Caffe Models for DesignWare EV Processors, v2020.06
·
29 commits
to master
since this release
This is release 2020.06 of the Synopsys-caffe-models, a set of Caffe Deep Learning Models adapted for use with DesignWare EV6x Processors.
These models must be used together with Synopsys-Caffe v2020.06 and the MetaWare EV Development Toolkit v2020.06 from Synopsys.
Supported Models
- alexnet
- DAN
- denoiser
- densenet
- deeplab
- facedetect_v1
- facedetect_v2
- faster_rcnn_resnet101
- fcn
- googlenet
- icnet
- inception_resnet_v1
- inception_resnet_v2
- inception_v1
- inception_v2
- inception_v3
- inception_v4
- lenet
- mobilenet
- mobilenet_ssd
- mtcnn_v1
- openpose
- pspnet
- resnet_101
- resnet_152
- resnet_50
- resnet50_ssd
- resnext_101
- resnext_152
- resnext_50
- retinanet
- segnet
- shufflenet_v1
- shufflenet_v2
- srgan
- squeezenet
- srcnn
- ssd
- pspnet
- unet
- vdcr
- vgg16
- yolo_tiny
- yolo_v1
- yolo_v2_coco
- yolo_v2_voc
- yolo_v3 (yolo_v3_tiny included)
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 v2020.03
New models
- retinanet
Updated models
- fcn- added FCN-ResNet18
- Inception V1 - added one new updated prototxt
- mobilenet_v3. Update pb_converted
- openpose. Add pose_deploy
- ResNet-152. Update models
Other changes
None
Helper tools
git_sparse_download.sh(bat) - helps to download only part of models.