Hi,
I get an error when I tried training with dice coefficient as the ago function. I noticed there was a new commit on this a couple days ago so I suspect it's some bug in the code. Would you know roughly where this might be?
InvalidArgumentError Traceback (most recent call last)
in ()
----> 1 path = trainer.train(generator, "./unet_trained", training_iters=100, epochs=100, display_step=5)
/home/proj/tf_unet/tf_unet/unet.pyc in train(self, data_provider, output_path, training_iters, epochs, dropout, display_step, restore)
424
425 if step % display_step == 0:
--> 426 self.output_minibatch_stats(sess, summary_writer, step, batch_x, util.crop_to_shape(batch_y, pred_shape))
427
428 total_loss += loss
/home/proj/tf_unet/tf_unet/unet.pyc in output_minibatch_stats(self, sess, summary_writer, step, batch_x, batch_y)
467 feed_dict={self.net.x: batch_x,
468 self.net.y: batch_y,
--> 469 self.net.keep_prob: 1.})
470 summary_writer.add_summary(summary_str, step)
471 summary_writer.flush()
/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in run(self, fetches, feed_dict, options, run_metadata)
764 try:
765 result = self._run(None, fetches, feed_dict, options_ptr,
--> 766 run_metadata_ptr)
767 if run_metadata:
768 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in _run(self, handle, fetches, feed_dict, options, run_metadata)
962 if final_fetches or final_targets:
963 results = self._do_run(handle, final_targets, final_fetches,
--> 964 feed_dict_string, options, run_metadata)
965 else:
966 results = []
/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1012 if handle is None:
1013 return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
-> 1014 target_list, options, run_metadata)
1015 else:
1016 return self._do_call(_prun_fn, self._session, handle, feed_dict,
/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in _do_call(self, fn, *args)
1032 except KeyError:
1033 pass
-> 1034 raise type(e)(node_def, op, message)
1035
1036 def _extend_graph(self):
InvalidArgumentError: Nan in summary histogram for: norm_grads
[[Node: norm_grads = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](norm_grads/tag, Variable_37/read)]]
Caused by op u'norm_grads', defined at:
File "/usr/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"main", fname, loader, pkg_name)
File "/usr/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/usr/local/lib/python2.7/dist-packages/ipykernel/main.py", line 3, in
app.launch_new_instance()
File "/usr/local/lib/python2.7/dist-packages/traitlets/config/application.py", line 658, in launch_instance
app.start()
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelapp.py", line 474, in start
ioloop.IOLoop.instance().start()
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "/usr/local/lib/python2.7/dist-packages/tornado/ioloop.py", line 887, in start
handler_func(fd_obj, events)
File "/usr/local/lib/python2.7/dist-packages/tornado/stack_context.py", line 275, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tornado/stack_context.py", line 275, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 276, in dispatcher
return self.dispatch_shell(stream, msg)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 228, in dispatch_shell
handler(stream, idents, msg)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 390, in execute_request
user_expressions, allow_stdin)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/zmqshell.py", line 501, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2717, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2821, in run_ast_nodes
if self.run_code(code, result):
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2881, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 1, in
path = trainer.train(generator, "./unet_trained", training_iters=100, epochs=100, display_step=5)
File "/home/proj/tf_unet/tf_unet/unet.py", line 389, in train
init = self._initialize(training_iters, output_path, restore)
File "/home/proj/tf_unet/tf_unet/unet.py", line 342, in _initialize
tf.summary.histogram('norm_grads', self.norm_gradients_node)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/summary/summary.py", line 205, in histogram
tag=scope.rstrip('/'), values=values, name=scope)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_logging_ops.py", line 139, in _histogram_summary
name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2240, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1128, in init
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): Nan in summary histogram for: norm_grads
[[Node: norm_grads = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](norm_grads/tag, Variable_37/read)]]