search

mks0601 / TF-SimpleHumanPose

TensorFlow implementation of "Simple Baselines for Human Pose Estimation and Tracking", ECCV 2018
335 stars 90 forks source link

resnet50？？？ #49

Closed henbucuoshanghai closed 4 years ago

henbucuoshanghai commented 4 years ago

blocks = [ resnet_utils.Block('block1', bottleneck, [(256, 64, 1)] 2 + [(256, 64, 1)]), resnet_utils.Block('block2', bottleneck, [(512, 128, 2)] + [(512, 128, 1)] 3), resnet_utils.Block('block3', bottleneck, [(1024, 256, 2)] + [(1024, 256, 1)] 5), resnet_utils.Block('block4', bottleneck, [(2048, 512, 2)] + [(2048, 512, 1)] 2) ]

blocks means resnet50？？？ but why compute net1234？？？ resnet_features = [net, net2, net3, net4] return resnet_features

it means？？？

mks0601 commented 4 years ago
Screen Shot 2019-09-25 at 7 18 48 AM
mks0601 commented 4 years ago

What are those question marks? I cannot understand your question.

henbucuoshanghai commented 4 years ago

blocks means resnet50？？？ but why compute [net, net2, net3, net4]？？？

mks0601 commented 4 years ago

I cannot understand your question. That is just pytorch official resnet code.

henbucuoshanghai commented 4 years ago

pytorch official resnet code? tensorflow??

mks0601 commented 4 years ago

Sorry, tensorflow

henbucuoshanghai commented 4 years ago

official resnet code. resnet v1? but the official code is bad to understand,too complex to understand..