run_classifier.py Error COLA
zzj0402 opened this issue · 2 comments
zzj0402 commented
Running the cola script returns:
2020-01-15 17:53:21.504699: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:163] no NVIDIA GPU device is present: /dev/nvidia0 does not exist
2020-01-15 17:53:21.505194: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 AVX512F FMA
2020-01-15 17:53:21.518577: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 3599910000 Hz
2020-01-15 17:53:21.519665: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3c2f130 executing computations on platform Host. Devices:
2020-01-15 17:53:21.519701: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): Host, Default Version
Traceback (most recent call last):
File "run_classifer.py", line 457, in <module>
app.run(main)
File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 299, in run
_run_main(main, args)
File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 250, in _run_main
sys.exit(main(argv))
File "run_classifer.py", line 307, in main
loss_multiplier=loss_multiplier)
File "run_classifer.py", line 195, in get_model
pooled_output, _ = albert_layer(input_word_ids, input_mask, input_type_ids)
File "/root/ALBERT-TF2.0/albert.py", line 212, in __call__
return super(AlbertModel, self).__call__(inputs, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/base_layer.py", line 842, in __call__
outputs = call_fn(cast_inputs, *args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/autograph/impl/api.py", line 237, in wrapper
raise e.ag_error_metadata.to_exception(e)
RuntimeError: in converted code:
/root/ALBERT-TF2.0/albert.py:229 call *
word_embeddings = self.embedding_lookup(input_word_ids)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/base_layer.py:817 __call__
self._maybe_build(inputs)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/base_layer.py:2141 _maybe_build
self.build(input_shapes)
/root/ALBERT-TF2.0/albert.py:273 build
dtype=self.dtype)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/base_layer.py:522 add_weight
aggregation=aggregation)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/training/tracking/base.py:744 _add_variable_with_custom_getter
**kwargs_for_getter)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/base_layer_utils.py:139 make_variable
shape=variable_shape if variable_shape else None)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/variables.py:258 __call__
return cls._variable_v1_call(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/variables.py:219 _variable_v1_call
shape=shape)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/variables.py:65 getter
return captured_getter(captured_previous, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/distribute/distribute_lib.py:1322 creator_with_resource_vars
return self._create_variable(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/distribute/one_device_strategy.py:262 _create_variable
return next_creator(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/variables.py:197 <lambda>
previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/variable_scope.py:2507 default_variable_creator
shape=shape)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/variables.py:262 __call__
return super(VariableMetaclass, cls).__call__(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/resource_variable_ops.py:1406 __init__
distribute_strategy=distribute_strategy)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/resource_variable_ops.py:1537 _init_from_args
initial_value() if init_from_fn else initial_value,
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/base_layer_utils.py:119 <lambda>
init_val = lambda: initializer(shape, dtype=dtype)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/init_ops_v2.py:343 __call__
self.stddev, dtype)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/init_ops_v2.py:809 truncated_normal
shape=shape, mean=mean, stddev=stddev, dtype=dtype, seed=self.seed)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/random_ops.py:171 truncated_normal
mean_tensor = ops.convert_to_tensor(mean, dtype=dtype, name="mean")
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py:1184 convert_to_tensor
return convert_to_tensor_v2(value, dtype, preferred_dtype, name)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py:1242 convert_to_tensor_v2
as_ref=False)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py:1296 internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/tensor_conversion_registry.py:52 _default_conversion_function
return constant_op.constant(value, dtype, name=name)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/constant_op.py:227 constant
allow_broadcast=True)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/constant_op.py:235 _constant_impl
t = convert_to_eager_tensor(value, ctx, dtype)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/constant_op.py:96 convert_to_eager_tensor
return ops.EagerTensor(value, ctx.device_name, dtype)
RuntimeError: /job:localhost/replica:0/task:0/device:GPU:0 unknown device.
suresh96458 commented
Bidek56 commented
Are you are trying run on a GPU but you don't have one or it's not configured?
Please try using a Docker file docker pull tensorflow/tensorflow:latest-gpu-py3 to ensure your GPU is configured if you have one.