imagenet | DPN | ImageNet-2012 | |
xception65_imagenet | Xception | ImageNet-2012 | |
repvgg_b3g4_imagenet | RepVGG | ImageNet-2012 | |
marine_biometrics | ResNet50_vd_ssld | Fish4Knowledge | |
res2net101_vd_26w_4s_imagenet | Res2Net | ImageNet-2012 | |
dpn98_imagenet | DPN | ImageNet-2012 | |
resnet18_vd_imagenet | ResNet_vd | ImageNet-2012 | |
densenet121_imagenet | DenseNet | ImageNet-2012 | |
vgg11_imagenet | VGG | ImageNet-2012 | |
hrnet44_imagenet | HRNet | ImageNet-2012 | |
densenet169_imagenet | DenseNet | ImageNet-2012 | |
hrnet32_imagenet | HRNet | ImageNet-2012 | |
dpn92_imagenet | DPN | ImageNet-2012 | |
ghostnet_x1_0_imagenet | GhostNet | ImageNet-2012 | |
hrnet48_imagenet_ssld | HRNet | ImageNet-2012 |
module | Network | Dataset | Introduction | Huggingface Spaces Demo |
---|---|---|---|---|
pixel2style2pixel | Pixel2Style2Pixel | - | human face | |
stgan_bald | STGAN | CelebA | stgan_bald | |
styleganv2_editing | StyleGAN V2 | - | human face editing | |
wav2lip | wav2lip | LRS2 | wav2lip | |
attgan_celeba | AttGAN | Celeba | human face editing | |
cyclegan_cityscapes | CycleGAN | Cityscapes | cyclegan_cityscapes | |
stargan_celeba | StarGAN | Celeba | human face editing | |
stgan_celeba | STGAN | Celeba | human face editing | |
ID_Photo_GEN | HRNet_W18 | - | ID_Photo_GEN | |
Photo2Cartoon | U-GAT-IT | cartoon_data | cartoon | |
U2Net_Portrait | U^2Net | - | Portrait | |
UGATIT_100w | U-GAT-IT | selfie2anime | selfie2anime | |
UGATIT_83w | U-GAT-IT | selfie2anime | selfie2anime | |
UGATIT_92w | U-GAT-IT | selfie2anime | selfie2anime | |
animegan_v1_hayao_60 | AnimeGAN | The Wind Rises | animegan_v1_hayao | |
animegan_v2_hayao_64 | AnimeGAN | The Wind Rises | animegan_v1_hayao | |
animegan_v2_hayao_99 | AnimeGAN | The Wind Rises | animegan_v1_hayao | |
animegan_v2_paprika_54 | AnimeGAN | Paprika | animegan_v2_paprika | |
animegan_v2_paprika_74 | AnimeGAN | Paprika | animegan_v2_paprika | |
animegan_v2_paprika_97 | AnimeGAN | Paprika | animegan_v2_paprika | |
animegan_v2_paprika_98 | AnimeGAN | Paprika | animegan_v2_paprika | |
animegan_v2_shinkai_33 | AnimeGAN | Your Name, Weathering with you | animegan_v2_shinkai | |
animegan_v2_shinkai_53 | AnimeGAN | Your Name, Weathering with you | animegan_v2_shinkai | |
msgnet | msgnet | COCO2014 | ||
stylepro_artistic | StyleProNet | MS-COCO + WikiArt | stylepro_artistic | |
stylegan_ffhq | StyleGAN | FFHQ | stylepro_artistic |
module | Network | Dataset | Introduction |
---|---|---|---|
face_landmark_localization | Face_Landmark | AFW/AFLW | Face_Landmark |
hand_pose_localization | - | MPII, NZSL | hand_pose_localization |
openpose_body_estimation | two-branch multi-stage CNN | MPII, COCO 2016 | openpose_body_estimation |
human_pose_estimation_resnet50_mpii | Pose_Resnet50 | MPII | human_pose_estimation |
openpose_hands_estimation | - | MPII, NZSL | openpose_hands_estimation |
module | Network | Dataset | Introduction |
---|---|---|---|
deeplabv3p_xception65_humanseg | deeplabv3p | - | humanseg |
humanseg_server | deeplabv3p | - | humanseg |
humanseg_mobile | hrnet | - | humanseg |
humanseg_lite | shufflenet | - | humanseg |
ExtremeC3_Portrait_Segmentation | ExtremeC3 | EG1800, Baidu fashion dataset | humanseg |
SINet_Portrait_Segmentation | SINet | EG1800, Baidu fashion dataset | humanseg |
FCN_HRNet_W18_Face_Seg | FCN_HRNet_W18 | - | humanseg |
ace2p | ACE2P | LIP | ACE2P |
Pneumonia_CT_LKM_PP | U-NET+ | - | Pneumonia_CT |
Pneumonia_CT_LKM_PP_lung | U-NET+ | - | Pneumonia_CT |
ocrnet_hrnetw18_voc | ocrnet, hrnet | PascalVoc2012 | |
U2Net | U^2Net | - | U2Net |
