I'm new to mxnet,I have confusion about getresnet()
`def getResNet(num_classes, ctx, NoTraining=True):
resnet = vision.resnet101_v1(pretrained=True, ctx=ctx)
net = vision.resnet101_v1(classes=num_classes, prefix='resnetv10_')
with net.name_scope():
net.output = nn.Dense(num_classes, flatten=True, in_units=resnet.output._in_units)
net.output.collect_params().initialize(
mx.init.Xavier(rnd_type='gaussian', factor_type="in", magnitude=2), ctx=ctx)
net.features = resnet.features
net.collect_params().reset_ctx(ctx)`
why is there have two vision.resnet101_v1() ,resnet and net ?
I'm new to mxnet,I have confusion about getresnet() `def getResNet(num_classes, ctx, NoTraining=True): resnet = vision.resnet101_v1(pretrained=True, ctx=ctx)
why is there have two vision.resnet101_v1() ,resnet and net ?