Download:
- release 1.1: https://s3.amazonaws.com/download.onnx/models/opset_3/squeezenet.tar.gz
- release 1.1.2: https://s3.amazonaws.com/download.onnx/models/opset_6/squeezenet.tar.gz
- release 1.2: https://s3.amazonaws.com/download.onnx/models/opset_7/squeezenet.tar.gz
- release 1.3: https://s3.amazonaws.com/download.onnx/models/opset_8/squeezenet.tar.gz
- master: https://s3.amazonaws.com/download.onnx/models/opset_9/squeezenet.tar.gz
Model size: 5 MB
SqueezeNet is a light-weight convolutional networks for classification.
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Caffe2 SqueezeNet ==> ONNX SqueezeNet
Run SqueezeNet in browser - implemented by ONNX.js with SqueezeNet release 1.2
data_0: float[1, 3, 224, 224]
softmaxout_1: float[1, 1000, 1, 1]
random generated sampe test data:
- test_data_set_0
- test_data_set_1
- test_data_set_2
MIT