Models / resnet-50

ResNet-50

The 50-layer residual network (v1.5) for ImageNet-1k: a 7x7 stem, four stages of bottleneck blocks 3, 4, 6, and 3 deep, and a linear classifier.

25.6M parametersresnetApache-2.0image-classificationvisionconvolutional

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

The input photo
ClassLinnetReference
tiger cat94.1%94.1%
tabby, tabby cat3.44%3.44%
remote control, remote0.16%0.16%
Egyptian cat0.14%0.14%
jinrikisha, ricksha, rickshaw7.9e-2%7.9e-2%

Both stacks rank the same classes in the same order.