Viewing: resources.wolframcloud.com

The Wolfram Neural Net Repository is a public resource that hosts an expanding collection of trained and untrained neural network models, suitable for immediate evaluation, training, visualization, transfer learning and more.

Building on the Wolfram Language neural net framework, the Wolfram Neural Net Repository provides a uniform system for storing neural net models in an immediately computable form. Including models from the latest research papers, as well as ones trained or created at Wolfram Research, the Wolfram Neural Net Repository is built to be a global resource for neural net models.

Audio Analysis

CREPE Pitch Detection Net Trained on Monophonic Signal Data []

Track the pitch of a monophonic signal
Whisper-V1 Multilingual Nets []

Translate multiple-language audio recordings to English
Whisper-V1 Multilingual Turbo []

Transcribe multiple-language audio recordings
Whisper-V1 Nets []

Transcribe an English audio recording
Wolfram AudioIdentify V1 Trained on AudioSet Data []

Identify sounds in an audio signal

Classification

3D-Inflated ResNet-50 Trained on Kinetics 400 Data

Identify the main action in a video
Ademxapp Model A Trained on ImageNet Competition Data []

Identify the main object in an image
Age Estimation VGG-16 Trained on IMDB-WIKI and Looking at People Data []

Predict a person's age from an image of their face
Age Estimation VGG-16 Trained on IMDB-WIKI Data []

Predict a person's age from an image of their face
CapsNet Trained on MNIST Data []

Identify the handwritten digit in an image
Channel-Separated Video Action Classification Net Trained on Kinetics-400 Data

Identify the main action in a video
DenseNet-121 Trained on ImageNet Competition Data []

Identify the main object in an image
EfficientNet Trained on ImageNet []

Identify the main object in an image
EfficientNet Trained on ImageNet with AdvProp and AutoAugment []

Identify the main object in an image
EfficientNet Trained on ImageNet with AutoAugment []

Identify the main object in an image
EfficientNet Trained on ImageNet with NoisyStudent []

Identify the main object in an image
EfficientNet Trained on ImageNet with RandAugment []

Identify the main object in an image
EfficientNet-V2 Trained on ImageNet-21K []

Identify the main object in an image
EfficientNet-V2 Trained on ImageNet Competition Data []

Identify the main object in an image
Gender Prediction VGG-16 Trained on IMDB-WIKI Data []

Predict a person's gender from an image of their face
Inception V1 Trained on Extended Salient Object Subitizing Data []

Count the number of prominent items in an image
Inception V1 Trained on ImageNet Competition Data []

Identify the main object in an image
Inception V1 Trained on Places365 Data []

Identify the scene type of an image
Inception V3 Trained on ImageNet Competition Data []

Identify the main object in an image
LeNet Trained on MNIST Data []

Identify the handwritten digit in an image
MobileNet-3D V1 Trained on Video Datasets

Identify the action in a video
MobileNet-3D V2 Trained on Video Datasets

Identify the main action in a video
MobileNet V1 Trained on ImageNet Competition Data []

Identify the main object in an image
MobileNet V2 Trained on ImageNet Competition Data []

Identify the main object in an image
MobileNet V3 Trained on ImageNet Competition Data []

Identify the main object in an image
Optic-Net Classifier for Retinal Diseases []

Diagnose retinal diseases from optical tomography images
ResNet-101 Trained on ImageNet Competition Data []

Identify the main object in an image
ResNet-101 Trained on YFCC100m Geotagged Data []

Determine the geolocation of a photograph
ResNet-152 Trained on ImageNet Competition Data []

Identify the main object in an image
ResNet-50 Trained on ImageNet Competition Data []

Identify the main object in an image
Self-Normalizing Net for Numeric Data []

Perform classification or regression on numeric data
ShuffleNet-3D V1 Trained on Video Datasets

Identify the main action in a video
ShuffleNet-3D V2 Trained on Video Datasets

Identify the main action in a video
ShuffleNet-V1 Trained on ImageNet Competition Data []

Identify the main object in an image
ShuffleNet-V2 Trained on ImageNet Competition Data []

Identify the main object in an image
SlowFast Video Action Classification Trained on Kinetics-400 Data

Identify the main action in a video
Spatiotemporal ResNet-18 for Action Recognition Trained on Kinetics-400 Data

Identify the main action in a video
Squeeze-and-Excitation Net Trained on ImageNet Competition Data []

Identify the main object in an image
SqueezeNet-3D Trained on Video Datasets

Identify the main action in a video
SqueezeNet V1.1 Trained on ImageNet Competition Data []

Identify the main object in an image
VGG-16 Trained on ImageNet Competition Data []

Identify the main object in an image
VGG-19 Trained on ImageNet Competition Data []

Identify the main object in an image
Vision Transformer Trained on ImageNet Competition Data []

