Invalid Argument error for train_shapes.ipynb

[yasiemir]

running train_shapes with the following config on a machine with CPU only:

class ShapesConfig(Config):

    NAME = "shapes"  
    GPU_COUNT = 1
    IMAGES_PER_GPU = 8
    NUM_CLASSES = 1 + 3  # background + 3 shapes   
    IMAGE_MIN_DIM = 128
    IMAGE_MAX_DIM = 128    
    RPN_ANCHOR_SCALES = (8, 16, 32, 64, 128)  # anchor side in pixels
    TRAIN_ROIS_PER_IMAGE = 32
    STEPS_PER_EPOCH = 100
    VALIDATION_STEPS = 3
    POST_NMS_ROIS_TRAINING = 200
    POST_NMS_ROIS_INFERENCE = 100
    BACKBONE_STRIDES = [4,8,16]
    RPN_ANCHOR_SCALES = (32, 64)
    MAX_GT_INSTANCES = 10

and and training with layers='heads':

model.train(dataset_train, dataset_val, 
            learning_rate=config.LEARNING_RATE, 
            epochs=1, 
            layers='heads')

generates the following InvalidArgumentError:

InvalidArgumentError                      Traceback (most recent call last)
/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1322     try:
-> 1323       return fn(*args)
   1324     except errors.OpError as e:

/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
   1301                                    feed_dict, fetch_list, target_list,
-> 1302                                    status, run_metadata)
   1303 

/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/errors_impl.py in __exit__(self, type_arg, value_arg, traceback_arg)
    472             compat.as_text(c_api.TF_Message(self.status.status)),
--> 473             c_api.TF_GetCode(self.status.status))
    474     # Delete the underlying status object from memory otherwise it stays alive

InvalidArgumentError: indices[1] = 3949 is not in [0, 3840)
     [[Node: ROI/Gather_22 = Gather[Tindices=DT_INT32, Tparams=DT_FLOAT, validate_indices=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](ROI/Gather_16/params, ROI/strided_slice_39)]]

During handling of the above exception, another exception occurred:

InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-10-2101606c7d8e> in <module>()
      6             learning_rate=config.LEARNING_RATE,
      7             epochs=1,
----> 8             layers='heads')

/home/meer/Documents/dsb/Mask_RCNN-master/model.py in train(self, train_dataset, val_dataset, learning_rate, epochs, layers)
   2208             max_queue_size=100,
   2209             workers=workers,
-> 2210             use_multiprocessing=True,
   2211         )
   2212         self.epoch = max(self.epoch, epochs)

/usr/local/lib/python3.5/dist-packages/keras/legacy/interfaces.py in wrapper(*args, **kwargs)
     89                 warnings.warn('Update your `' + object_name +
     90                               '` call to the Keras 2 API: ' + signature, stacklevel=2)
---> 91             return func(*args, **kwargs)
     92         wrapper._original_function = func
     93         return wrapper

/usr/local/lib/python3.5/dist-packages/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
   2175                     outs = self.train_on_batch(x, y,
   2176                                                sample_weight=sample_weight,
-> 2177                                                class_weight=class_weight)
   2178 
   2179                     if not isinstance(outs, list):

/usr/local/lib/python3.5/dist-packages/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight)
   1847             ins = x + y + sample_weights
   1848         self._make_train_function()
-> 1849         outputs = self.train_function(ins)
   1850         if len(outputs) == 1:
   1851             return outputs[0]

/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 

/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
    887     try:
    888       result = self._run(None, fetches, feed_dict, options_ptr,
--> 889                          run_metadata_ptr)
    890       if run_metadata:
    891         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
   1118     if final_fetches or final_targets or (handle and feed_dict_tensor):
   1119       results = self._do_run(handle, final_targets, final_fetches,
-> 1120                              feed_dict_tensor, options, run_metadata)
   1121     else:
   1122       results = []

/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1315     if handle is None:
   1316       return self._do_call(_run_fn, self._session, feeds, fetches, targets,
-> 1317                            options, run_metadata)
   1318     else:
   1319       return self._do_call(_prun_fn, self._session, handle, feeds, fetches)

