ResNet 50 - AshokBhat/ml GitHub Wiki
About
- 50-layer ResNet
- Trained on more than a million images from the ImageNet database
- Achieved a top-5 error rate of 3.57% in 2015 which beats human-level performance on ImageNet dataset
Characteristics
- Depth - 50 layers
- Input size -
224
x224
- Can classify images into 1000 object categories, such as a keyboard, mouse, pencil, and many animals
Accuracy
- Top-1 Accuracy: 75.8%
- Top-5 Accuracy: 92.9%
Performance
Example code
Graph
See also
- [AlexNet]] ](/AshokBhat/ml/wiki/[VGG) | [ResNet]]
- [MobileNet]] ](/AshokBhat/ml/wiki/[[DenseNet) | ResNeXt