1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250
| >>> bash run.sh localhost,localhost WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/horovod/tensorflow/__init__.py:117: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.
WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/horovod/tensorflow/__init__.py:143: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.
logdir = mkdir: missing operand Try 'mkdir --help' for more information. ('Training model: ', 'vgg19') WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/init_ops.py:1251: calling __init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version. Instructions for updating: Call initializer instance with the dtype argument instead of passing it to the constructor WARNING:tensorflow:From tf-keras-dapple.py:159: The name tf.logging.set_verbosity is deprecated. Please use tf.compat.v1.logging.set_verbosity instead.
WARNING:tensorflow:From tf-keras-dapple.py:159: The name tf.logging.DEBUG is deprecated. Please use tf.compat.v1.logging.DEBUG instead.
WARNING:tensorflow:From tf-keras-dapple.py:172: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.
WARNING:tensorflow:From tf-keras-dapple.py:175: The name tf.GPUOptions is deprecated. Please use tf.compat.v1.GPUOptions instead.
['localhost:4000', 'localhost:5000'] WARNING:tensorflow:From /root/source/DAPPLE/vgg19/applications/cluster_utils.py:57: The name tf.train.replica_device_setter is deprecated. Please use tf.compat.v1.train.replica_device_setter instead.
WARNING:tensorflow:From /root/source/DAPPLE/vgg19/applications/cluster_utils.py:80: The name tf.train.Server is deprecated. Please use tf.distribute.Server instead.
2021-06-02 08:21:53.616519: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2021-06-02 08:21:53.623581: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcuda.so.1 2021-06-02 08:21:54.910991: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x5591bba7fb30 executing computations on platform CUDA. Devices: 2021-06-02 08:21:54.911022: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): GeForce GTX 1080 Ti, Compute Capability 6.1 2021-06-02 08:21:54.911028: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (1): GeForce GTX 1080 Ti, Compute Capability 6.1 2021-06-02 08:21:54.936597: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2095155000 Hz 2021-06-02 08:21:54.936705: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x5591bba8d3b0 executing computations on platform Host. Devices: 2021-06-02 08:21:54.936718: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): <undefined>, <undefined> 2021-06-02 08:21:54.939208: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties: name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.582 pciBusID: 0000:03:00.0 2021-06-02 08:21:54.940335: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 1 with properties: name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.582 pciBusID: 0000:04:00.0 2021-06-02 08:21:54.940375: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0 2021-06-02 08:21:54.941705: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0 2021-06-02 08:21:54.942817: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcufft.so.10.0 2021-06-02 08:21:54.943097: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcurand.so.10.0 2021-06-02 08:21:54.944652: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusolver.so.10.0 2021-06-02 08:21:54.945872: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusparse.so.10.0 2021-06-02 08:21:54.950215: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7 2021-06-02 08:21:54.955523: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0, 1 2021-06-02 08:21:54.955562: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0 2021-06-02 08:21:55.338971: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1181] Device interconnect StreamExecutor with strength 1 edge matrix: 2021-06-02 08:21:55.338998: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1187] 0 1 2021-06-02 08:21:55.339005: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 0: N Y 2021-06-02 08:21:55.339009: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 1: Y N 2021-06-02 08:21:55.345703: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:worker/replica:0/task:0/device:GPU:0 with 10452 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:03:00.0, compute capability: 6.1) 2021-06-02 08:21:55.347717: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:worker/replica:0/task:0/device:GPU:1 with 10470 MB memory) -> physical GPU (device: 1, name: GeForce GTX 1080 Ti, pci bus id: 0000:04:00.0, compute capability: 6.1) 2021-06-02 08:21:55.350960: I tensorflow/core/distributed_runtime/rpc/grpc_channel.cc:250] Initialize GrpcChannelCache for job worker -> {0 -> localhost:4000, 1 -> localhost:5000} 2021-06-02 08:21:55.351616: I