jiangwei221
commented
5 years ago Did you try to use the docker image? The docker image should provide the complete run time enviroment, just tried on my PC, and it works. This repo requires an old version of tensorflow, tensorflow-gpu==1.4.0, I doubt this is the issue. here is my running log from docker:
(base) root@cbff9cb4a1d3:/home# python run_lfnet.py --in=./sacre_coeur/release/outdoor_examples/images/sacre_coeur/dense/images --out=./test
/opt/conda/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: compiletime version 3.5 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.6
return f(*args, **kwds)
Act-Fn: <function get_activation_fn.<locals>.<lambda> at 0x7f3e74a5e950>
Apply instance norm on input photos
Scales (0.707107~1.41 #5): [1.41421356 1.18920712 1. 0.84089642 0.70710678]
PAD=16, #conv=8, ksize=5 ori-ksize=5
Act-Fn: <function relu at 0x7f3e89cc16a8>
===== SimpleDesc (reuse=False) =====
#1 conv-bn-act (?, 16, 16, 64)
#2 conv-bn-act (?, 8, 8, 128)
#3 conv-bn-act (?, 4, 4, 256)
FLAT (?, 4096)
Feat-Norm: L2-NORM
FEAT (?, 256)
2019-07-17 22:41:50.073841: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-07-17 22:41:50.192150: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-07-17 22:41:50.192576: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.582
pciBusID: 0000:01:00.0
totalMemory: 10.91GiB freeMemory: 7.44GiB
2019-07-17 22:41:50.283076: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-07-17 22:41:50.283506: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 1 with properties:
name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.582
pciBusID: 0000:02:00.0
totalMemory: 10.92GiB freeMemory: 10.76GiB
2019-07-17 22:41:50.284422: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Device peer to peer matrix
2019-07-17 22:41:50.284447: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1051] DMA: 0 1
2019-07-17 22:41:50.284455: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1061] 0: Y Y
2019-07-17 22:41:50.284460: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1061] 1: Y Y
2019-07-17 22:41:50.284468: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1)
2019-07-17 22:41:50.284475: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:1) -> (device: 1, name: GeForce GTX 1080 Ti, pci bus id: 0000:02:00.0, compute capability: 6.1)
Load trained models...
Checkpoint models-latest-42000
[Wed Jul 17 22:41:50 2019] Resuming...
Done.
Found 1179 images...
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1179/1179 [03:07<00:00, 6.37it/s]
Done.
(base) root@cbff9cb4a1d3:/home# 
UCRajkumar
When I ran
run_lfnet.pyas specified in the github, I produce this following error:Everything seems to be starting to run correctly as the code finds all the images and makes progress 2% of the way. However, it abruptly stops with that following error. The dataset is the sacre_coeur dataset downloaded as is and no modifications have been made to it.