Python caffe2.python.workspace.CreateNet() Examples

The following are 30 code examples of caffe2.python.workspace.CreateNet(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module caffe2.python.workspace , or try the search function .
Example #1
Source File: test_engine.py    From Detectron-Cascade-RCNN with Apache License 2.0 6 votes vote down vote up 
def initialize_model_from_cfg(weights_file, gpu_id=0):
    """Initialize a model from the global cfg. Loads test-time weights and
    creates the networks in the Caffe2 workspace.
    """
    model = model_builder.create(cfg.MODEL.TYPE, train=False, gpu_id=gpu_id)
    net_utils.initialize_gpu_from_weights_file(
        model, weights_file, gpu_id=gpu_id,
    )
    model_builder.add_inference_inputs(model)
    workspace.CreateNet(model.net)
    workspace.CreateNet(model.conv_body_net)
    if cfg.MODEL.MASK_ON:
        workspace.CreateNet(model.mask_net)
    if cfg.MODEL.KEYPOINTS_ON:
        workspace.CreateNet(model.keypoint_net)
    return model
Example #2
Source File: test_engine.py    From KL-Loss with Apache License 2.0 6 votes vote down vote up 
def initialize_model_from_cfg(weights_file, gpu_id=0):
    """Initialize a model from the global cfg. Loads test-time weights and
    creates the networks in the Caffe2 workspace.
    """
    model = model_builder.create(cfg.MODEL.TYPE, train=False, gpu_id=gpu_id)
    net_utils.initialize_gpu_from_weights_file(
        model, weights_file, gpu_id=gpu_id,
    )
    model_builder.add_inference_inputs(model)
    workspace.CreateNet(model.net)
    workspace.CreateNet(model.conv_body_net)
    if cfg.MODEL.MASK_ON:
        workspace.CreateNet(model.mask_net)
    if cfg.MODEL.KEYPOINTS_ON:
        workspace.CreateNet(model.keypoint_net)
    return model
Example #3
Source File: dlrm_s_caffe2.py    From dlrm with MIT License 6 votes vote down vote up 
def create_model(self, X, S_lengths, S_indices, T):
        #setup tril indices for the interactions
        offset = 1 if self.arch_interaction_itself else 0
        num_fea = len(self.emb_l) + 1
        tril_indices = np.array([j + i * num_fea
                                 for i in range(num_fea) for j in range(i + offset)])
        self.FeedBlobWrapper(self.tint + "_tril_indices", tril_indices)

        # create compute graph
        if T is not None:
            # WARNING: RunNetOnce call is needed only if we use brew and ConstantFill.
            # We could use direct calls to self.model functions above to avoid it
            workspace.RunNetOnce(self.model.param_init_net)
            workspace.CreateNet(self.model.net)
            if self.test_net is not None:
                workspace.CreateNet(self.test_net)
Example #4
Source File: test_batch_permutation_op.py    From seg_every_thing with Apache License 2.0 6 votes vote down vote up 
def _run_speed_test(self, iters=5, N=1024):
        """This function provides an example of how to benchmark custom
        operators using the Caffe2 'prof_dag' network execution type. Please
        note that for 'prof_dag' to work, Caffe2 must be compiled with profiling
        support using the `-DUSE_PROF=ON` option passed to `cmake` when building
        Caffe2.
        """
        net = core.Net('test')
        net.Proto().type = 'prof_dag'
        net.Proto().num_workers = 2
        Y = net.BatchPermutation(['X', 'I'], 'Y')
        Y_flat = net.FlattenToVec([Y], 'Y_flat')
        loss = net.AveragedLoss([Y_flat], 'loss')
        net.AddGradientOperators([loss])
        workspace.CreateNet(net)

