ResNet 各个版本 tensorflow下载:
下载链接:https://github.com/keras-team/keras-applications/releases/tag/resnet
resnet101v2_weights_tf_dim_ordering_tf_kernels.h5 171 MB
resnet101v2_weights_tf_dim_ordering_tf_kernels_notop.h5 163 MB
resnet101_weights_tf_dim_ordering_tf_kernels.h5 171 MB
resnet101_weights_tf_dim_ordering_tf_kernels_notop.h5 164 MB
resnet152v2_weights_tf_dim_ordering_tf_kernels.h5 232 MB
resnet152v2_weights_tf_dim_ordering_tf_kernels_notop.h5 224 MB
resnet152_weights_tf_dim_ordering_tf_kernels.h5 232 MB
resnet152_weights_tf_dim_ordering_tf_kernels_notop.h5 224 MB
resnet50v2_weights_tf_dim_ordering_tf_kernels.h5 98.1 MB
resnet50v2_weights_tf_dim_ordering_tf_kernels_notop.h5 90.3 MB
resnet50_weights_tf_dim_ordering_tf_kernels.h5 98.2 MB
resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5 90.4 MB
resnext101_weights_tf_dim_ordering_tf_kernels.h5 170 MB
resnext101_weights_tf_dim_ordering_tf_kernels_notop.h5 162 MB
resnext50_weights_tf_dim_ordering_tf_kernels.h5 96.2 MB
resnext50_weights_tf_dim_ordering_tf_kernels_notop.h5 88.4 MB
notop模型是指什么?
是否包含最后的3个全连接层(whether to include the 3 fully-connected layers at the top of the network)。用来做fine-tuning专用,专门开源了这类模型。