T-2022.09-RC1

This is T-2022.09 release candidate 1 of the Synopsys-caffe-models, a set of Caffe Deep Learning Models adapted for use with DesignWare EV Processors.

These models must be used together with Synopsys-Caffe T-2022.09 and the MetaWare EV Development Toolkit T-2022.09 from Synopsys.

Supported Models

Alexnet, DAN, Denoiser, Densenet, Deeplab, Facedetect v1/v2, FaceNet, Faster_rcnn_resnet101, FCN, Googlenet. ICNet,
Inception_Resnet v1/v2, Inception v1/v2/v3/v4, LeNet, Mobilenet, Mobilenet_ssd, mtcnn v1, OpenPose, PSPNet,
Resnet 50/101/152, Resnet50_ssd, ResNext 50/101/152, RetinaNet, SegNet, ShuffleNet v1/v2, SRGAN, SqueezeNet, SRCNN, SSD,
PSPNet, UNet, VDCR, VGG16, Yolo v1/v1_tiny/v2_coco/v2_voc/v2_tiny/v3/v3_tiny

Images

• imagenet_mean - mean images for different image sizes
• imagenet_test_images - simple set of test images
• images - different image data sub-sets

T-2022.06-RC1

This is T-2022.06 release candidate 1 of the Synopsys-caffe-models, a set of Caffe Deep Learning Models adapted for use with DesignWare EV Processors.

These models must be used together with Synopsys-Caffe T-2022.06 and the MetaWare EV Development Toolkit T-2022.06 from Synopsys.

Supported Models

Alexnet, DAN, Denoiser, Densenet, Deeplab, Facedetect v1/v2, FaceNet, Faster_rcnn_resnet101, FCN, Googlenet. ICNet,
Inception_Resnet v1/v2, Inception v1/v2/v3/v4, LeNet, Mobilenet, Mobilenet_ssd, mtcnn v1, OpenPose, PSPNet,
Resnet 50/101/152, Resnet50_ssd, ResNext 50/101/152, RetinaNet, SegNet, ShuffleNet v1/v2, SRGAN, SqueezeNet, SRCNN, SSD,
PSPNet, UNet, VDCR, VGG16, Yolo v1/v1_tiny/v2_coco/v2_voc/v2_tiny/v3/v3_tiny

Images

• imagenet_mean - mean images for different image sizes
• imagenet_test_images - simple set of test images
• images - different image data sub-sets

Changes vs 2021.12

Updated the following graphs:

• added MT-CNN version mtcnn-transp-pnet_optimized.prototxt and ResNet version ResNet-50-deploy-1280x720.prototxt

S-2021.12-RC1

This is S-2021.12 release candidate 1 of the Synopsys-caffe-models, a set of Caffe Deep Learning Models adapted for use with DesignWare EV Processors.

These models must be used together with Synopsys-Caffe S-2021.12 and the MetaWare EV Development Toolkit S-2021.12 from Synopsys.

Supported Models

Alexnet, DAN, Denoiser, Densenet, Deeplab, Facedetect v1/v2, FaceNet, Faster_rcnn_resnet101, FCN, Googlenet. ICNet,
Inception_Resnet v1/v2, Inception v1/v2/v3/v4, LeNet, Mobilenet, Mobilenet_ssd, mtcnn v1, OpenPose, PSPNet,
Resnet 50/101/152, Resnet50_ssd, ResNext 50/101/152, RetinaNet, SegNet, ShuffleNet v1/v2, SRGAN, SqueezeNet, SRCNN, SSD,
PSPNet, UNet, VDCR, VGG16, Yolo v1/v1_tiny/v2_coco/v2_voc/v2_tiny/v3/v3_tiny

Images

• imagenet_mean - mean images for different image sizes
• imagenet_test_images - simple set of test images
• images - different image data sub-sets

Changes vs 2021.09

Updated the following graphs:

• removed the deprecated fasterrcnn lib codesVGG16

Caffe Models for DesignWare EV Processors, S-2021.09

This is release S-2021.09 of the Synopsys-caffe-models, a set of Caffe Deep Learning Models adapted for use with DesignWare EV Processors.

These models must be used together with Synopsys-Caffe S-2021.09 and the MetaWare EV Development Toolkit S-2021.09 from Synopsys.

