Onnx Emitter has not supported operator [MatMul] [Shape] [Square] [Sum] [Maximum] [Rsqrt]

[zhou-zhiyuan]

Platform (like ubuntu 16.04):

Python version:

Source framework with version ( Tensorflow 1.4.0):

Destination framework with version (like onnx 1.7.0):

Pre-trained model path (model_squeezenet.pb):

Running scripts: mmconvert -sf tensorflow -iw model_squeezenet.pb --inNodeName input --inputShape 160,160,3 --dstNodeName embeddings -df onnx -om model_squeezenet.onnx

log:

---

OnnxEmitter has not supported operator [MatMul]. squeezenet/Bottleneck/MatMul OnnxEmitter has not supported operator [Shape]. squeezenet/Bottleneck/BatchNorm/Shape OnnxEmitter has not supported operator [Square]. embeddings/Square OnnxEmitter has not supported operator [Sum]. embeddings/Sum OnnxEmitter has not supported operator [Maximum]. embeddings/Maximum OnnxEmitter has not supported operator [Rsqrt]. embeddings/Rsqrt

---

[wangxudong-cq]

any update,i have the same issue:

OnnxEmitter has not supported operator [ConvTranspose].
upscore2
OnnxEmitter has not supported operator [Crop].
score_pool4c
OnnxEmitter has not supported operator [ConvTranspose].
upscore_pool4
OnnxEmitter has not supported operator [Crop].
score_pool3c
OnnxEmitter has not supported operator [ConvTranspose].
upscore8
OnnxEmitter has not supported operator [Crop].
score