tensorflow/core/distributed_runtime/rpc/grpc_server_lib.cc:365] Started server with target: grpc://localhost:4000 INFO:tensorflow:TF_CONFIG environment variable: {u'cluster': {u'chief': [u'localhost:4000'], u'worker': [u'localhost:5000']}, u'task': {u'index': 0, u'type': u'chief'}} WARNING:tensorflow:Using temporary folder as model directory: /tmp/tmp5c7pnu INFO:tensorflow:Using config: {'_save_checkpoints_secs': None, '_session_config': gpu_options { allow_growth: true } allow_soft_placement: true , '_keep_checkpoint_max': 5, '_task_type': u'chief', '_global_id_in_cluster': 0, '_is_chief': True, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x7fe074a88a90>, '_model_dir': '/tmp/tmp5c7pnu', '_protocol': None, '_save_checkpoints_steps': None, '_keep_checkpoint_every_n_hours': 10000, '_service': None, '_num_ps_replicas': 0, '_tf_random_seed': None, '_save_summary_steps': 100, '_device_fn': None, '_experimental_distribute': None, '_num_worker_replicas': 2, '_task_id': 0, '_log_step_count_steps': 10, '_experimental_max_worker_delay_secs': None, '_evaluation_master': '', '_eval_distribute': None, '_train_distribute': None, '_master': u'grpc://localhost:4000'} Training starts. WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/tensorflow/python/training/training_util.py:236: initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version. Instructions for updating: Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts. Using Fake IO ((224, 224, 3), (224, 224)) WARNING:tensorflow: The TensorFlow contrib module will not be included in TensorFlow 2.0. For more information, please see: * https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md * https://github.com/tensorflow/addons * https://github.com/tensorflow/io (for I/O related ops) If you depend on functionality not listed there, please file an issue.
WARNING:tensorflow:From tf-keras-dapple.py:73: prefetch_to_device (from tensorflow.contrib.data.python.ops.prefetching_ops) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.data.experimental.prefetch_to_device(...)`. INFO:tensorflow:Calling model_fn.
hvd.local_rank() == 0 ['/job:worker/replica:0/task:0/device:GPU:0', '/job:worker/replica:0/task:1/device:GPU:0']
['/job:worker/replica:0/task:0/device:GPU:0', '/job:worker/replica:0/task:0/device:GPU:1'] 2021-06-02 08:22:00.197197: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties: name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.582 pciBusID: 0000:03:00.0 2021-06-02 08:22:00.198343: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 1 with properties: name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.582 pciBusID: 0000:04:00.0 2021-06-02 08:22:00.198377: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0 2021-06-02 08:22:00.198403: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0 2021-06-02 08:22:00.198416: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcufft.so.10.0 2021-06-02 08:22:00.198429: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcurand.so.10.0 2021-06-02 08:22:00.198441: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusolver.so.10.0 2021-06-02 08:22:00.198453: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusparse.so.10.0 2021-06-02 08:22:00.198466: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7 2021-06-02 08:22:00.202942: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0, 1 2021-06-02 08:22:00.203023: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1181] Device interconnect StreamExecutor with strength 1 edge matrix: 2021-06-02 08:22:00.203032: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1187] 0 1 2021-06-02 08:22:00.203037: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 0: N Y 2021-06-02 08:22:00.203042: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 1: Y N 2021-06-02 08:22:00.206630: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10452 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:03:00.0, compute capability: 6.1) 2021-06-02 08:22:00.207768: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:1 with 10470 MB memory) -> physical GPU (device: 1, name: GeForce GTX 1080 Ti, pci bus id: 0000:04:00.0, compute capability: 6.1) Traceback (most recent call last): File "tf-keras-dapple.py", line 391, in <module> est.train( input_fn = fn_image_preprocess , steps = FLAGS.num_batches) File "/usr/local/lib/python2.7/dist-packages/tensorflow_estimator/python/estimator/estimator.py", line 367, in train loss = self._train_model(input_fn, hooks, saving_listeners) File "/usr/local/lib/python2.7/dist-packages/tensorflow_estimator/python/estimator/estimator.py", line 1158, in _train_model return self._train_model_default(input_fn, hooks, saving_listeners) File "/usr/local/lib/python2.7/dist-packages/tensorflow_estimator/python/estimator/estimator.py", line 1188, in _train_model_default