Identify the main object in an image
Wide ResNet-50-2 Trained on ImageNet Competition Data []

Identify the main object in an image
Wolfram AudioIdentify V1 Trained on AudioSet Data []

Identify sounds in an audio signal
Wolfram ImageIdentify Net V1 []

Identify the main object in an image
Wolfram ImageIdentify Net V2 []

Identify the main object in an image
X3D Video Action Classification Trained on Kinetics-400 Data

Identify the main action in a video
Yahoo Open NSFW Model V1 []

Determine whether an image contains pornographic content
YOLO V8 Classify Trained on ImageNet Competition Data []

Identify the main object in an image

Data Generation

Sketch-RNN Trained on QuickDraw Data [] []

Generate hand-drawn sketches
Stable Diffusion V1 [] []

Generate photorealistic images

Denoising

FastDVDNet Trained on DAVIS Data

Remove noise from a video

Feature Extraction

BERT Trained on BookCorpus and Wikipedia Data []

Represent text as a sequence of vectors
BioBERT Trained on PubMed and PMC Data []

Represent text as a sequence of vectors
BLIP Image Captioning Nets Trained on MS-COCO Data []

Generate a textual description of an image
BLIP Image-Text Matching Nets Trained on Captioning Datasets [] []

Find the similarity score between a text and an image
BLIP Visual Question Answering Nets Trained on VQA Data [] []

Generate an answer to a question given an image
BPEmb Subword Embeddings Trained on Wikipedia Data []

Represent words or subwords as vectors
Clinical Concept Embeddings Trained on Health Insurance Claims, Clinical Narratives from Stanford and PubMed Journal Articles []

Represent a clinical concept as a vector
CLIP Multi-domain Feature Extractor [] []

Represent words and images as vectors
CoCa Image Captioning Nets Trained on LAION-2B Data [] []

Represent words and images as vectors
ConceptNet Numberbatch Word Vectors V17.06 []

Represent words as vectors
D2-Net Trained on MegaDepth Data []

Find generic keypoints and their feature vectors in an image
DistilBERT Trained on BookCorpus and English Wikipedia Data []

Represent text as a sequence of vectors
ELMo Contextual Word Representations Trained on 1B Word Benchmark []

Represent words as contextual word-embedding vectors
ESMFold-V1 Trained on UR50 Data []

Predict protein's 3D structure from amino acid sequences
GloVe 100-Dimensional Word Vectors Trained on Tweets []

Represent words as vectors
GloVe 100-Dimensional Word Vectors Trained on Wikipedia and Gigaword 5 Data []

Represent words as vectors
GloVe 200-Dimensional Word Vectors Trained on Tweets []

Represent words as vectors
GloVe 25-Dimensional Word Vectors Trained on Tweets []

Represent words as vectors
GloVe 300-Dimensional Word Vectors Trained on Common Crawl 42B []

Represent words as vectors
GloVe 300-Dimensional Word Vectors Trained on Common Crawl 840B []

Represent words as vectors
GloVe 300-Dimensional Word Vectors Trained on Wikipedia and Gigaword 5 Data []

Represent words as vectors
GloVe 50-Dimensional Word Vectors Trained on Tweets []

Represent words as vectors
GloVe 50-Dimensional Word Vectors Trained on Wikipedia and Gigaword 5 Data []

Represent words as vectors
GPT2 Transformer Trained on WebText Data []

Generate text in English and represent text as a sequence of vectors
GPT Transformer Trained on BookCorpus Data []

Generate text in English and represent text as a sequence of vectors
MiniLM V2 Text Feature Extractor []

Represent text as a sequence of vectors
NuNER-V2 Text Feature Extractor []

Represent text as a sequence of vectors
NuTopic Text Feature Extractor []

Represent text as a sequence of vectors
NuToxicity Text Feature Extractor []

Represent text as a sequence of vectors
OpenCLIP Multi-domain Feature Extractor Trained on DataComp-1B Data [] []

Represent words and images as vectors
OpenCLIP Multi-domain Feature Extractor Trained on LAION-2B Data [] []

Represent words and images as vectors
OpenFace Face Recognition Net Trained on CASIA-WebFace and FaceScrub Data []

Represent a facial image as a vector
Pose-Aware Face Recognition in the Wild Nets Trained on CASIA WebFace Data []

Represent a facial image as a vector
Pre-trained Distilled BERT Trained on BookCorpus and English Wikipedia Data []

Represent text as a sequence of vectors
ResNet-101 for 3D Morphable Model Regression Trained on Casia WebFace Data []

Represent a facial image as a vector
ResNet-101 Trained on Augmented CASIA-WebFace Data []

Represent a facial image as a vector
RoBERTa Trained on BookCorpus, English Wikipedia, CC-News, OpenWebText and Stories Datasets []

Represent text as a sequence of vectors
SciBERT Trained on Semantic Scholar Data []

