efficientnet-widese-b4 ImageNet pretrained weights

efficientnet_v1-wse-b4_pyt_ckpt

Semantic segmentation of persons in an image.

peoplesemsegnet

speechsynthesis_en_us_auxiliary_files

4 class object detection network to detect cars in an image.

trafficcamnet

1 class instance segmentation network to detect and segment instances of people in an image.

peoplesegnet

3 class object detection network to detect people in an image.

peoplenet

bodyposenet

Pretrained weights to facilitate transfer learning using TAO Toolkit.

pretrained_object_detection

dashcamnet

gpunet_0_pyt_ckpt

Resnet18 model to classify a car crop into 1 out 6 car types.

vehicletypenet

pretrained_classification

pretrained_detectnet_v2

Resnet18 model to classify a car crop into 1 out 20 car brands.

vehiclemakenet

1 class object detection network to detect faces in an image.

facedetectir

facenet

Pretrained backbones for TAO Toolkit TF2 image classification

pretrained_classification_tf2

5 class action recognition network to recognize what people do in an image.

actionrecognitionnet

StyleGAN3 pretrained models for FFHQ, AFHQv2 and MetFaces datasets.

stylegan3

gpunet_p0_pyt_ckpt

Speech Synthesis model trained on female English speech

tts_en_talknet

gpunet_1_pyt_ckpt

gpunet_2_pyt_ckpt

gpunet_d1_pyt_ckpt

LlaMa 2 is a large language AI model capable of generating text and code in response to prompts.

llama2-13b

The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.1 generative text model using a variety of publicly available conversation datasets.