tinghuiz / SfMLearner

An unsupervised learning framework for depth and ego-motion estimation from monocular videos
MIT License
1.97k stars 557 forks source link

too manyindices for array in pose test #108

Closed MeNinaa closed 5 years ago

MeNinaa commented 5 years ago

Hi

thank you for sharing your code. I trained the model in pose mode, however now I am getting an error for testing. Can anyone help me with this please? I downloaded the data_odometry_gray.zip file

Best regards Maria

python test_kitti_pose.py --test_seq 9 --dataset_dir /media/maria/0C7ED7537ED733E4/Downloads-/inspiration_code/dataset/ --output_dir /media/maria/0C7ED7537ED733E4/Downloads-/inspiration_code/SfMLearner-master/out --ckpt_file checkpoint/model-185383 WARNING:tensorflow:From /home/maria/.local/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/datasets/base.py:198: retry (from tensorflow.contrib.learn.python.learn.datasets.base) is deprecated and will be removed in a future version. Instructions for updating: Use the retry module or similar alternatives. ('seq_dir', '/media/maria/0C7ED7537ED733E4/Downloads-/inspiration_code/dataset/sequences/09') ('img_dir', '/media/maria/0C7ED7537ED733E4/Downloads-/inspiration_code/dataset/sequences/09/image_2') 2019-01-07 13:10:47.840369: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2019-01-07 13:10:47.913908: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:898] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2019-01-07 13:10:47.914157: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1344] Found device 0 with properties: name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.62 pciBusID: 0000:01:00.0 totalMemory: 10.91GiB freeMemory: 10.35GiB 2019-01-07 13:10:47.914169: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1423] Adding visible gpu devices: 0 2019-01-07 13:10:48.060579: I tensorflow/core/common_runtime/gpu/gpu_device.cc:911] Device interconnect StreamExecutor with strength 1 edge matrix: 2019-01-07 13:10:48.060605: I tensorflow/core/common_runtime/gpu/gpu_device.cc:917] 0 2019-01-07 13:10:48.060609: I tensorflow/core/common_runtime/gpu/gpu_device.cc:930] 0: N 2019-01-07 13:10:48.060770: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1041] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10017 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1) ('mage_seq.shape', (128, 1248)) Traceback (most recent call last): File "test_kitti_pose.py", line 103, in <module> main() File "test_kitti_pose.py", line 93, in main pred = sfm.inference(image_seq[None, :, :, :], sess, mode='pose') IndexError: too many indices for array