U2Netp | U^2Net | - | U2Net |
Extract_Line_Draft | UNet | Pixiv | Extract_Line_Draft |
unet_cityscapes | UNet | cityscapes | |
ocrnet_hrnetw18_cityscapes | ocrnet_hrnetw18 | cityscapes | |
hardnet_cityscapes | hardnet | cityscapes | |
fcn_hrnetw48_voc | fcn_hrnetw48 | PascalVoc2012 | |
fcn_hrnetw48_cityscapes | fcn_hrnetw48 | cityscapes | |
fcn_hrnetw18_voc | fcn_hrnetw18 | PascalVoc2012 | |
fcn_hrnetw18_cityscapes | fcn_hrnetw18 | cityscapes | |
fastscnn_cityscapes | fastscnn | cityscapes | |
deeplabv3p_resnet50_voc | deeplabv3p, resnet50 | PascalVoc2012 | |
deeplabv3p_resnet50_cityscapes | deeplabv3p, resnet50 | cityscapes | |
bisenetv2_cityscapes | bisenetv2 | cityscapes |
module | Network | Dataset | Introduction |
---|---|---|---|
pyramidbox_lite_mobile | PyramidBox | WIDER FACE | face_detection |
pyramidbox_lite_mobile_mask | PyramidBox | WIDER FACE | face_detection |
pyramidbox_lite_server_mask | PyramidBox | WIDER FACE | face_detection |
ultra_light_fast_generic_face_detector_1mb_640 | Ultra-Light-Fast-Generic-Face-Detector-1MB | WIDER FACE | face_detection |
ultra_light_fast_generic_face_detector_1mb_320 | Ultra-Light-Fast-Generic-Face-Detector-1MB | WIDER FACE | face_detection |
pyramidbox_lite_server | PyramidBox | WIDER FACE | face_detection |
pyramidbox_face_detection | PyramidBox | WIDER FACE | face_detection |
module | Network | Dataset | Introduction | Huggingface Spaces Demo |
---|---|---|---|---|
chinese_ocr_db_crnn_mobile | Differentiable Binarization+RCNN | icdar2015 | Chinese text recognition | |
chinese_text_detection_db_mobile | Differentiable Binarization | icdar2015 | Chinese text Detection | |
chinese_text_detection_db_server | Differentiable Binarization | icdar2015 | Chinese text Detection | |
chinese_ocr_db_crnn_server | Differentiable Binarization+RCNN | icdar2015 | Chinese text recognition | |
Vehicle_License_Plate_Recognition | - | CCPD | Vehicle license plate recognition | |
chinese_cht_ocr_db_crnn_mobile | Differentiable Binarization+CRNN | icdar2015 | Traditional Chinese text Detection | |
japan_ocr_db_crnn_mobile | Differentiable Binarization+CRNN | icdar2015 | Japanese text recognition | |
korean_ocr_db_crnn_mobile | Differentiable Binarization+CRNN | icdar2015 | Korean text recognition | |
german_ocr_db_crnn_mobile | Differentiable Binarization+CRNN | icdar2015 | German text recognition | |
french_ocr_db_crnn_mobile | Differentiable Binarization+CRNN | icdar2015 | French text recognition | |
latin_ocr_db_crnn_mobile | Differentiable Binarization+CRNN | icdar2015 | Latin text recognition | |
cyrillic_ocr_db_crnn_mobile | Differentiable Binarization+CRNN | icdar2015 | Cyrillic text recognition | |
multi_languages_ocr_db_crnn | Differentiable Binarization+RCNN | icdar2015 | Multi languages text recognition | |
kannada_ocr_db_crnn_mobile | Differentiable Binarization+CRNN | icdar2015 | Kannada text recognition | |
arabic_ocr_db_crnn_mobile | Differentiable Binarization+CRNN | icdar2015 | Arabic text recognition | |
telugu_ocr_db_crnn_mobile | Differentiable Binarization+CRNN | icdar2015 | Telugu text recognition | |
devanagari_ocr_db_crnn_mobile | Differentiable Binarization+CRNN | icdar2015 | Devanagari text recognition | |
tamil_ocr_db_crnn_mobile | Differentiable Binarization+CRNN | icdar2015 | Tamil text recognition |
module | Network | Dataset | Introduction | Huggingface Spaces Demo |
---|---|---|---|---|
realsr | LP-KPN | RealSR dataset | Image / Video super-resolution | |
deoldify | GAN | ILSVRC 2012 | Black-and-white image / video colorization | |