Supported Models

Alexnet, DAN, Denoiser, Densenet, Deeplab, Facedetect v1/v2, FaceNet, Faster_rcnn_resnet101, FCN, Googlenet. ICNet,
Inception_Resnet v1/v2, Inception v1/v2/v3/v4, LeNet, Mobilenet, Mobilenet_ssd, mtcnn v1, OpenPose, PSPNet,
Resnet 50/101/152, Resnet50_ssd, ResNext 50/101/152, RetinaNet, SegNet, ShuffleNet v1/v2, SRGAN, SqueezeNet, SRCNN, SSD,
PSPNet, UNet, VDCR, VGG16, Yolo v1/v1_tiny/v2_coco/v2_voc/v2_tiny/v3/v3_tiny

Images

• imagenet_mean - mean images for different image sizes
• imagenet_test_images - simple set of test images
• images - different image data sub-sets

Changes vs 2021.06

Updated the following graphs:

• VGG16

Caffe Models for DesignWare EV Processors, S-2021.09-RC1

This is release S-2021.09-RC1 of the Synopsys-caffe-models, a set of Caffe Deep Learning Models adapted for use with DesignWare EV Processors.

These models must be used together with Synopsys-Caffe S-2021.09 and the MetaWare EV Development Toolkit S-2021.09 from Synopsys.

Supported Models

Alexnet, DAN, Denoiser, Densenet, Deeplab, Facedetect v1/v2, FaceNet, Faster_rcnn_resnet101, FCN, Googlenet. ICNet,
Inception_Resnet v1/v2, Inception v1/v2/v3/v4, LeNet, Mobilenet, Mobilenet_ssd, mtcnn v1, OpenPose, PSPNet,
Resnet 50/101/152, Resnet50_ssd, ResNext 50/101/152, RetinaNet, SegNet, ShuffleNet v1/v2, SRGAN, SqueezeNet, SRCNN, SSD,
PSPNet, UNet, VDCR, VGG16, Yolo v1/v1_tiny/v2_coco/v2_voc/v2_tiny/v3/v3_tiny

Images

• imagenet_mean - mean images for different image sizes
• imagenet_test_images - simple set of test images
• images - different image data sub-sets

Changes vs 2021.06

Updated the following graphs:

• VGG16

Caffe Models for DesignWare EV Processors, S-2021.06

This is release S-2021.06 of the Synopsys-caffe-models, a set of Caffe Deep Learning Models adapted for use with DesignWare EV Processors.

These models must be used together with Synopsys-Caffe S-2021.06 and the MetaWare EV Development Toolkit S-2021.06 from Synopsys.

Supported Models

Alexnet, DAN, Denoiser, Densenet, Deeplab, Facedetect v1/v2, FaceNet, Faster_rcnn_resnet101, FCN, Googlenet. ICNet,
Inception_Resnet v1/v2, Inception v1/v2/v3/v4, LeNet, Mobilenet, Mobilenet_ssd, mtcnn v1, OpenPose, PSPNet,
Resnet 50/101/152, Resnet50_ssd, ResNext 50/101/152, RetinaNet, SegNet, ShuffleNet v1/v2, SRGAN, SqueezeNet, SRCNN, SSD,
SSD_Mobilenet_v2_coco, PSPNet, UNet, VDCR, VGG16, Yolo v1/v1_tiny/v2_coco/v2_voc/v2_tiny/v3/v3_tiny

Images

• imagenet_mean - mean images for different image sizes
• imagenet_test_images - simple set of test images
• images - different image data sub-sets

Changes vs 2021.03

New models

• SSD_Mobilenet_v2_coco

Caffe Models for DesignWare EV Processors, R-2021.03

This is release R-2021.03 of the Synopsys-caffe-models, a set of Caffe Deep Learning Models adapted for use with DesignWare EV Processors.

These models must be used together with Synopsys-Caffe R-2021.03 and the MetaWare EV Development Toolkit R-2021.03 from Synopsys.

Supported Models

Alexnet, DAN, Denoiser, Densenet, Deeplab, Facedetect v1/v2, FaceNet, Faster_rcnn_resnet101, FCN, Googlenet. ICNet,
Inception_Resnet v1/v2, Inception v1/v2/v3/v4, LeNet, Mobilenet, Mobilenet_ssd, mtcnn v1, OpenPose, PSPNet,
Resnet 50/101/152, Resnet50_ssd, ResNext 50/101/152, RetinaNet, SegNet, ShuffleNet v1/v2, SRGAN, SqueezeNet, SRCNN, SSD,
PSPNet, UNet, VDCR, VGG16, Yolo v1/v1_tiny/v2_coco/v2_voc/v2_tiny/v3/v3_tiny

Images

• imagenet_mean - mean images for different image sizes
• imagenet_test_images - simple set of test images
• images - different image data sub-sets

Changes vs 2020.12

New models

• Yolo-V2 Tiny

New zipped models and downloader

In the archived_models folder, we placed zipped models and a Python downloader script. Please see details in:
archived_models/README.md

Helper tools

git_sparse_download.sh(bat) - old git based downloader
archived_models/download_unpack_cnn_models.py - new Python based downloader

Caffe Models for DesignWare EV Processors, R-2021.03-RC1

This is release R-2021.03-RC1 of the Synopsys-caffe-models, a set of Caffe Deep Learning Models adapted for use with DesignWare EV Processors.

