def add_training_inputs(model, roidb=None):
"""Create network input ops and blobs used for training. To be called
*after* model_builder.create().
"""
# Implementation notes:
# Typically, one would create the input ops and then the rest of the net.
# However, creating the input ops depends on loading the dataset, which
# can take a few minutes for COCO.
# We prefer to avoid waiting so debugging can fail fast.
# Thus, we create the net *without input ops* prior to loading the
# dataset, and then add the input ops after loading the dataset.
# Since we defer input op creation, we need to do a little bit of surgery
# to place the input ops at the start of the network op list.
assert model.train, 'Training inputs can only be added to a trainable model'
if roidb is not None:
# To make debugging easier you can set cfg.DATA_LOADER.NUM_THREADS = 1
model.roi_data_loader = RoIDataLoader(
roidb,
num_loaders=cfg.DATA_LOADER.NUM_THREADS,
minibatch_queue_size=cfg.DATA_LOADER.MINIBATCH_QUEUE_SIZE,
blobs_queue_capacity=cfg.DATA_LOADER.BLOBS_QUEUE_CAPACITY)
orig_num_op = len(model.net._net.op)
blob_names = roi_data_minibatch.get_minibatch_blob_names(is_training=True)
for gpu_id in range(cfg.NUM_GPUS):
with c2_utils.NamedCudaScope(gpu_id):
for blob_name in blob_names:
workspace.CreateBlob(core.ScopedName(blob_name))
model.net.DequeueBlobs(model.roi_data_loader._blobs_queue_name,
blob_names)
# A little op surgery to move input ops to the start of the net
diff = len(model.net._net.op) - orig_num_op
new_op = model.net._net.op[-diff:] + model.net._net.op[:-diff]
del model.net._net.op[:]
model.net._net.op.extend(new_op)
def __init__(
self,
roidb,
num_loaders=4,
minibatch_queue_size=64,
blobs_queue_capacity=8
):
self._roidb = roidb
self._lock = threading.Lock()
self._perm = deque(range(len(self._roidb)))
self._cur = 0 # _perm cursor
# The minibatch queue holds prepared training data in host (CPU) memory
# When training with N > 1 GPUs, each element in the minibatch queue
# is actually a partial minibatch which contributes 1 / N of the
# examples to the overall minibatch
self._minibatch_queue = Queue.Queue(maxsize=minibatch_queue_size)
self._blobs_queue_capacity = blobs_queue_capacity
# Random queue name in case one instantiates multple RoIDataLoaders
self._loader_id = uuid.uuid4()
self._blobs_queue_name = 'roi_blobs_queue_{}'.format(self._loader_id)
# Loader threads construct (partial) minibatches and put them on the
# minibatch queue
self._num_loaders = num_loaders
self._num_gpus = cfg.NUM_GPUS
self.coordinator = Coordinator()
self._output_names = get_minibatch_blob_names()
self._shuffle_roidb_inds()
self.create_threads()
def __init__(
self,
roidb,
num_loaders=4,
minibatch_queue_size=64,
blobs_queue_capacity=8
):
self._roidb = roidb
self._lock = threading.Lock()
self._perm = deque(range(len(self._roidb)))
self._cur = 0 # _perm cursor
# The minibatch queue holds prepared training data in host (CPU) memory
# When training with N > 1 GPUs, each element in the minibatch queue
# is actually a partial minibatch which contributes 1 / N of the
# examples to the overall minibatch
self._minibatch_queue = Queue.Queue(maxsize=minibatch_queue_size)
self._blobs_queue_capacity = blobs_queue_capacity
# Random queue name in case one instantiates multple RoIDataLoaders
self._loader_id = uuid.uuid4()
self._blobs_queue_name = 'roi_blobs_queue_{}'.format(self._loader_id)
# Loader threads construct (partial) minibatches and put them on the
# minibatch queue
self._num_loaders = num_loaders
self._num_gpus = cfg.NUM_GPUS
self.coordinator = Coordinator()
self._output_names = get_minibatch_blob_names()
self._shuffle_roidb_inds()
self.create_threads()
def create_model(weights_file):
"""adapted from utils.train.setup_model_for_training
"""
model = model_builder.create(cfg.MODEL.TYPE, train=True)
if cfg.MEMONGER:
optimize_memory(model)
# Performs random weight initialization as defined by the model
workspace.RunNetOnce(model.param_init_net)
roidb = combined_roidb_for_training(
cfg.TRAIN.DATASETS, cfg.TRAIN.PROPOSAL_FILES
)
# To make debugging easier you can set cfg.DATA_LOADER.NUM_THREADS = 1
model.roi_data_loader = RoIDataLoaderSimple(
roidb,
num_loaders=cfg.DATA_LOADER.NUM_THREADS,
minibatch_queue_size=cfg.DATA_LOADER.MINIBATCH_QUEUE_SIZE,
blobs_queue_capacity=cfg.DATA_LOADER.BLOBS_QUEUE_CAPACITY
)
orig_num_op = len(model.net._net.op)
blob_names = roi_data_minibatch.get_minibatch_blob_names(is_training=True)
with c2_utils.NamedCudaScope(0):
for blob_name in blob_names:
workspace.CreateBlob(core.ScopedName(blob_name))
model.net.DequeueBlobs(
model.roi_data_loader._blobs_queue_name, blob_names
)
# A little op surgery to move input ops to the start of the net
diff = len(model.net._net.op) - orig_num_op
new_op = model.net._net.op[-diff:] + model.net._net.op[:-diff]
del model.net._net.op[:]
model.net._net.op.extend(new_op)
nu.initialize_gpu_from_weights_file(model, weights_file, gpu_id=0)
nu.broadcast_parameters(model)
workspace.CreateBlob("gpu_0/track_n_rois_two")
workspace.CreateNet(model.net)
# Start loading mini-batches and enqueuing blobs
model.roi_data_loader.register_sigint_handler()
model.roi_data_loader.start(prefill=True)
return model
def add_training_inputs(model, roidb=None):
"""Create network input ops and blobs used for training. To be called
*after* model_builder.create().