photo_restoration | deoldify + realsr | - | Old photo restoration | |
user_guided_colorization | siggraph | ILSVRC 2012 | User guided colorization | |
falsr_c | falsr_c | DIV2k | Lightweight super resolution - 2x | |
dcscn | dcscn | DIV2k | Lightweight super resolution - 2x | |
falsr_a | falsr_a | DIV2k | Lightweight super resolution - 2x | |
falsr_b | falsr_b | DIV2k | Lightweight super resolution - 2x |
module | Network | Dataset | Introduction |
---|---|---|---|
solov2 | - | COCO2014 | Instance segmentation |
module | Network | Dataset | Introduction |
---|---|---|---|
faster_rcnn_resnet50_coco2017 | faster_rcnn | COCO2017 | |
ssd_vgg16_512_coco2017 | SSD | COCO2017 | |
faster_rcnn_resnet50_fpn_venus | faster_rcnn | Baidu self built dataset | Large-scale general detection |
ssd_vgg16_300_coco2017 | |||
yolov3_resnet34_coco2017 | YOLOv3 | COCO2017 | |
yolov3_darknet53_pedestrian | YOLOv3 | Baidu Self built large-scale pedestrian dataset | Pedestrian Detection |
yolov3_mobilenet_v1_coco2017 | YOLOv3 | COCO2017 | |
ssd_mobilenet_v1_pascal | SSD | PASCAL VOC | |
faster_rcnn_resnet50_fpn_coco2017 | faster_rcnn | COCO2017 | |
yolov3_darknet53_coco2017 | YOLOv3 | COCO2017 | |
yolov3_darknet53_vehicles | YOLOv3 | Baidu Self built large-scale vehicles dataset | vehicles Detection |
yolov3_darknet53_venus | YOLOv3 | Baidu self built datasetset | Large-scale general detection |
yolov3_resnet50_vd_coco2017 | YOLOv3 | COCO2017 |
module | Network | Dataset | Introduction | Huggingface Spaces Demo |
---|---|---|---|---|
MiDaS_Large | - | 3D Movies, WSVD, ReDWeb, MegaDepth | ||
MiDaS_Small | - | 3D Movies, WSVD, ReDWeb, MegaDepth, etc. |
module | Network | Dataset | Introduction | Huggingface Spaces Demo |
---|---|---|---|---|
disco_diffusion_clip_rn101 | - | Open domain multi round dataset | text_to_image | |
ernie_vilg | - | Open domain multi round dataset | text_to_image | |
stable_diffusion_img2img | - | Open domain multi round dataset | img2img |
module | Network | Dataset | Introduction |
---|---|---|---|
ernie_gen | ERNIE-GEN | - | Pre-training finetuning framework for generating tasks |
ernie_gen_poetry | ERNIE-GEN | Open source poetry dataset | Poetry generation |
ernie_gen_couplet | ERNIE-GEN | Open source couplet dataset | Couplet generation |
ernie_gen_lover_words | ERNIE-GEN | Online love poems and love talk data | Love word generation |
ernie_tiny_couplet | Eernie_tiny | Open source couplet dataset | Couplet generation |
ernie_gen_acrostic_poetry | ERNIE-GEN | Open source poetry dataset | Acrostic poetry Generation |
Rumor_prediction | - | Sina Weibo Chinese rumor data | Rumor prediction |
plato-mini | Unified Transformer | Billion level Chinese conversation data | Chinese dialogue |
plato2_en_large | plato2 | Open domain multi round dataset | Super large scale generative dialogue |
plato2_en_base | plato2 | Open domain multi round dataset | Super large scale generative dialogue |
CPM_LM | GPT-2 | Self built dataset | Chinese text generation |
unified_transformer-12L-cn | Unified Transformer | Ten million level Chinese conversation data | Man machine multi round dialogue |
unified_transformer-12L-cn-luge | Unified Transformer | dialogue dataset | Man machine multi round dialogue |
reading_pictures_writing_poems | Multi network cascade | - | Look at pictures and write poems |
GPT2_CPM_LM | Q&A text generation | ||
GPT2_Base_CN | Q&A text generation |
expand
module | Network | Dataset | Introduction |
---|---|---|---|
transformer_zh-en | Transformer | CWMT2021 | 中文译英文 |
transformer_en-de | Transformer | WMT14 EN-DE | 英文译德文 |