/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1334         except KeyError:
   1335           pass
-> 1336       raise type(e)(node_def, op, message)
   1337 
   1338   def _extend_graph(self):

InvalidArgumentError: indices[1] = 3949 is not in [0, 3840)
     [[Node: ROI/Gather_22 = Gather[Tindices=DT_INT32, Tparams=DT_FLOAT, validate_indices=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](ROI/Gather_16/params, ROI/strided_slice_39)]]

Caused by op 'ROI/Gather_22', 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/__main__.py", line 3, in <module>
    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 474, in start
    ioloop.IOLoop.instance().start()
  File "/usr/local/lib/python3.5/dist-packages/zmq/eventloop/ioloop.py", line 177, in start
    super(ZMQIOLoop, self).start()
  File "/usr/lib/python3/dist-packages/tornado/ioloop.py", line 866, in start
    handler_func(fd_obj, events)
  File "/usr/lib/python3/dist-packages/tornado/stack_context.py", line 275, 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/lib/python3/dist-packages/tornado/stack_context.py", line 275, in null_wrapper
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py", line 276, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py", line 228, in dispatch_shell
    handler(stream, idents, msg)
  File "/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py", line 390, in execute_request
    user_expressions, allow_stdin)
  File "/usr/local/lib/python3.5/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/python3.5/dist-packages/ipykernel/zmqshell.py", line 501, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py", line 2717, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py", line 2821, in run_ast_nodes
    if self.run_code(code, result):
  File "/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py", line 2881, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-7-ae82d0e47c39>", line 3, in <module>
    model_dir=MODEL_DIR)
  File "/home/meer/Documents/dsb/Mask_RCNN-master/model.py", line 1735, in __init__
    self.keras_model = self.build(mode=mode, config=config)
  File "/home/meer/Documents/dsb/Mask_RCNN-master/model.py", line 1851, in build
    config=config)([rpn_class, rpn_bbox])
  File "/usr/local/lib/python3.5/dist-packages/keras/engine/topology.py", line 617, in __call__
    output = self.call(inputs, **kwargs)
  File "/home/meer/Documents/dsb/Mask_RCNN-master/model.py", line 271, in call
    names=["pre_nms_anchors"])
  File "/home/meer/Documents/dsb/Mask_RCNN-master/utils.py", line 678, in batch_slice
    output_slice = graph_fn(*inputs_slice)
  File "/home/meer/Documents/dsb/Mask_RCNN-master/model.py", line 269, in <lambda>
    anchors = utils.batch_slice(ix, lambda x: tf.gather(anchors, x),
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/array_ops.py", line 2486, in gather
    params, indices, validate_indices=validate_indices, name=name)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 1834, in gather
    validate_indices=validate_indices, name=name)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
    op_def=op_def)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 1470, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): indices[1] = 3949 is not in [0, 3840)
     [[Node: ROI/Gather_22 = Gather[Tindices=DT_INT32, Tparams=DT_FLOAT, validate_indices=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](ROI/Gather_16/params, ROI/strided_slice_39)]]

[woodm1979]

I'm also running into this issue. I'll try and debug it tonight/tomorrow.

[yasiemir]

I think its related to #211

[woodm1979]

Somehow we're getting more Scores than we are anchors. ... which seems to be impossible, so there may be a mismatch in combining some things somehow.

[tonyzhao6]

Are you using the default ResNet-101 with FPN structure? If so, you have a mismatch in the number of elements between RPN_ANCHOR_SCALES and BACKBONE_STRIDES. Also, you have RPN_ANCHOR_SCALES defined twice.

In general, if you are using ResNet-101 with FPN and taking the C4 backbone, there are 5 levels in the FPN. Thus, you should have 5 elements in RPN_ANCHOR_SCALES and 5 elements in BACKBONE_STRIDES.

[dxs66]

When i run the train_shapes.ipynb, I met the result is that FileNotFoundError: [Errno 2] Could not find weight files in /home/ubuntu66/logs/shapes20181007T1338. How can i solve this problem?

[PROFRAGU]

did anybody fix this issue?