Model Zoo

More info on downloading, converting, and submitting models can be found on the main documentation website. If you are already a Caffe2 contributor, feel free to modify this wiki and add models.

Image Classification

Name	Type	Dataset	Caffe Model	Caffe2 Model
Squeezenet	image classification	ImageNet > AlexNet
BVLC AlexNet	image classification	ImageNet > AlexNet
BVLC CaffeNet Model	image classification	ImageNet > AlexNet
BVLC GoogleNet Model	image classification	ILSVRC 2014 > GoogleNet/Inception
VGG Team ILSVRC14 16-layer	image classification	ILSVRC 2014 > Very Deep CNN
VGG Team ILSVRC14 19-layer	image classification	ILSVRC 2014 > Very Deep CNN
Network in Network ImageNet Model	small image classification dataset and fast	ImageNet
Network in Network CIFAR10 Model	tiny image classification dataset and fast	CIFAR-10
FCN-32s PASCAL	image classification	ILSVRC14 VGG-16
FCN-16s-PASCAL	image classification	ILSVRC14 VGG-16
FCN-8s PASCAL	image classification	ILSVRC14 VGG-16
FCN-8s PASCAL at-once	image classification	ILSVRC14 VGG-16
FCN-AlexNet PASCAL	image classification	AlexNet
Places-CNN model	places	Places205-AlexNet	tar.gz
Flower Power	flowers	Oxford 102
ImageNet ILSVRC13 RCNN	image classification	ILSVRC13

Image Segmentation

Name	Type	Dataset	Caffe Model	Caffe2 Model
FCN-32s NYUDv2 Color	image segmentation	AlexNet
FCN-32s NYUDv2 HHA	image segmentation	AlexNet
FCN-32s NYUDv2 Early Color-Depth	image segmentation	AlexNet	n/a
FCN-32s NYUDv2 Late Color-HHA	image segmentation	AlexNet
FCN-32s SIFT Flow	image segmentation	AlexNet
FCN-16s SIFT Flow	image segmentation	AlexNet
FCN-8s SIFT Flow	image segmentation	AlexNet
CRF-RNN PASCAL	image segmentation, object classification	PASCAL

Object and Scene Labeling

Name	Type	Dataset	Caffe Model	Caffe2 Model
FCN-32s PASCAL-Context	object and scene labeling	AlexNet
FCN-16s PASCAL-Context	object and scene labeling	AlexNet
FCN-8s PASCAL-Context	object and scene labeling	AlexNet
Salient Object Subitizing	object detection	various
GoogLeNet_cars on car model classification	cars	CompCars

Style

Name	Type	Dataset	Caffe Model	Caffe2 Model
Flickr Style	image style	CaffeNet

Style Transfer

Name	Type	Dataset	Caffe Model	Caffe2 Model
Crayon

Faces

Name	Type	Dataset	Caffe Model	Caffe2 Model
Models for Age and Gender Classification	faces > age, gender	OUI-Adience Face	zip
VGG Face CNN descriptor	faces > celebrities	VGG-Face	tar.gz
Yearbook Photo	faces > yearbook	VGG-16 + train_val,solver
Emotion Recognition	faces > emotion		zip
Facial Landmark Detection	faces > landmark
Pose-Aware CNN Models (PAMs)	faces > recognition	CASIA WebFaces
ResFace-101	faces > recognition	3D Augmented CASIA
ResNet-101 for regressing 3DMMs	faces > recognition, 3D shape and texture	3DMMs on CASIA
Age Estimation Using Ranking-CNN	faces > age	MORPH Database

Video Processing

Name	Type	Dataset	Caffe Model	Caffe2 Model
SegNet	scene segmentation: cars, buildings, pedestrians, etc
Translating Videos to Natural Language	CNN + RNN, video input, text output
Sequence to Sequence - Video to Text	CNN + RNN, video input, text output	S2VT_VGG, S2VT_vocabulary