expand
module | Network | Dataset | Introduction |
---|---|---|---|
chinese_electra_small | |||
chinese_electra_base | |||
roberta-wwm-ext-large | roberta-wwm-ext-large | Baidu self built dataset | |
chinese-bert-wwm-ext | chinese-bert-wwm-ext | Baidu self built dataset | |
lda_webpage | LDA | Baidu Self built Web Page Domain Dataset | |
lda_novel | |||
bert-base-multilingual-uncased | |||
rbt3 | |||
ernie_v2_eng_base | ernie_v2_eng_base | Baidu self built dataset | |
bert-base-multilingual-cased | |||
rbtl3 | |||
chinese-bert-wwm | chinese-bert-wwm | Baidu self built dataset | |
bert-large-uncased | |||
slda_novel | |||
slda_news | |||
electra_small | |||
slda_webpage | |||
bert-base-cased | |||
slda_weibo | |||
roberta-wwm-ext | roberta-wwm-ext | Baidu self built dataset | |
bert-base-uncased | |||
electra_large | |||
ernie | ernie-1.0 | Baidu self built dataset | |
simnet_bow | BOW | Baidu self built dataset | |
ernie_tiny | ernie_tiny | Baidu self built dataset | |
bert-base-chinese | bert-base-chinese | Baidu self built dataset | |
lda_news | LDA | Baidu Self built News Field Dataset | |
electra_base | |||
ernie_v2_eng_large | ernie_v2_eng_large | Baidu self built dataset | |
bert-large-cased |
module | Network | Dataset | Introduction | Huggingface Spaces Demo |
---|---|---|---|---|
ernie_skep_sentiment_analysis | SKEP | Baidu self built dataset | Sentence level sentiment analysis | |
emotion_detection_textcnn | TextCNN | Baidu self built dataset | Dialogue emotion detection | |
senta_bilstm | BiLSTM | Baidu self built dataset | Chinesesentiment analysis | |
senta_bow | BOW | Baidu self built dataset | Chinese sentiment analysis | |
senta_gru | GRU | Baidu self built dataset | Chinese sentiment analysis | |
senta_lstm | LSTM | Baidu self built dataset | Chinese sentiment analysis | |
senta_cnn | CNN | Baidu self built dataset | Chinese sentiment analysis |
module | Network | Dataset | Introduction |
---|---|---|---|
DDParser | Deep Biaffine Attention | Search query, web text, voice input and other data | Syntactic analysis |
module | Network | Dataset | Introduction |
---|---|---|---|
transformer_nist_wait_1 | transformer | NIST 2008 | Chinese to English - wait-1 |
transformer_nist_wait_3 | transformer | NIST 2008 | Chinese to English - wait-3 |
transformer_nist_wait_5 | transformer | NIST 2008 | Chinese to English - wait-5 |
transformer_nist_wait_7 | transformer | NIST 2008 | Chinese to English - wait-7 |
transformer_nist_wait_all | transformer | NIST 2008 | Chinese to English - waitk=-1 |
module | Network | Dataset | Introduction | Huggingface Spaces Demo |
---|---|---|---|---|
jieba_paddle | BiGRU+CRF | Baidu self built dataset | Jieba uses Paddle to build a word segmentation network (two-way GRU). At the same time, it supports traditional word segmentation methods of jieba, such as precise mode, full mode, search engine mode, etc. | |
lac | BiGRU+CRF | Baidu self built dataset | The lexical analysis model jointly developed by Baidu can complete the tasks of Chinese word segmentation, part of speech tagging and proper name recognition as a whole. Evaluated on Baidu self built dataset, LAC effect: Precision=88.0%, Recall=88.7%, F1 Score=88.4%. |
module | Network | Dataset | Introduction |
---|---|---|---|
auto_punc | Ernie-1.0 | WuDaoCorpora 2.0 | Automatically add 7 punctuation marks |
module | Network | Dataset | Introduction |
---|---|---|---|
porn_detection_cnn | CNN | Baidu self built dataset | Pornography detection, automatically identify whether the text is pornographic and give the corresponding confidence, and identify pornographic descriptions, vulgar friends, and dirty documents in the text |