Represent text as a sequence of vectors
VGGish Feature Extractor Trained on YouTube Data []

Represent sounds as a sequence of vectors

Image Processing

AdaIN-Style Trained on MS-COCO and Painter by Numbers Data []

Transfer the style of one image to another image
CoCa Image Captioning Nets Trained on LAION-2B Data [] []

Represent words and images as vectors
Colorful Image Colorization Trained on ImageNet Competition Data []

Colorize a grayscale image
ColorNet Image Colorization Trained on ImageNet Competition Data []

Colorize a grayscale image
ColorNet Image Colorization Trained on Places Data []

Colorize a grayscale image
CycleGAN Apple-to-Orange Translation Trained on ImageNet Competition Data []

Turn apples into oranges in a photo
CycleGAN Horse-to-Zebra Translation Trained on ImageNet Competition Data []

Turn horses into zebras in a photo
CycleGAN Monet-to-Photo Translation []

Turn a Monet-style painting into a photo
CycleGAN Orange-to-Apple Translation Trained on ImageNet Competition Data []

Turn oranges into apples in a photo
CycleGAN Photo-to-Cezanne Translation []

Turn a photo into a Cezanne-style painting
CycleGAN Photo-to-Monet Translation []

Turn a photo into a Monet-style painting
CycleGAN Photo-to-Van Gogh Translation []

Turn a photo into a Van Gogh-style painting
CycleGAN Summer-to-Winter Translation []

Turn a summertime photo into a wintertime photo
CycleGAN Winter-to-Summer Translation []

Turn a wintertime photo into a summertime photo
CycleGAN Zebra-to-Horse Translation Trained on ImageNet Competition Data []

Turn zebras into horses in a photo
Enhanced Super-Resolution GAN Trained on DIV2K, Flickr2K and OST Data []

Increase the resoution of an image
Pix2pix Photo-to-Street-Map Translation []

Generate a street map from a satellite photo
Pix2pix Street-Map-to-Photo Translation []

Generate a satellite photo from a street map
StarGAN Trained on CelebA Data []

Translate an image from one domain to another
U2-Net Portrait Generator Trained on APDrawing Data []

Generate a portrait sketch from a photo
Very Deep Net for Super-Resolution []

Increase the resolution of an image

Language Modeling

Google-T5 Multitask Language Model []

Perform a wide array of text-to-text tasks
GPT2 Transformer Trained on WebText Data []

Generate text in English and represent text as a sequence of vectors
GPT Transformer Trained on BookCorpus Data []

Generate text in English and represent text as a sequence of vectors
Sentiment Language Model Trained on Amazon Product Review Data []

Generate text in English and analyze sentiment
Wolfram C Character-Level Language Model V1 []

Generate C code
Wolfram English Character-Level Language Model V1 []

Generate text in English
Wolfram JavaScript Character-Level Language Model V1 []

Generate JavaScript code
Wolfram LaTeX Character-Level Language Model V1 []

Generate LaTeX code
Wolfram Python Character-Level Language Model V1 []

Generate Python code

Object Detection

CenterNet Pose Estimation Nets Trained on MS-COCO Data []

Detect and localize human joints and objects in an image
CenterNet Trained on MS-COCO Data []

Detect and localize objects in an image
DBNet Text Detector Trained on ICDAR-2015 and Total-Text Data []

Detect and localize text in an image
EfficientDet Trained on MS-COCO Data []

Detect and localize objects in an image
PANet Text Detector Trained on ICDAR-2015 and CTW1500 Data []

Detect and localize text in an image
PSENet Text Detector Trained on ICDAR-2015 and CTW1500 Data []

Detect and localize text in an image
RetinaNet-101 Feature Pyramid Net Trained on MS-COCO Data []

Detect and localize objects in an image
Scaled-YOLO V4 Trained on MS-COCO Data []

Detect and localize objects in an image
SSD Feature Pyramid Nets Trained on MS-COCO Data []

Detect and localize objects in an image
SSD-MobileNet V2 Trained on MS-COCO Data [] NEW

Detect and localize objects in an image
SSD-VGG-300 Trained on PASCAL VOC Data []

Detect and localize objects in an image
SSD-VGG-512 Trained on MS-COCO Data []

Detect and localize objects in an image
SSD-VGG-512 Trained on PASCAL VOC2007, PASCAL VOC2012 and MS-COCO Data []

Detect and localize objects in an image
YOLOR Trained on MS-COCO Data []

Detect and localize objects in an image
YOLO V2 Trained on MS-COCO Data []

Detect and localize objects in an image
YOLO V3 Trained on Open Images Data []

Detect and localize objects in an image
YOLO V5 Trained on MS-COCO Data []

Detect and localize objects in an image
YOLO V8 Detect Trained on MS-COCO Data []

Detect and localize objects in an image
YOLO V8 Pose Trained on MS-COCO Data []