        X = np.random.randn(N, 256, 14, 14)
        for _i in range(iters):
            I = np.random.permutation(N)
            workspace.FeedBlob('X', X.astype(np.float32))
            workspace.FeedBlob('I', I.astype(np.int32))
            workspace.RunNet(net.Proto().name)
            np.testing.assert_allclose(
                workspace.FetchBlob('Y'), X[I], rtol=1e-5, atol=1e-08
            )
Example #5
Source File: train.py    From Clustered-Object-Detection-in-Aerial-Image with Apache License 2.0 6 votes vote down vote up 
def setup_model_for_training(model, weights_file, output_dir):
    """Loaded saved weights and create the network in the C2 workspace."""
    logger = logging.getLogger(__name__)
    add_model_training_inputs(model)

    if weights_file:
        # Override random weight initialization with weights from a saved model
        nu.initialize_gpu_from_weights_file(model, weights_file, gpu_id=0)
    # Even if we're randomly initializing we still need to synchronize
    # parameters across GPUs
    nu.broadcast_parameters(model)
    workspace.CreateNet(model.net)

    logger.info('Outputs saved to: {:s}'.format(os.path.abspath(output_dir)))
    dump_proto_files(model, output_dir)

    # Start loading mini-batches and enqueuing blobs
    model.roi_data_loader.register_sigint_handler()
    model.roi_data_loader.start(prefill=True)
    return output_dir
Example #6
Source File: test_batch_permutation_op.py    From Clustered-Object-Detection-in-Aerial-Image with Apache License 2.0 6 votes vote down vote up 
def _run_speed_test(self, iters=5, N=1024):
        """This function provides an example of how to benchmark custom
        operators using the Caffe2 'prof_dag' network execution type. Please
        note that for 'prof_dag' to work, Caffe2 must be compiled with profiling
        support using the `-DUSE_PROF=ON` option passed to `cmake` when building
        Caffe2.
        """
        net = core.Net('test')
        net.Proto().type = 'prof_dag'
        net.Proto().num_workers = 2
        Y = net.BatchPermutation(['X', 'I'], 'Y')
        Y_flat = net.FlattenToVec([Y], 'Y_flat')
        loss = net.AveragedLoss([Y_flat], 'loss')
        net.AddGradientOperators([loss])
        workspace.CreateNet(net)

        X = np.random.randn(N, 256, 14, 14)
        for _i in range(iters):
            I = np.random.permutation(N)
            workspace.FeedBlob('X', X.astype(np.float32))
            workspace.FeedBlob('I', I.astype(np.int32))
            workspace.RunNet(net.Proto().name)
            np.testing.assert_allclose(
                workspace.FetchBlob('Y'), X[I], rtol=1e-5, atol=1e-08
            )
Example #7
Source File: test_batch_permutation_op.py    From KL-Loss with Apache License 2.0 6 votes vote down vote up 
def _run_speed_test(self, iters=5, N=1024):
        """This function provides an example of how to benchmark custom
        operators using the Caffe2 'prof_dag' network execution type. Please
        note that for 'prof_dag' to work, Caffe2 must be compiled with profiling
        support using the `-DUSE_PROF=ON` option passed to `cmake` when building
        Caffe2.
        """
        net = core.Net('test')
        net.Proto().type = 'prof_dag'
        net.Proto().num_workers = 2
        Y = net.BatchPermutation(['X', 'I'], 'Y')
        Y_flat = net.FlattenToVec([Y], 'Y_flat')
        loss = net.AveragedLoss([Y_flat], 'loss')
        net.AddGradientOperators([loss])
        workspace.CreateNet(net)

        X = np.random.randn(N, 256, 14, 14)
        for _i in range(iters):
            I = np.random.permutation(N)
            workspace.FeedBlob('X', X.astype(np.float32))
            workspace.FeedBlob('I', I.astype(np.int32))
            workspace.RunNet(net.Proto().name)
            np.testing.assert_allclose(
                workspace.FetchBlob('Y'), X[I], rtol=1e-5, atol=1e-08
            )
Example #8
Source File: model_utils.py    From inference with Apache License 2.0 6 votes vote down vote up 
def load_model_pb(net_file, init_file=None, is_run_init=True, is_create_net=True):
    net = core.Net("net")
    if net_file is not None:
        net.Proto().ParseFromString(open(net_file, "rb").read())

    if init_file is None:
        fn, ext = os.path.splitext(net_file)
        init_file = fn + "_init" + ext

    init_net = caffe2_pb2.NetDef()
    init_net.ParseFromString(open(init_file, "rb").read())

