CaffeNet 1.2

CaffeNet a variant of AlexNet. AlexNet is the name of a convolutional neural network for classification, which competed in the ImageNet Large Scale Visual Recognition Challenge in 2012. **Differences:** * not training with the relighting data-augmentation; * the order of pooling and normalization layers is switched (in CaffeNet, pooling is done before normalization). **Object categories for classification** [Class ID][4] **Paper** [ImageNet Classification with Deep Convolutional Neural Networks][1] **Dataset** [ILSVRC2012][2] **Source** Caffe BVLC CaffeNet ==> Caffe2 CaffeNet ==> ONNX CaffeNet **Model input and output** **Input** data_0: float[1, 3, 224, 224] **Output** * prob_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 model is snapshot of iteration 310,000. The best validation performance during training was iteration 313,000 with validation accuracy 57.412% and loss 1.82328. This model obtains a top-1 accuracy 57.4% and a top-5 accuracy 80.4% 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 still.) **Model size: 244 MB** **License** [BSD-3][3] [1]: https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf [2]: http://www.image-net.org/challenges/LSVRC/2012/ [3]: https://github.com/onnx/models/blob/master/bvlc_reference_caffenet/LICENSE [4]:https://contentmamluswest001.blob.core.windows.net/content/14b2744cf8d6418c87ffddc3f3127242/9502630827244d60a1214f250e3bbca7/938a67b527b94dbf96a28510ff43f1a0/synsets.txt