第一步：運行demo.py
https://blog.csdn.net/zxcqlf/article/details/88736889
bug1:
(base) parallels@parallels-Parallels-Virtual-Platform:~/DPWorkspace/SfMLearner-master$ bash ./models/download_depth_model.sh
WARNING: timestamping does nothing in combination with -O. See the manual
for details.
–2019-05-06 15:10:19-- http://people.eecs.berkeley.edu/~tinghuiz/projects/SfMLearner/models/kitti_depth_model.tar
Resolving people.eecs.berkeley.edu (people.eecs.berkeley.edu)… 128.32.189.73
Connecting to people.eecs.berkeley.edu (people.eecs.berkeley.edu)|128.32.189.73|:80… connected.
HTTP request sent, awaiting response… 200 OK
Length: 139591680 (133M) [application/x-tar]
Saving to: ‘./models/kitti_depth_model.tar’
./models/kitti_dept 100%[===================>] 133.12M 376KB/s in 12m 18s
2019-05-06 15:22:37 (185 KB/s) - ‘
./models/kitti_depth_model.tar’ saved [139591680/139591680]
model-190532.data-00000-of-00001
model-190532.index
bug2:
runfile('/home/parallels/DPWorkspace/SfMLearner-master/demo.py', wdir='/home/parallels/DPWorkspace/SfMLearner-master')
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
解決方法：
https://blog.csdn.net/zhaohaibo_/article/details/80573676