You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, thank you very much for this nice work.
I'm trying to train a model using the 3DMatch dataset, but after a while, I'm getting the following error:
[1059 530 38 ... 631 144 924]
Validation : 0.0% (timings : 58.95 0.00)
2022-02-07 16:05:30.380600: E tensorflow/stream_executor/dnn.cc:613] CUDNN_STATUS_NOT_SUPPORTED
in tensorflow/stream_executor/cuda/cuda_dnn.cc(3935): 'cudnnBatchNormalizationForwardInference( cudnn.handle(), mode, &one, &zero, x_descriptor.handle(), x.opaque(), x_descriptor.handle(), y->opaque(), scale_offset_descriptor.handle(), scale.opaque(), offset.opaque(), estimated_mean.opaque(), maybe_inv_var, epsilon)'
Traceback (most recent call last):
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1365, in _do_call
return fn(*args)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1350, in _run_fn
target_list, run_metadata)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1443, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.OutOfRangeError: 2 root error(s) found.
(0) Out of range: End of sequence
[[{{node IteratorGetNext}}]]
(1) Out of range: End of sequence
[[{{node IteratorGetNext}}]]
[[optimizer/gradients/KernelPointNetwork/Sum_1_grad/Fill/value/_571]]
0 successful operations.
0 derived errors ignored.
Original stack trace for 'IteratorGetNext':
File "training_3DMatch.py", line 175, in <module>
dataset.init_input_pipeline(config)
File "/home/rambo/ws_benji/D3Feat/datasets/common.py", line 770, in init_input_pipeline
self.flat_inputs = iter.get_next()
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/data/ops/iterator_ops.py", line 429, in get_next
name=name)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/ops/gen_dataset_ops.py", line 2518, in iterator_get_next
output_shapes=output_shapes, name=name)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/framework/op_def_library.py", line 794, in _apply_op_helper
op_def=op_def)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/util/deprecation.py", line 513, in new_func
return func(*args, **kwargs)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py", line 3357, in create_op
attrs, op_def, compute_device)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py", line 3426, in _create_op_internal
op_def=op_def)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py", line 1748, in __init__
self._traceback = tf_stack.extract_stack()
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1365, in _do_call
return fn(*args)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1350, in _run_fn
target_list, run_metadata)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1443, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.InternalError: 2 root error(s) found.
(0) Internal: cuDNN launch failure : input shape ([68418,64,1,1])
[[{{node KernelPointNetwork/layer_0/simple_0/batch_normalization/cond/FusedBatchNormV3_1}}]]
[[loss/cdist/Sqrt/_1141]]
(1) Internal: cuDNN launch failure : input shape ([68418,64,1,1])
[[{{node KernelPointNetwork/layer_0/simple_0/batch_normalization/cond/FusedBatchNormV3_1}}]]
0 successful operations.
0 derived errors ignored.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "training_3DMatch.py", line 207, in <module>
trainer.train(model, dataset)
File "/home/rambo/ws_benji/D3Feat/utils/trainer.py", line 387, in train
self.validation(model, dataset)
File "/home/rambo/ws_benji/D3Feat/utils/trainer.py", line 441, in validation
desc_loss, det_loss, accuracy, ave_d_pos, ave_d_neg, dists, scores, anc_key, pos_key = self.sess.run(ops, {model.dropout_prob: 1.0})
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 956, in run
run_metadata_ptr)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1180, in _run
feed_dict_tensor, options, run_metadata)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1359, in _do_run
run_metadata)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/client/session.py", line 1384, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InternalError: 2 root error(s) found.
(0) Internal: cuDNN launch failure : input shape ([68418,64,1,1])
[[node KernelPointNetwork/layer_0/simple_0/batch_normalization/cond/FusedBatchNormV3_1 (defined at /home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py:1748) ]]
[[loss/cdist/Sqrt/_1141]]
(1) Internal: cuDNN launch failure : input shape ([68418,64,1,1])
[[node KernelPointNetwork/layer_0/simple_0/batch_normalization/cond/FusedBatchNormV3_1 (defined at /home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py:1748) ]]
0 successful operations.