These models must be used together with Synopsys-Caffe R-2021.03-RC1 and the MetaWare EV Development Toolkit R-2021.03-RC1 from Synopsys.

Supported Models

Alexnet, DAN, Denoiser, Densenet, Deeplab, Facedetect v1/v2, FaceNet, Faster_rcnn_resnet101, FCN, Googlenet. ICNet,
Inception_Resnet v1/v2, Inception v1/v2/v3/v4, LeNet, Mobilenet, Mobilenet_ssd, mtcnn v1, OpenPose, PSPNet,
Resnet 50/101/152, Resnet50_ssd, ResNext 50/101/152, RetinaNet, SegNet, ShuffleNet v1/v2, SRGAN, SqueezeNet, SRCNN, SSD,
PSPNet, UNet, VDCR, VGG16, Yolo v1/v1_tiny/v2_coco/v2_voc/v2_tiny/v3/v3_tiny

Images

• imagenet_mean - mean images for different image sizes
• imagenet_test_images - simple set of test images
• images - different image data sub-sets

Changes vs 2020.12

New models

• Yolo-V2 Tiny

Helper tools

git_sparse_download.sh(bat) - helps to download only part of models.

Caffe Models for DesignWare EV Processors, R-2020.12

This is release R-2020.12 of the Synopsys-caffe-models, a set of Caffe Deep Learning Models adapted for use with DesignWare EV Processors.

These models must be used together with Synopsys-Caffe R-2020.12 and the MetaWare EV Development Toolkit R-2020.12 from Synopsys.

Supported Models

Alexnet, DAN, Denoiser, Densenet, Deeplab, Facedetect v1/v2, FaceNet, Faster_rcnn_resnet101, FCN, Googlenet. ICNet,
Inception_Resnet v1/v2, Inception v1/v2/v3/v4, LeNet, Mobilenet, Mobilenet_ssd, mtcnn v1, OpenPose, PSPNet,
Resnet 50/101/152, Resnet50_ssd, ResNext 50/101/152, RetinaNet, SegNet, ShuffleNet v1/v2, SRGAN, SqueezeNet, SRCNN, SSD,
PSPNet, UNet, VDCR, VGG16, Yolo v1/v1_tiny/v2_coco/v2_voc/v3/v3_tiny

Images

• imagenet_mean - mean images for different image sizes
• imagenet_test_images - simple set of test images
• images - different image data sub-sets

Changes vs 2020.09

Updated models

• DAN
• DeepLab,
• ICNet,
• Inception-Resnet-V1
• LeNet
• MobileNet
• MobileNet-SSD
• ResNet50-SSD
• RetinaNet
• SEGNet
• SSD
• Yolo-V3

Other changes

Add Yolo-V3 annotation test_images

Helper tools

git_sparse_download.sh(bat) - helps to download only part of models.

Caffe Models for DesignWare EV Processors, R-2020.12-RC2

This is release R-2020.12-RC2 of the Synopsys-caffe-models, a set of Caffe Deep Learning Models adapted for use with DesignWare EV Processors.

These models must be used together with Synopsys-Caffe R-2020.12-RC2 and the MetaWare EV Development Toolkit R-2020.12-RC2 from Synopsys.

Supported Models

Alexnet, DAN, Denoiser, Densenet, Deeplab, Facedetect v1/v2, FaceNet, Faster_rcnn_resnet101, FCN, Googlenet. ICNet,
Inception_Resnet v1/v2, Inception v1/v2/v3/v4, LeNet, Mobilenet, Mobilenet_ssd, mtcnn v1, OpenPose, PSPNet,
Resnet 50/101/152, Resnet50_ssd, ResNext 50/101/152, RetinaNet, SegNet, ShuffleNet v1/v2, SRGAN, SqueezeNet, SRCNN, SSD,
PSPNet, UNet, VDCR, VGG16, Yolo v1/v1_tiny/v2_coco/v2_voc/v3/v3_tiny

Images

• imagenet_mean - mean images for different image sizes
• imagenet_test_images - simple set of test images
• images - different image data sub-sets

Changes vs 2020.09

Updated models

• DeepLab,
• ICNet,
• Inception-Resnet-V1
• MobileNet
• MobileNet-SSD
• RetinaNet
• SEGNet
• SSD
• Yolo-V3

Other changes

Add Yolo-V3 annotation test_images

Helper tools

git_sparse_download.sh(bat) - helps to download only part of models.