Models / resnet-18

ResNet-18

The 18-layer residual network for ImageNet-1k: a 7x7 stem, four stages of two residual blocks, and a linear classifier.

11.7M parametersresnetApache-2.0image-classificationvisionconvolutional

The top 5 classes for one photo, through Linnet and through transformers (eager, fp32).

The input photo
ClassLinnetReference
tabby, tabby cat60.3%60.3%
Egyptian cat30.4%30.4%
tiger cat8.75%8.75%
lynx, catamount0.18%0.18%
tiger, Panthera tigris5.0e-2%5.0e-2%

Both stacks rank the same classes in the same order.