0 derived errors ignored.
Original stack trace for 'KernelPointNetwork/layer_0/simple_0/batch_normalization/cond/FusedBatchNormV3_1':
File "training_3DMatch.py", line 189, in <module>
model = KernelPointFCNN(dataset.flat_inputs, config)
File "/home/rambo/ws_benji/D3Feat/models/KPFCNN_model.py", line 130, in __init__
self.out_features, self.out_scores = assemble_FCNN_blocks(self.anchor_inputs, self.config, self.dropout_prob)
File "/home/rambo/ws_benji/D3Feat/models/D3Feat.py", line 15, in assemble_FCNN_blocks
F = assemble_CNN_blocks(inputs, config, dropout_prob)
File "/home/rambo/ws_benji/D3Feat/models/network_blocks.py", line 1099, in assemble_CNN_blocks
training)
File "/home/rambo/ws_benji/D3Feat/models/network_blocks.py", line 242, in simple_block
training))
File "/home/rambo/ws_benji/D3Feat/models/network_blocks.py", line 160, in batch_norm
training=training)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/util/deprecation.py", line 330, in new_func
return func(*args, **kwargs)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/layers/normalization.py", line 327, in batch_normalization
return layer.apply(inputs, training=training)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/util/deprecation.py", line 330, in new_func
return func(*args, **kwargs)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 1700, in apply
return self.__call__(inputs, *args, **kwargs)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/layers/base.py", line 548, in __call__
outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 854, in __call__
outputs = call_fn(cast_inputs, *args, **kwargs)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/autograph/impl/api.py", line 234, in wrapper
return converted_call(f, options, args, kwargs)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/autograph/impl/api.py", line 439, in converted_call
return _call_unconverted(f, args, kwargs, options)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/autograph/impl/api.py", line 330, in _call_unconverted
return f(*args, **kwargs)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/layers/normalization.py", line 167, in call
return super(BatchNormalization, self).call(inputs, training=training)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/keras/layers/normalization.py", line 710, in call
outputs = self._fused_batch_norm(inputs, training=training)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/keras/layers/normalization.py", line 565, in _fused_batch_norm
training, _fused_batch_norm_training, _fused_batch_norm_inference)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/keras/utils/tf_utils.py", line 59, in smart_cond
pred, true_fn=true_fn, false_fn=false_fn, name=name)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/framework/smart_cond.py", line 59, in smart_cond
name=name)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/util/deprecation.py", line 513, in new_func
return func(*args, **kwargs)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/ops/control_flow_ops.py", line 1235, in cond
orig_res_f, res_f = context_f.BuildCondBranch(false_fn)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/ops/control_flow_ops.py", line 1061, in BuildCondBranch
original_result = fn()
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/keras/layers/normalization.py", line 562, in _fused_batch_norm_inference
data_format=data_format)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/ops/nn_impl.py", line 1502, in fused_batch_norm
name=name)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/ops/gen_nn_ops.py", line 4620, in fused_batch_norm_v3
name=name)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/framework/op_def_library.py", line 794, in _apply_op_helper
op_def=op_def)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/util/deprecation.py", line 513, in new_func
return func(*args, **kwargs)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py", line 3357, in create_op
attrs, op_def, compute_device)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py", line 3426, in _create_op_internal
op_def=op_def)
File "/home/rambo/anaconda3/envs/tf_n1.15/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py", line 1748, in __init__
self._traceback = tf_stack.extract_stack()
2022-02-07 16:05:32.189426: W tensorflow/core/kernels/data/generator_dataset_op.cc:103] Error occurred when finalizing GeneratorDataset iterator: Failed precondition: Python interpreter state is not initialized. The process may be terminated.
The error comes from this section of code:
Do you have any idea why is this happening?
Thanks a lot,
Benjamin
The text was updated successfully, but these errors were encountered:
Hello, thank you very much for this nice work.
I'm trying to train a model using the 3DMatch dataset, but after a while, I'm getting the following error:
The error comes from this section of code:
Do you have any idea why is this happening?
Thanks a lot,
Benjamin
The text was updated successfully, but these errors were encountered: