I am running Mask RCNN object detection, which I got the same internal error over two different size RCNN structures. The demo are in this repository :
I tried to train shapes (only circles, triangles, squares instead of regular 80 classes object detection) on my desktop PC, I got a h5 model which has much less backbone structure than the real object detection. Then I used this h5 file on Jetson TX2. However I still got internal error as below:
Question is: Should I expand my swap memory for GPU or CPU? Or should I install a 60GB SSD drive for the whole system? Maybe reduce the ROI detection to utilize fewer registers on CPU?
InternalError Traceback (most recent call last)
~/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1326 try:
→ 1327 return fn(*args)
1328 except errors.OpError as e:
~/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
1305 feed_dict, fetch_list, target_list,
→ 1306 status, run_metadata)
1307
/usr/lib/python3.5/contextlib.py in exit(self, type, value, traceback)
65 try:
—> 66 next(self.gen)
67 except StopIteration:
~/.local/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py in raise_exception_on_not_ok_status()
465 compat.as_text(pywrap_tensorflow.TF_Message(status)),
→ 466 pywrap_tensorflow.TF_GetCode(status))
467 finally:
InternalError: WhereOp: Could not launch cub::DeviceReduce::Sum to count number of true indices. temp_storage_bytes: 1, status: too many resources requested for launch
[[Node: roi_align_classifier_1/Where_2 = Where_device=“/job:localhost/replica:0/task:0/gpu:0”]]
[[Node: roi_align_classifier_1/Cast_5/_5545 = _Recvclient_terminated=false, recv_device=“/job:localhost/replica:0/task:0/cpu:0”, send_device=“/job:localhost/replica:0/task:0/gpu:0”, send_device_incarnation=1, tensor_name=“edge_3201_roi_align_classifier_1/Cast_5”, tensor_type=DT_INT32, _device=“/job:localhost/replica:0/task:0/cpu:0”]]
During handling of the above exception, another exception occurred:
InternalError Traceback (most recent call last)
in ()
----> 1 results = model.detect([original_image], verbose=1)
2
3 r = results[0]
4 visualize.display_instances(original_image, r[‘rois’], r[‘masks’], r[‘class_ids’],
5 dataset_val.class_names, r[‘scores’], ax=get_ax())
~/Desktop/Mask_RCNN-master/model.py in detect(self, images, verbose)
2338 detections, mrcnn_class, mrcnn_bbox, mrcnn_mask,
2339 rois, rpn_class, rpn_bbox =
→ 2340 self.keras_model.predict([molded_images, image_metas], verbose=0)
2341 # Process detections
2342 results =
/usr/local/lib/python3.5/dist-packages/keras/engine/training.py in predict(self, x, batch_size, verbose, steps)
1798 f = self.predict_function
1799 return self._predict_loop(f, ins, batch_size=batch_size,
→ 1800 verbose=verbose, steps=steps)
1801
1802 def train_on_batch(self, x, y,
/usr/local/lib/python3.5/dist-packages/keras/engine/training.py in _predict_loop(self, f, ins, batch_size, verbose, steps)
1299 ins_batch[i] = ins_batch[i].toarray()
1300
→ 1301 batch_outs = f(ins_batch)
1302 if not isinstance(batch_outs, list):
1303 batch_outs = [batch_outs]
/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py in call(self, inputs)
2473 session = get_session()
2474 updated = session.run(fetches=fetches, feed_dict=feed_dict,
→ 2475 **self.session_kwargs)
2476 return updated[:len(self.outputs)]
2477
~/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
893 try:
894 result = self._run(None, fetches, feed_dict, options_ptr,
→ 895 run_metadata_ptr)
896 if run_metadata:
897 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
~/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
1122 if final_fetches or final_targets or (handle and feed_dict_tensor):
1123 results = self._do_run(handle, final_targets, final_fetches,
→ 1124 feed_dict_tensor, options, run_metadata)
1125 else:
1126 results =
~/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1319 if handle is None:
1320 return self._do_call(_run_fn, self._session, feeds, fetches, targets,
→ 1321 options, run_metadata)
1322 else:
1323 return self._do_call(_prun_fn, self._session, handle, feeds, fetches)
~/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1338 except KeyError:
1339 pass
→ 1340 raise type(e)(node_def, op, message)
1341
1342 def _extend_graph(self):
InternalError: WhereOp: Could not launch cub::DeviceReduce::Sum to count number of true indices. temp_storage_bytes: 1, status: too many resources requested for launch
[[Node: roi_align_classifier_1/Where_2 = Where_device=“/job:localhost/replica:0/task:0/gpu:0”]]
[[Node: roi_align_classifier_1/Cast_5/_5545 = _Recvclient_terminated=false, recv_device=“/job:localhost/replica:0/task:0/cpu:0”, send_device=“/job:localhost/replica:0/task:0/gpu:0”, send_device_incarnation=1, tensor_name=“edge_3201_roi_align_classifier_1/Cast_5”, tensor_type=DT_INT32, _device=“/job:localhost/replica:0/task:0/cpu:0”]]
Caused by op ‘roi_align_classifier_1/Where_2’, defined at:
File “/usr/lib/python3.5/runpy.py”, line 184, in _run_module_as_main
“main”, mod_spec)
File “/usr/lib/python3.5/runpy.py”, line 85, in _run_code
exec(code, run_globals)
File “/usr/local/lib/python3.5/dist-packages/ipykernel_launcher.py”, line 16, in
app.launch_new_instance()
File “/usr/local/lib/python3.5/dist-packages/traitlets/config/application.py”, line 658, in launch_instance
app.start()
File “/usr/local/lib/python3.5/dist-packages/ipykernel/kernelapp.py”, line 478, in start
self.io_loop.start()
File “/usr/local/lib/python3.5/dist-packages/zmq/eventloop/ioloop.py”, line 177, in start
super(ZMQIOLoop, self).start()
File “/usr/local/lib/python3.5/dist-packages/tornado/ioloop.py”, line 888, in start
handler_func(fd_obj, events)
File “/usr/local/lib/python3.5/dist-packages/tornado/stack_context.py”, line 277, in null_wrapper
return fn(*args, **kwargs)
File “/usr/local/lib/python3.5/dist-packages/zmq/eventloop/zmqstream.py”, line 440, in _handle_events
self._handle_recv()
File “/usr/local/lib/python3.5/dist-packages/zmq/eventloop/zmqstream.py”, line 472, in _handle_recv
self._run_callback(callback, msg)
File “/usr/local/lib/python3.5/dist-packages/zmq/eventloop/zmqstream.py”, line 414, in _run_callback
callback(*args, **kwargs)
File “/usr/local/lib/python3.5/dist-packages/tornado/stack_context.py”, line 277, in null_wrapper
return fn(*args, **kwargs)
File “/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py”, line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File “/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py”, line 233, in dispatch_shell
handler(stream, idents, msg)
File “/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py”, line 399, in execute_request
user_expressions, allow_stdin)
File “/usr/local/lib/python3.5/dist-packages/ipykernel/ipkernel.py”, line 208, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File “/usr/local/lib/python3.5/dist-packages/ipykernel/zmqshell.py”, line 537, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File “/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py”, line 2728, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File “/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py”, line 2850, in run_ast_nodes
if self.run_code(code, result):
File “/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py”, line 2910, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File “”, line 15, in
model_dir=DIR)
File “/home/nvidia/Desktop/Mask_RCNN-master/model.py”, line 1735, in init
self.keras_model = self.build(mode=mode, config=config)
File “/home/nvidia/Desktop/Mask_RCNN-master/model.py”, line 1918, in build
config.POOL_SIZE, config.NUM_CLASSES)
File “/home/nvidia/Desktop/Mask_RCNN-master/model.py”, line 876, in fpn_classifier_graph
name=“roi_align_classifier”)([rois] + feature_maps)
File “/usr/local/lib/python3.5/dist-packages/keras/engine/topology.py”, line 617, in call
output = self.call(inputs, **kwargs)
File “/home/nvidia/Desktop/Mask_RCNN-master/model.py”, line 373, in call
ix = tf.where(tf.equal(roi_level, level))
File “/home/nvidia/.local/lib/python3.5/site-packages/tensorflow/python/ops/array_ops.py”, line 2365, in where
return gen_array_ops.where(input=condition, name=name)
File “/home/nvidia/.local/lib/python3.5/site-packages/tensorflow/python/ops/gen_array_ops.py”, line 4053, in where
result = _op_def_lib.apply_op(“Where”, input=input, name=name)
File “/home/nvidia/.local/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py”, line 767, in apply_op
op_def=op_def)
File “/home/nvidia/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py”, line 2630, in create_op
original_op=self._default_original_op, op_def=op_def)
File “/home/nvidia/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py”, line 1204, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InternalError (see above for traceback): WhereOp: Could not launch cub::DeviceReduce::Sum to count number of true indices. temp_storage_bytes: 1, status: too many resources requested for launch
[[Node: roi_align_classifier_1/Where_2 = Where_device=“/job:localhost/replica:0/task:0/gpu:0”]]
[[Node: roi_align_classifier_1/Cast_5/_5545 = _Recvclient_terminated=false, recv_device=“/job:localhost/replica:0/task:0/cpu:0”, send_device=“/job:localhost/replica:0/task:0/gpu:0”, send_device_incarnation=1, tensor_name=“edge_3201_roi_align_classifier_1/Cast_5”, tensor_type=DT_INT32, _device=“/job:localhost/replica:0/task:0/cpu:0”]]