Detect and localize human joints in an image
YOLOX Trained on MS-COCO Data []

Detect and localize objects in an image

Question Answering

BLIP Visual Question Answering Nets Trained on VQA Data [] []

Generate an answer to a question given an image
Google-T5 Multitask Language Model []

Perform a wide array of text-to-text tasks

Regression

2D Face Alignment Net Trained on 300W Large Pose Data []

Determine the locations of keypoints from a facial image
3D Face Alignment Net Trained on 300W Large Pose Data []

Determine the 2D projection of 3D keypoints from a facial image
CenterNet Pose Estimation Nets Trained on MS-COCO Data []

Detect and localize human joints and objects in an image
CenterNet Trained on MS-COCO Data []

Detect and localize objects in an image
D2-Net Trained on MegaDepth Data []

Find generic keypoints and their feature vectors in an image
ESMFold-V1 Trained on UR50 Data []

Predict protein's 3D structure from amino acid sequences
Micro Aerial Vehicle Trail Navigation Nets Trained on IDSIA Swiss Alps and PASCAL VOC Data []

Navigate a drone in a forest environment
MiDaS V2.1 Depth Perception Nets Trained on Multiple-Datasets []

Estimate the depth map of an image
MiniLM V2 Reranker Trained on MS MARCO Data []

Compute a relevance score for a query-passage pair
Self-Normalizing Net for Numeric Data []

Perform classification or regression on numeric data
Single-Image Depth Perception Net Trained on Depth in the Wild Data []

Estimate the depth map of an image
Single-Image Depth Perception Net Trained on NYU Depth V2 and Depth in the Wild Data []

Estimate the depth map of an image
Single-Image Depth Perception Net Trained on NYU Depth V2 Data []

Estimate the depth map of an image
Unguided Volumetric Regression Net for 3D Face Reconstruction []

Reconstruct a 3D facial image from a 2D facial image
Vanilla CNN for Facial Landmark Regression []

Determine the locations of the eyes, nose and mouth from a facial image

Semantic Segmentation

Ademxapp Model A1 Trained on ADE20K Data []

Segment an image into various semantic component classes
Ademxapp Model A1 Trained on Cityscapes Data []

Segment an image of a driving scenario into semantic component classes
Ademxapp Model A1 Trained on PASCAL VOC2012 and MS-COCO Data []

Segment an image into various semantic component classes
Dilated ResNet-105 Trained on Cityscapes Data []

Segment an image of a driving scenario into semantic component classes
Dilated ResNet-22 Trained on Cityscapes Data []

Segment an image of a driving scenario into semantic component classes
Dilated ResNet-38 Trained on Cityscapes Data []

Segment an image of a driving scenario into semantic component classes
DoubleU-Net Trained on Medical Image Segmentation Datasets []

Segment medical images performing a task-dependent binary classification
FastSAM Trained on MS-COCO Data []

Detect, segment and localize objects in an image
ForkNet Brain Segmentation Net Trained on NAMIC Data []

Segment an image of a human brain into different anatomical structures
Multi-scale Context Aggregation Net Trained on CamVid Data []

Segment an image of a driving scenario into semantic component classes
Multi-scale Context Aggregation Net Trained on Cityscapes Data []

Segment an image of a driving scenario into semantic component classes
Multi-scale Context Aggregation Net Trained on PASCAL VOC2012 Data []

Segment an image into various semantic component classes
U2-Net Trained on DUTS-TR Data []

Segment objects in an image
U-Net Trained on Glioblastoma-Astrocytoma U373 Cells on a Polyacrylamide Substrate Data []

Segment a microscopy image to detect cells
YOLO V8 Segment Trained on MS-COCO Data []

Detect, segment and localize objects in an image

Speech Recognition

Deep Speech 2 Trained on Baidu English Data []

Transcribe an English-language audio recording
Wav2Vec2 Trained on LibriSpeech Data []

Transcribe an English audio recording
Wav2Vec2 Trained on Multiple Datasets []

Transcribe an English audio recording
Wav2Vec2 XLSR-53 Trained on Multilingual Data []

Transcribe multiple-language audio recordings

Translation

Google-T5 Multitask Language Model []

Perform a wide array of text-to-text tasks
M2M-100 Multilingual Translation Net []

Translate text between any pair of one hundred languages
Whisper-V1 Multilingual Nets []

Translate multiple-language audio recordings to English
Whisper-V1 Multilingual Turbo []

Transcribe multiple-language audio recordings
Whisper-V1 Nets []

Transcribe an English audio recording

Image Captioning

BLIP Image Captioning Nets Trained on MS-COCO Data []

Generate a textual description of an image
CoCa Image Captioning Nets Trained on LAION-2B Data [] []

Represent words and images as vectors

Wolfram Neural Net Repository

Primary Navigation