'%20fill='%23C31D20'%20fill-rule='nonzero'%3e%3cpath%20d='M7.55269822,13.7609409%20C10.8552199,9.97176134%2014.2271223,7.63452926%2017.1034483,6.5677512%20L17.0816429,0.884990191%20C17.0593112,0.508963963%2016.8188535,0.182653682%2016.4703158,0.055395956%20C16.1217781,-0.0718617705%2015.7322263,0.0244201241%2015.4799397,0.300178022%20L12.9584465,3.07097775%20L0.368821458,17.4916392%20C0.0232151224,17.8857306%20-0.0894678188,18.437454%200.0732192079,18.9389805%20C0.235906234,19.4405071%200.649247199,19.815643%201.15754056,19.9230783%20C1.66583392,20.0305135%202.19185783,19.853926%202.53746417,19.4598346%20L7.5467513,13.7690073%20L7.55269822,13.7609409%20Z'%20id='路径'%3e%3c/path%3e%3cpath%20d='M10.6896552,12.0927463%20L15.1004089,17.5535201%20C15.4511303,17.8402432%2015.9409156,17.8973222%2016.3502521,17.6991755%20C16.7595885,17.5010287%2017.0117165,17.0848129%2016.993637,16.6370685%20L17.1034483,10.0202479%20C14.5615201,9.75868982%2012.477139,10.7130773%2010.6896552,12.0927463%20Z'%20id='路径'%3e%3c/path%3e%3c/g%3e%3crect%20id='矩形'%20x='0'%20y='0'%20width='24'%20height='24'%3e%3c/rect%3e%3c/g%3e%3c/g%3e%3c/svg%3e)
模型支持列表
当前MindX SDK支持新、老两种模型后处理框架，具体请参见推理模型后处理开发介绍，请根据实际框架使用对应的后处理动态库。
模型种类 |
模型框架 |
使用后处理动态库 |
获取途径 |
|---|---|---|---|
YOLOv3 |
TensorFlow |
（新框架）modelpostprocessors/libyolov3postprocess.so |
无 |
Caffe |
内部调试中，暂请勿使用，请等待后续提供。 |
||
ResNet50 |
TensorFlow |
（新框架）modelpostprocessors/libresnet50postprocess.so |
无 |
Faster Rcnn |
TensorFlow |
（新框架）modelpostprocessors/libfasterrcnnpostprocess.so |
无 |
MindSpore |
|||
YOLOv4 |
Pytorch |
（新框架）modelpostprocessors/libyolov3postprocess.so |
|
MindSpore |
无 |
||
SSD-VGG16 |
Caffe |
（新框架）modelpostprocessors/libssdvggpostprocess.so |
内部调试中，暂请勿使用，请等待后续提供。 |
SSD MobileNet v1 FPN |
TensorFlow |
（新框架）modelpostprocessors/libssdmobilenetfpnpostprocess.so |
|
CRNN |
TensorFlow |
（新框架）modelpostprocessors/libcrnnpostprocess.so |
|
YOLOv5 |
Pytorch |
（新框架）modelpostprocessors/libyolov3postprocess.so |
|
FasterRCNN-FPN/CascadeRCNN-FPN |
Pytorch |
（新框架）modelpostprocessors/libfasterrcnnpostprocess.so |
|
ResNet-18 |
TensorFlow |
（新框架）modelpostprocessors/libresnet50postprocess.so |
|
DeepLabv3+ |
TensorFlow |
（新框架）modelpostprocessors/libdeeplabv3post.so |
无 |
CTPN |
TensorFlow |
（新框架）modelpostprocessors/libctpnpostprocess.so |
|
CTPN |
MindSpore |
（新框架）modelpostprocessors/libctpnpostprocess.so |
|
DeepLabv3 |
MindSpore |
（新框架）modelpostprocessors/libdeeplabv3post.so |
|
BERT-Base (Uncased) |
TensorFlow |
（新框架）modelpostprocessors/libresnet50postprocess.so |
|
DeepLabv3+ |
Pytorch |
（新框架）modelpostprocessors/libdeeplabv3post.so |
|
U-Net |
MindSpore |
（新框架）modelpostprocessors/libunetmindsporepostprocess.so |
|
Mask R-CNN |
Pytorch |
（新框架）modelpostprocessors/libmaskrcnnmindsporepost.so |
|
FaceNet |
TensorFlow |
无需后处理。 |
|
SSD MobileNet v1 FPN |
MindSpore |
（新框架）modelpostprocessors/libSsdMobilenetFpn_MindsporePost.so |
|
OpenPose |
TensorFlow |
（新框架）modelpostprocessors/libopenposepostprocess.so |
内部调试中，暂请勿使用，请等待后续提供。 |
Unet++ |
MindSpore |
（新框架）modelpostprocessors/libunetmindsporepostprocess.so |
内部调试中，暂请勿使用，请等待后续提供。 |
RetinaNet |
TensorFlow |
（新框架）modelpostprocessors/retinanetpostprocess.so |
|
HigherHRnet |
Pytorch |
（新框架）modelpostprocessors/libhigherhrnetpostprocess.so |