porn_detection_gru | GRU | Baidu self built dataset | Pornography detection, automatically identify whether the text is pornographic and give the corresponding confidence, and identify pornographic descriptions, vulgar friends, and dirty documents in the text |
porn_detection_lstm | LSTM | Baidu self built dataset | Pornography detection, automatically identify whether the text is pornographic and give the corresponding confidence, and identify pornographic descriptions, vulgar friends, and dirty documents in the text |
module | Network | Dataset | Introduction |
---|---|---|---|
ge2e_fastspeech2_pwgan | FastSpeech2 | AISHELL-3 | Chinese speech cloning |
lstm_tacotron2 | LSTM、Tacotron2、WaveFlow | AISHELL-3 | Chinese speech cloning |
module | Network | Dataset | Introduction |
---|---|---|---|
transformer_tts_ljspeech | Transformer | LJSpeech-1.1 | English speech synthesis |
fastspeech_ljspeech | FastSpeech | LJSpeech-1.1 | English speech synthesis |
fastspeech2_baker | FastSpeech2 | Chinese Standard Mandarin Speech Copus | Chinese speech synthesis |
fastspeech2_ljspeech | FastSpeech2 | LJSpeech-1.1 | English speech synthesis |
deepvoice3_ljspeech | DeepVoice3 | LJSpeech-1.1 | English speech synthesis |
module | Network | Dataset | Introduction |
---|---|---|---|
deepspeech2_aishell | DeepSpeech2 | AISHELL-1 | Chinese Speech Recognition |
deepspeech2_librispeech | DeepSpeech2 | LibriSpeech | English Speech Recognition |
u2_conformer_aishell | Conformer | AISHELL-1 | Chinese Speech Recognition |
u2_conformer_wenetspeech | Conformer | WenetSpeech | Chinese Speech Recognition |
u2_conformer_librispeech | Conformer | LibriSpeech | English Speech Recognition |
module | Network | Dataset | Introduction |
---|---|---|---|
panns_cnn6 | PANNs | Google Audioset | It mainly includes 4 convolution layers and 2 full connection layers, and the model parameter is 4.5M. After pre-training, it can be used to extract the embbedding of audio. The dimension is 512 |
panns_cnn14 | PANNs | Google Audioset | It mainly includes 4 convolution layers and 2 full connection layers, and the model parameter is 4.5M. After pre-training, it can be used to extract the embbedding of audio. The dimension is 2048 |
panns_cnn10 | PANNs | Google Audioset | It mainly includes 4 convolution layers and 2 full connection layers, and the model parameter is 4.5M. After pre-training, it can be used to extract the embbedding of audio. The dimension is 512 |
module | Network | Dataset | Introduction |
---|---|---|---|
videotag_tsn_lstm | TSN + AttentionLSTM | Baidu self built dataset | Short-video classification |
tsn_kinetics400 | TSN | Kinetics-400 | Video classification |
tsm_kinetics400 | TSM | Kinetics-400 | Video classification |
stnet_kinetics400 | StNet | Kinetics-400 | Video classification |
nonlocal_kinetics400 | Non-local | Kinetics-400 | Video classification |
module | Network | Dataset | Introduction |
---|---|---|---|
SkyAR | UNet | UNet | Video sky Replacement |
module | Network | Dataset | Introduction |
---|---|---|---|
fairmot_dla34 | CenterNet | Caltech Pedestrian+CityPersons+CUHK-SYSU+PRW+ETHZ+MOT17 | Realtime multiple object tracking |
jde_darknet53 | YOLOv3 | Caltech Pedestrian+CityPersons+CUHK-SYSU+PRW+ETHZ+MOT17 | object tracking with both accuracy and speed |
module | Network | Dataset | Introduction |
---|---|---|---|
WatermeterSegmentation | DeepLabV3 | Water meter dataset | Water meter segmentation |