search

hellochick / ICNet-tensorflow

TensorFlow-based implementation of "ICNet for Real-Time Semantic Segmentation on High-Resolution Images".
405 stars 153 forks source link

Error while train on cityscape dataset #55

Closed SoebHussain closed 6 years ago

SoebHussain commented 6 years ago

Hi,

I tried to run train.py to train the model on cityscapes dataset. Could you please help me rectify this issue ?

python train.py --train-beta-gamma 2018-03-28 13:36:47.131437: 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 2018-03-28 13:36:47.253316: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had nega tive value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2018-03-28 13:36:47.253751: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties: name: Tesla K80 major: 3 minor: 7 memoryClockRate(GHz): 0.8235 pciBusID: 0000:00:04.0 totalMemory: 11.17GiB freeMemory: 11.09GiB 2018-03-28 13:36:47.329395: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had nega tive value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2018-03-28 13:36:47.329761: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 1 with properties: name: Tesla K80 major: 3 minor: 7 memoryClockRate(GHz): 0.8235 pciBusID: 0000:00:05.0 totalMemory: 11.17GiB freeMemory: 11.10GiB 2018-03-28 13:36:47.329816: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1045] Device peer to peer matrix 2018-03-28 13:36:47.329850: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1051] DMA: 0 1 2018-03-28 13:36:47.329863: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1061] 0: Y N 2018-03-28 13:36:47.329868: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1061] 1: N Y 2018-03-28 13:36:47.329878: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (d evice: 0, name: Tesla K80, pci bus id: 0000:00:04.0, compute capability: 3.7) 2018-03-28 13:36:47.329886: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:1) -> (d evice: 1, name: Tesla K80, pci bus id: 0000:00:05.0, compute capability: 3.7) Restore from pre-trained model... Traceback (most recent call last): File "train.py", line 211, in main() File "train.py", line 189, in main net.load(args.restore_from, sess) File "/home/soebans15/ICNet-tensorflow/network.py", line 77, in load var = tf.get_variable(param_name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 1203, in get_variable constraint=constraint) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 1092, in get_variable constraint=constraint) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 425, in get_variable constraint=constraint) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 394, in _true_getter use_resource=use_resource, constraint=constraint) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 760, in _get_single_variable "reuse=tf.AUTO_REUSE in VarScope?" % name) ValueError: Variable conv1_1_3x3_s2/biases does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=tf.AU TO_REUSE in VarScope?