"""
# Implementation notes:
# Typically, one would create the input ops and then the rest of the net.
# However, creating the input ops depends on loading the dataset, which
# can take a few minutes for COCO.
# We prefer to avoid waiting so debugging can fail fast.
# Thus, we create the net *without input ops* prior to loading the
# dataset, and then add the input ops after loading the dataset.
# Since we defer input op creation, we need to do a little bit of surgery
# to place the input ops at the start of the network op list.
assert model.train, 'Training inputs can only be added to a trainable model'
if roidb is not None:
# To make debugging easier you can set cfg.DATA_LOADER.NUM_THREADS = 1
model.roi_data_loader = RoIDataLoader(
roidb,
num_loaders=cfg.DATA_LOADER.NUM_THREADS,
minibatch_queue_size=cfg.DATA_LOADER.MINIBATCH_QUEUE_SIZE,
blobs_queue_capacity=cfg.DATA_LOADER.BLOBS_QUEUE_CAPACITY
)
orig_num_op = len(model.net._net.op)
blob_names = roi_data_minibatch.get_minibatch_blob_names(is_training=True)
for gpu_id in range(cfg.NUM_GPUS):
with c2_utils.NamedCudaScope(gpu_id):
for blob_name in blob_names:
workspace.CreateBlob(core.ScopedName(blob_name))
model.net.DequeueBlobs(
model.roi_data_loader._blobs_queue_name, blob_names
)
# A little op surgery to move input ops to the start of the net
diff = len(model.net._net.op) - orig_num_op
new_op = model.net._net.op[-diff:] + model.net._net.op[:-diff]
del model.net._net.op[:]
model.net._net.op.extend(new_op)
def __init__(
self,
roidb,
num_loaders=4,
minibatch_queue_size=64,
blobs_queue_capacity=8
):
self._mc = pylibmc.Client(["127.0.0.1:11212"], binary=True,
behaviors={"tcp_nodelay": True,
"ketama": True})
self._mc.set('rois_s','yidu')
self._mc.set('inds_s','yidu')
self._mc.set('freeze_fastrcnn_label_s','yidu')
self._mc.set('rpn_cls_probs_fpn2_s','yidu')
self._mc.set('rpn_bbox_pred_fpn2_s','yidu')
self._mc.set('rpn_cls_probs_fpn3_s','yidu')
self._mc.set('rpn_bbox_pred_fpn3_s','yidu')
self._mc.set('rpn_cls_probs_fpn4_s','yidu')
self._mc.set('rpn_bbox_pred_fpn4_s','yidu')
self._mc.set('rpn_cls_probs_fpn5_s','yidu')
self._mc.set('rpn_bbox_pred_fpn5_s','yidu')
self._mc.set('rpn_cls_probs_fpn6_s','yidu')
self._mc.set('rpn_bbox_pred_fpn6_s','yidu')
self._mc.set('rois',[])
self._mc.set('inds',[])
self._mc.set('freeze_fastrcnn_label',[])
self._mc.set('rpn_cls_probs_fpn2',[])
self._mc.set('rpn_bbox_pred_fpn2',[])
self._mc.set('rpn_cls_probs_fpn3',[])
self._mc.set('rpn_bbox_pred_fpn3',[])
self._mc.set('rpn_cls_probs_fpn4',[])
self._mc.set('rpn_bbox_pred_fpn4',[])
self._mc.set('rpn_cls_probs_fpn5',[])
self._mc.set('rpn_bbox_pred_fpn5',[])
self._mc.set('rpn_cls_probs_fpn6',[])
self._mc.set('rpn_bbox_pred_fpn6',[])
self._roidb = roidb
self._lock = threading.Lock()
self._perm = deque(range(len(self._roidb)))
self._cur = 0 # _perm cursor
# The minibatch queue holds prepared training data in host (CPU) memory
# When training with N > 1 GPUs, each element in the minibatch queue
# is actually a partial minibatch which contributes 1 / N of the
# examples to the overall minibatch
self._minibatch_queue = Queue.Queue(maxsize=minibatch_queue_size)
self._blobs_queue_capacity = blobs_queue_capacity
# Random queue name in case one instantiates multple RoIDataLoaders
self._loader_id = uuid.uuid4()
self._blobs_queue_name = 'roi_blobs_queue_{}'.format(self._loader_id)
# Loader threads construct (partial) minibatches and put them on the
# minibatch queue
self._num_loaders = num_loaders
self._num_gpus = cfg.NUM_GPUS
self.coordinator = Coordinator()
self._output_names = get_minibatch_blob_names()
self._inds=[]
self._shuffle_roidb_inds0()
self._shuffle_roidb_inds()
self.create_threads()
