BLVC Googlenet
A deep convolutional neural network architecture codenamed "Inception", responsible for improving the classification and detection in the ImageNet Challenge in 2014. The hallmark of this architecture is the improved utilization of the computing resources inside the network.
**Description**
GoogLeNet is the name of a convolutional neural network for classification, which competed in the ImageNet Large Scale Visual Recognition Challenge in 2014.
**Differences:**
* not training with the relighting data-augmentation;
* not training with the scale or aspect-ratio data-augmentation;
* uses "xavier" to initialize the weights instead of "gaussian";
**Object categories for classification**
[Class ID][3]
**Paper**
[Going deeper with convolutions][1]
**Dataset**
[ILSVRC2014][2]
**Source**
Caffe BVLC GoogLeNet ==> Caffe2 GoogLeNet ==> ONNX GoogLeNet
**Model input and output**
**Input**
data_0: float[1, 3, 224, 224]
**Output**
softmaxout_1: float[1, 1000]
**Pre-processing steps**
**Post-processing steps**
**Sample test data**
random generated sampe test data:
* test_data_set_0
* test_data_set_1
* test_data_set_2
* test_data_set_3
* test_data_set_4
* test_data_set_5
**Results/accuracy on test set**
This bundled model obtains a top-1 accuracy 68.7% (31.3% error) and a top-5 accuracy 88.9% (11.1% error) on the validation set, using just the center crop. (Using the average of 10 crops, (4 + 1 center) * 2 mirror, should obtain a bit higher accuracy.)
**Model size: 28 MB**
**License**
[BSD-3][4]
[1]: https://arxiv.org/pdf/1409.4842.pdf
[2]: http://www.image-net.org/challenges/LSVRC/2014/
[3]:https://contentmamluswest001.blob.core.windows.net/content/14b2744cf8d6418c87ffddc3f3127242/9502630827244d60a1214f250e3bbca7/76551ba59649440f9baa5a6dc01ab8db/synsets.txt
[4]: https://github.com/onnx/models/blob/master/bvlc_googlenet/LICENSE