features, labels, ModeKeys.TRAIN, self.config) File "/usr/local/lib/python2.7/dist-packages/tensorflow_estimator/python/estimator/estimator.py", line 1146, in _call_model_fn model_fn_results = self._model_fn(features=features, **kwargs) File "tf-keras-dapple.py", line 254, in model_fn total_loss, outputs = model.build(features, labels) File "/root/source/DAPPLE/vgg19/applications/vgg19_slice_model.py", line 329, in build x = self.block4_conv1[0](x) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 561, in __call__ base_layer_utils.create_keras_history(inputs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/engine/base_layer_utils.py", line 200, in create_keras_history _, created_layers = _create_keras_history_helper(tensors, set(), []) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/engine/base_layer_utils.py", line 244, in _create_keras_history_helper constants[i] = backend.function([], op_input)([]) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/backend.py", line 3253, in __call__ session = get_session(inputs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/backend.py", line 462, in get_session _initialize_variables(session) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/backend.py", line 879, in _initialize_variables [variables_module.is_variable_initialized(v) for v in candidate_vars]) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 950, in run run_metadata_ptr) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1173, in _run feed_dict_tensor, options, run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1350, in _do_run run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1370, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InvalidArgumentError: Cannot assign a device for operation block1_conv1/kernel/Initializer/random_uniform/RandomUniform: Could not satisfy explicit device specification '' because the node node block1_conv1/kernel/Initializer/random_uniform/RandomUniform (defined at /root/source/DAPPLE/vgg19/applications/vgg19_slice_model.py:280) placed on device Device assignments active during op 'block1_conv1/kernel/Initializer/random_uniform/RandomUniform' creation: with tf.device(None): </usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/resource_variable_ops.py:602> with tf.device(/job:worker/replica:0/task:0/device:GPU:0): </root/source/DAPPLE/vgg19/applications/vgg19_slice_model.py:275> with tf.device(None): </usr/local/lib/python2.7/dist-packages/tensorflow_estimator/python/estimator/estimator.py:1174> was colocated with a group of nodes that required incompatible device '/job:worker/replica:0/task:0/device:GPU:0'. All available devices [/job:localhost/replica:0/task:0/device:CPU:0, /job:localhost/replica:0/task:0/device:XLA_GPU:0, /job:localhost/replica:0/task:0/device:XLA_GPU:1, /job:localhost/replica:0/task:0/device:XLA_CPU:0, /job:localhost/replica:0/task:0/device:GPU:0, /job:localhost/replica:0/task:0/device:GPU:1]. Colocation Debug Info: Colocation group had the following types and supported devices: Root Member(assigned_device_name_index_=-1 requested_device_name_='/job:worker/replica:0/task:0/device:GPU:0' assigned_device_name_='' resource_device_name_='/job:worker/replica:0/task:0/device:GPU:0' supported_device_types_=[GPU, CPU, XLA_CPU, XLA_GPU] possible_devices_=[] AssignVariableOp: GPU CPU XLA_CPU XLA_GPU VarIsInitializedOp: GPU CPU XLA_CPU XLA_GPU Mul: GPU CPU XLA_CPU XLA_GPU Add: GPU CPU XLA_CPU XLA_GPU Sub: GPU CPU XLA_CPU XLA_GPU ReadVariableOp: GPU CPU XLA_CPU XLA_GPU RandomUniform: GPU CPU XLA_CPU XLA_GPU VarHandleOp: GPU CPU XLA_CPU XLA_GPU Const: GPU CPU XLA_CPU XLA_GPU
Colocation members, user-requested devices, and framework assigned devices, if any: block1_conv1/kernel/Initializer/random_uniform/shape (Const) block1_conv1/kernel/Initializer/random_uniform/min (Const) block1_conv1/kernel/Initializer/random_uniform/max (Const) block1_conv1/kernel/Initializer/random_uniform/RandomUniform (RandomUniform) block1_conv1/kernel/Initializer/random_uniform/sub (Sub) block1_conv1/kernel/Initializer/random_uniform/mul (Mul) block1_conv1/kernel/Initializer/random_uniform (Add) block1_conv1/kernel (VarHandleOp) /job:worker/replica:0/task:0/device:GPU:0 block1_conv1/kernel/IsInitialized/VarIsInitializedOp (VarIsInitializedOp) /job:worker/replica:0/task:0/device:GPU:0 block1_conv1/kernel/Assign (AssignVariableOp) /job:worker/replica:0/task:0/device:GPU:0 block1_conv1/kernel/Read/ReadVariableOp (ReadVariableOp) /job:worker/replica:0/task:0/device:GPU:0 block1_conv1/Conv2D/ReadVariableOp (ReadVariableOp) /job:worker/replica:0/task:0/device:GPU:0 VarIsInitializedOp_18 (VarIsInitializedOp) /job:worker/replica:0/task:1/device:GPU:0
