MIVisionX supported models and operators#
The following tables list the models and operators supported by different frameworks in the current release of MIVisionX.
Models#
Networks |
Caffe |
ONNX |
NNEF |
AlexNet |
|
|
|
Caffenet |
|
||
DenseNet |
|
||
Googlenet |
|
|
|
Inception-V1 |
|
|
|
Inception-V2 |
|
|
|
Inception-V3 |
|||
Inception-V4 |
|
||
MNIST |
|
|
|
Mobilenet |
|
|
|
MobilenetV2 |
|
||
ResNet-18 |
|
||
ResNet-34 |
|
||
ResNet-50 |
|
|
|
ResNet-101 |
|
|
|
ResNet-152 |
|
|
|
ResNetV2-18 |
|
||
ResNetV2-34 |
|
||
ResNetV2-50 |
|
||
ResNetV2-101 |
|
||
Squeezenet |
|
|
|
Tiny-Yolo-V2 |
|
||
VGGNet-16 |
|
|
|
VGGNet-19 |
|
|
|
Yolo-V3 |
|
||
ZFNet |
|
Note
MIVisionX supports ONNX models with release 1.1 and release 1.3 tags
Operators#
Layers |
Caffe |
ONNX |
NNEF |
Add |
|
|
|
Argmax |
|
|
|
AveragePool |
|
|
|
BatchNormalization |
|
|
|
Cast |
|
||
Clamp |
|
||
Clip |
|
||
Concat |
|
|
|
Constant |
|
||
Conv |
|
|
|
ConvTranspose |
|
|
|
Copy |
|
|
|
Crop |
|
||
CropAndResize |
|||
Deconv |
|
|
|
DetectionOutput |
|
||
Div |
|
|
|
Dropout |
|||
Eltwise |
|
||
Exp |
|
|
|
Equal |
|
||
Flatten |
|
||
Gather |
|
||
GEMM |
|
|
|
GlobalAveragePool |
|
|
|
Greater |
|
||
GreaterOrEqual |
|
||
InnerProduct |
|
||
Interp |
|
||
LeakyRelu |
|
|
|
Less |
|
||
LessOrEqual |
|
||
Linear |
|
||
Log |
|
|
|
LRN |
|
|
|
Matmul |
|
|
|
Max |
|
|
|
MaxPool |
|
|
|
MeanReduce |
|
||
Min |
|
|
|
Mul |
|
|
|
MulAdd |
|||
NonMaxSuppression |
|
||
Permute |
|
|
|
PriorBox |
|
||
ReduceMin |
|
||
Relu |
|
|
|
Reshape |
|
|
|
Shape |
|
||
Sigmoid |
|
|
|
Slice |
|
|
|
Split |
|
||
Softmax |
|
|
|
SoftmaxWithLoss |
|
||
Squeeze |
|
|
|
Sub |
|
|
|
Sum |
|
||
Tile |
|
||
TopK |
|
||
Transpose |
|
|
|
Unsqueeze |
|
|
|
Upsample |
|
|