Size

Speed

DCUNet

Accuracy

ResNeXt50_32X4D

ResNet101

CNN based end2end head pose estimation model.

SixDRepNet

ViT_B_32

EfficientNet

ViT_L_32

Transformer based image classification model.

ViT_B_16

ResNeXt101_32X8D

Speech to text model for transcribing audio files. 

Whisper Large V2

image-text similarity and for zero-shot image classification

CLIP

Fully convolutional network for semantic segmentation

FCN ResNet101

FCN ResNet50

DeepLabV3 ResNet50

ResNet152

CNN based real-time anchor-free object detection model.

YOLOX

ResNet50

ResNet18

CNN based real time face detection model.

RetinaFace

ResNet34

YOLOv7

CNN based lightweight Image Super-Resolution model.