OpenVINO之六：转换MXNet模型

1

2 OpenVINO支持的MXNet模型

2-1 Classification models:

• VGG-16 VGG-19
• ResNet-152 v1
• SqueezeNet_v1.1
• Inception BN
• CaffeNet
• DenseNet-121 DenseNet-161 DenseNet-169 DenseNet-201
• MobileNet

2-2 Object detection models:

• SSD-ResNet-50
• SSD-VGG-16-300
• SSD-Inception v3

2-3 Semantic Segmentation models:

• FCN8

2-4 Face Detection models:

• MTCNN P-Net MTCNN N-Net MTCNN O-Net MTCNN R-Net

Lightened_moon
RNN-Transducer Repo
word_lm Repo

3 OpenVINO支持的MXNet层与其在Intermediate Representation (IR)中的对应关系

NUMBER	SYMBOL NAME IN MXNET*	LAYER NAME IN THE INTERMEDIATE REPRESENTATION
1	BatchNorm	BatchNormalization
2	Crop	Crop
3	ScaleShift	ScaleShift
4	Pooling	Pooling
5	SoftmaxOutput	SoftMax
6	SoftmaxActivation	SoftMax
7	null	Ignored, does not appear in IR
8	Convolution	Convolution
9	Deconvolution	Deconvolution
10	Activation(act_type = relu)	ReLU
11	ReLU	ReLU
12	LeakyReLU	ReLU (negative_slope = 0.25)
13	Concat	Concat
14	elemwise_add	Eltwise(operation = sum)
15	_Plus	Eltwise(operation = sum)
16	Flatten	Flatten
17	Reshape	Reshape
18	FullyConnected	FullyConnected
19	UpSampling	Resample
20	transpose	Permute
21	LRN	Norm
22	L2Normalization	Normalize
23	Dropout	Ignored, does not appear in IR
24	_copy	Ignored, does not appear in IR
25	_contrib_MultiBoxPrior	PriorBox
26	_contrib_MultiBoxDetection	DetectionOutput
27	broadcast_mul	ScaleShift
28	sigmoid	sigmoid
29	Activation (act_type = tanh)	Activation (operation = tanh)
30	LeakyReLU (act_type = prelu)	PReLU
31	LeakyReLU (act_type = elu)	Activation (operation = elu)
32	elemwise_mul	Eltwise (operation = mul)
33	add_n	Eltwise (operation = sum)
34	ElementWiseSum	Eltwise (operation = sum)
35	_mul_scalar	Power
36	broadcast_add	Eltwise (operation = sum)
37	slice_axis	Crop
38	Custom	Custom Layers in the Model Optimizer
39	_minus_scalar	Power
40	Pad	Pad
41	_contrib_Proposal	Proposal
42	ROIPooling	ROIPooling
43	stack	Concat
44	swapaxis	Permute
45	zeros	Const
45	rnn	TensorIterator
46	rnn_param_concat	Concat
47	slice_channel	Split
48	_maximum	Eltwise(operation = max)
49	_minimum	Power(scale=-1) + Eltwise(operation = max) + Power(scale=-1)
50	InstanceNorm	scale * (x - mean) / sqrt(variance + epsilon) + B
51	Embedding	Gather

参考资料：
1 Converting a MXNet* Model
2 Supported Framework Layers