[[node block1_conv1/kernel/Initializer/random_uniform/RandomUniform (defined at /root/source/DAPPLE/vgg19/applications/vgg19_slice_model.py:280) ]]Additional information about colocations:No node-device colocations were active during op 'block1_conv1/kernel/Initializer/random_uniform/RandomUniform' creation. Device assignments active during op 'block1_conv1/kernel/Initializer/random_uniform/RandomUniform' creation: with tf.device(None): </usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/resource_variable_ops.py:602> with tf.device(/job:worker/replica:0/task:0/device:GPU:0): </root/source/DAPPLE/vgg19/applications/vgg19_slice_model.py:275> with tf.device(None): </usr/local/lib/python2.7/dist-packages/tensorflow_estimator/python/estimator/estimator.py:1174>
Original stack trace for u'block1_conv1/kernel/Initializer/random_uniform/RandomUniform': File "tf-keras-dapple.py", line 391, in <module> est.train( input_fn = fn_image_preprocess , steps = FLAGS.num_batches) File "/usr/local/lib/python2.7/dist-packages/tensorflow_estimator/python/estimator/estimator.py", line 367, in train loss = self._train_model(input_fn, hooks, saving_listeners) File "/usr/local/lib/python2.7/dist-packages/tensorflow_estimator/python/estimator/estimator.py", line 1158, in _train_model return self._train_model_default(input_fn, hooks, saving_listeners) File "/usr/local/lib/python2.7/dist-packages/tensorflow_estimator/python/estimator/estimator.py", line 1188, in _train_model_default features, labels, ModeKeys.TRAIN, self.config) File "/usr/local/lib/python2.7/dist-packages/tensorflow_estimator/python/estimator/estimator.py", line 1146, in _call_model_fn model_fn_results = self._model_fn(features=features, **kwargs) File "tf-keras-dapple.py", line 254, in model_fn total_loss, outputs = model.build(features, labels) File "/root/source/DAPPLE/vgg19/applications/vgg19_slice_model.py", line 280, in build x = self.block1_conv1[i](img_input) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 591, in __call__ self._maybe_build(inputs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 1881, in _maybe_build self.build(input_shapes) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/layers/convolutional.py", line 165, in build dtype=self.dtype) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 384, in add_weight aggregation=aggregation) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/tracking/base.py", line 663, in _add_variable_with_custom_getter **kwargs_for_getter) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/engine/base_layer_utils.py", line 155, in make_variable shape=variable_shape if variable_shape.rank else None) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 259, in __call__ return cls._variable_v1_call(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 220, in _variable_v1_call shape=shape) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 198, in <lambda> previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 2495, in default_variable_creator shape=shape) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 263, in __call__ return super(VariableMetaclass, cls).__call__(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/resource_variable_ops.py", line 460, in __init__ shape=shape) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/resource_variable_ops.py", line 604, in _init_from_args initial_value() if init_from_fn else initial_value, File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/keras/engine/base_layer_utils.py", line 135, in <lambda> init_val = lambda: initializer(shape, dtype=dtype) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/init_ops.py", line 533, in __call__ shape, -limit, limit, dtype, seed=self.seed) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/random_ops.py", line 247, in random_uniform rnd = gen_random_ops.random_uniform(shape, dtype, seed=seed1, seed2=seed2) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_random_ops.py", line 820, in random_uniform name=name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper op_def=op_def) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/util/deprecation.py", line 507, in new_func return func(*args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 3616, in create_op op_def=op_def) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2005, in __init__ self._traceback = tf_stack.extract_stack()
-------------------------------------------------------------------------- Primary job terminated normally, but 1 process returned a non-zero exit code. Per user-direction, the job has been aborted. -------------------------------------------------------------------------- -------------------------------------------------------------------------- mpirun detected that one or more processes exited with non-zero status, thus causing the job to be terminated. The first process to do so was:
Process name: [[63853,1],0] Exit code: 1 --------------------------------------------------------------------------
|