Implementing ResNet with Base Line Accuracy
Implementing ResNet with Base Line Accuracy ResNet Base Line Accuracies https://keras.io/api/applications/ Model Size (MB) Top-1 Accuracy Top-5 Accuracy Parameters Depth Time ( ms ) per inference step (CPU) Time ( ms ) per inference step (GPU) ResNet50 98 0.749 0.921 25,636,712 - 58.20 4.55 ResNet101 171 0.764 0.928 44,707,176 - 89.59 5.19 Results Summary & Comparison (Reasons and the Implementations described below) Model Size (MB) Base Line Top-1 Accuracy Actual Base Line Top 1 Accuracy ResNet50 98 74.9 % 68.084 % ResNet101 171 76.4 % 69.976 % ResNet 50 Validation Test Results Data Set: ImageNet Validation data set (50,000 images) Validation Accuracy (Top1) = 68.084 % with caffe input preprocessing ResNet 101 Validation Test Results Data Set: ImageNet Validation data set (50,000 images) Validation Accuracy (Top1) = 69.976 % with caffe input preprocessing Base Line Setup Deta