Caught a NaN error : 3

[yolic66]

EPOCH 0 Caught a NaN error : 3 Graph execution error:

Detected at node 'loss/mul' defined at (most recent call last): File "c:\Users\dell\Desktop\RandLA-Net-master\main_Semantic3D.py", line 324, in model = Network(dataset, cfg) File "c:\Users\dell\Desktop\RandLA-Net-master\RandLANet.py", line 80, in init self.loss = self.get_loss(valid_logits, valid_labels, self.class_weights) File "c:\Users\dell\Desktop\RandLA-Net-master\RandLANet.py", line 266, in get_loss weights = tf.reduce_sum(class_weights * one_hot_labels, axis=1) Node: 'loss/mul' Detected at node 'loss/mul' defined at (most recent call last): File "c:\Users\dell\Desktop\RandLA-Net-master\main_Semantic3D.py", line 324, in model = Network(dataset, cfg) File "c:\Users\dell\Desktop\RandLA-Net-master\RandLANet.py", line 80, in init self.loss = self.get_loss(valid_logits, valid_labels, self.class_weights) File "c:\Users\dell\Desktop\RandLA-Net-master\RandLANet.py", line 266, in get_loss weights = tf.reduce_sum(class_weights * one_hot_labels, axis=1) Node: 'loss/mul' 2 root error(s) found. (0) INVALID_ARGUMENT: required broadcastable shapes [[{{node loss/mul}}]] [[optimizer/gradients/layers/Encoder_layer_0LFAmlp1/Conv2D_grad/Conv2DBackpropFilter/_1021]] (1) INVALID_ARGUMENT: required broadcastable shapes [[{{node loss/mul}}]] 0 successful operations. 0 derived errors ignored. name: "loss/mul" op: "Mul" input: "loss/Const" input: "loss/one_hot" attr { key: "T" value { type: DT_FLOAT } }

loss/mul ['loss/Const:0', 'loss/one_hot:0'] ['loss/mul:0'] Traceback (most recent call last): File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\client\session.py", line 1377, in _do_call return fn(*args) File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\client\session.py", line 1360, in _run_fn return self._call_tf_sessionrun(options, feed_dict, fetch_list, File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\client\session.py", line 1453, in _call_tf_sessionrun return tf_session.TF_SessionRun_wrapper(self._session, options, feed_dict, tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found. (0) INVALID_ARGUMENT: required broadcastable shapes [[{{node loss/mul}}]] [[optimizer/gradients/layers/Encoder_layer_0LFAmlp1/Conv2D_grad/Conv2DBackpropFilter/_1021]] (1) INVALID_ARGUMENT: required broadcastable shapes [[{{node loss/mul}}]] 0 successful operations. 0 derived errors ignored.

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "c:\Users\dell\Desktop\RandLA-Net-master\RandLANet.py", line 162, in train _, _, summary, l_out, probs, labels, acc = self.sess.run(ops, {self.is_training: True}) File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\client\session.py", line 967, in run result = self._run(None, fetches, feed_dict, options_ptr, File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\client\session.py", line 1190, in _run results = self._do_run(handle, final_targets, final_fetches, File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\client\session.py", line 1370, in _do_run return self._do_call(_run_fn, feeds, fetches, targets, options, File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\client\session.py", line 1396, in _do_call raise type(e)(node_def, op, message) # pylint: disable=no-value-for-parameter tensorflow.python.framework.errors_impl.InvalidArgumentError: Graph execution error:

Detected at node 'loss/mul' defined at (most recent call last): File "c:\Users\dell\Desktop\RandLA-Net-master\main_Semantic3D.py", line 324, in model = Network(dataset, cfg) File "c:\Users\dell\Desktop\RandLA-Net-master\RandLANet.py", line 80, in init self.loss = self.get_loss(valid_logits, valid_labels, self.class_weights) File "c:\Users\dell\Desktop\RandLA-Net-master\RandLANet.py", line 266, in get_loss weights = tf.reduce_sum(class_weights * one_hot_labels, axis=1) Node: 'loss/mul' Detected at node 'loss/mul' defined at (most recent call last): File "c:\Users\dell\Desktop\RandLA-Net-master\main_Semantic3D.py", line 324, in model = Network(dataset, cfg) File "c:\Users\dell\Desktop\RandLA-Net-master\RandLANet.py", line 80, in init self.loss = self.get_loss(valid_logits, valid_labels, self.class_weights) File "c:\Users\dell\Desktop\RandLA-Net-master\RandLANet.py", line 266, in get_loss weights = tf.reduce_sum(class_weights * one_hot_labels, axis=1) Node: 'loss/mul' 2 root error(s) found. (0) INVALID_ARGUMENT: required broadcastable shapes [[{{node loss/mul}}]] [[optimizer/gradients/layers/Encoder_layer_0LFAmlp1/Conv2D_grad/Conv2DBackpropFilter/_1021]] (1) INVALID_ARGUMENT: required broadcastable shapes [[{{node loss/mul}}]] 0 successful operations. 0 derived errors ignored.

Original stack trace for 'loss/mul': File "c:\Users\dell\Desktop\RandLA-Net-master\main_Semantic3D.py", line 324, in model = Network(dataset, cfg) File "c:\Users\dell\Desktop\RandLA-Net-master\RandLANet.py", line 80, in init self.loss = self.get_loss(valid_logits, valid_labels, self.class_weights) File "c:\Users\dell\Desktop\RandLA-Net-master\RandLANet.py", line 266, in get_loss weights = tf.reduce_sum(class_weights * one_hot_labels, axis=1) File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\util\traceback_utils.py", line 150, in error_handler return fn(*args, **kwargs) File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\ops\math_ops.py", line 1406, in binary_op_wrapper return func(x, y, name=name) File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\ops\math_ops.py", line 1766, in _mul_dispatch return multiply(x, y, name=name) File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\util\traceback_utils.py", line 150, in error_handler return fn(*args, **kwargs) File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\util\dispatch.py", line 1082, in op_dispatch_handler return dispatch_target(*args, **kwargs) File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\ops\math_ops.py", line 529, in multiply return gen_math_ops.mul(x, y, name) File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 6588, in mul _, _, _op, _outputs = _op_def_library._apply_op_helper( File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 740, in _apply_op_helper op = g._create_op_internal(op_type_name, inputs, dtypes=None, File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\framework\ops.py", line 3776, in _create_op_internal ret = Operation( File "D:\software\Anaconda\envs\etmvsnet\lib\site-packages\tensorflow\python\framework\ops.py", line 2175, in init self._traceback = tf_stack.extract_stack_for_node(self._c_op)

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "c:\Users\dell\Desktop\RandLA-Net-master\main_Semantic3D.py", line 325, in model.train(dataset) File "c:\Users\dell\Desktop\RandLA-Net-master\RandLANet.py", line 199, in train a = 1 / 0 ZeroDivisionError: division by zero