    if is_run_init:
        workspace.RunNetOnce(init_net)
        create_blobs_if_not_existed(net.external_inputs)
        if net.Proto().name == "":
            net.Proto().name = "net"
    if is_create_net:
        workspace.CreateNet(net)

    return (net, init_net)
Example #9
Source File: train.py    From seg_every_thing with Apache License 2.0 6 votes vote down vote up 
def setup_model_for_training(model, weights_file, output_dir):
    """Loaded saved weights and create the network in the C2 workspace."""
    logger = logging.getLogger(__name__)
    add_model_training_inputs(model)

    if weights_file:
        # Override random weight initialization with weights from a saved model
        nu.initialize_gpu_from_weights_file(model, weights_file, gpu_id=0)
    # Even if we're randomly initializing we still need to synchronize
    # parameters across GPUs
    nu.broadcast_parameters(model)
    workspace.CreateNet(model.net)

    logger.info('Outputs saved to: {:s}'.format(os.path.abspath(output_dir)))
    dump_proto_files(model, output_dir)

    # Start loading mini-batches and enqueuing blobs
    model.roi_data_loader.register_sigint_handler()
    model.roi_data_loader.start(prefill=True)
    return output_dir
Example #10
Source File: test_engine.py    From seg_every_thing with Apache License 2.0 6 votes vote down vote up 
def initialize_model_from_cfg(weights_file, gpu_id=0):
    """Initialize a model from the global cfg. Loads test-time weights and
    creates the networks in the Caffe2 workspace.
    """
    model = model_builder.create(cfg.MODEL.TYPE, train=False, gpu_id=gpu_id)
    net_utils.initialize_gpu_from_weights_file(
        model, weights_file, gpu_id=gpu_id,
    )
    model_builder.add_inference_inputs(model)
    workspace.CreateNet(model.net)
    workspace.CreateNet(model.conv_body_net)
    if cfg.MODEL.MASK_ON:
        workspace.CreateNet(model.mask_net)
    if cfg.MODEL.KEYPOINTS_ON:
        workspace.CreateNet(model.keypoint_net)
    return model
Example #11
Source File: test_batch_permutation_op.py    From masktextspotter.caffe2 with Apache License 2.0 6 votes vote down vote up 
def _run_speed_test(self, iters=5, N=1024):
        """This function provides an example of how to benchmark custom
        operators using the Caffe2 'prof_dag' network execution type. Please
        note that for 'prof_dag' to work, Caffe2 must be compiled with profiling
        support using the `-DUSE_PROF=ON` option passed to `cmake` when building
        Caffe2.
        """
        net = core.Net('test')
        net.Proto().type = 'prof_dag'
        net.Proto().num_workers = 2
        Y = net.BatchPermutation(['X', 'I'], 'Y')
        Y_flat = net.FlattenToVec([Y], 'Y_flat')
        loss = net.AveragedLoss([Y_flat], 'loss')
        net.AddGradientOperators([loss])
        workspace.CreateNet(net)

        X = np.random.randn(N, 256, 14, 14)
        for _i in range(iters):
            I = np.random.permutation(N)
            workspace.FeedBlob('X', X.astype(np.float32))
            workspace.FeedBlob('I', I.astype(np.int32))
            workspace.RunNet(net.Proto().name)
            np.testing.assert_allclose(
                workspace.FetchBlob('Y'), X[I], rtol=1e-5, atol=1e-08
            )
Example #12
Source File: test_engine.py    From masktextspotter.caffe2 with Apache License 2.0 6 votes vote down vote up 
def initialize_model_from_cfg():
    """Initialize a model from the global cfg. Loads test-time weights and
    creates the networks in the Caffe2 workspace.
    """
    model = model_builder.create(cfg.MODEL.TYPE, train=False)
    net_utils.initialize_from_weights_file(
        model, cfg.TEST.WEIGHTS, broadcast=False
    )
    model_builder.add_inference_inputs(model)
    workspace.CreateNet(model.net)
    workspace.CreateNet(model.conv_body_net)
    if cfg.MODEL.MASK_ON:
        workspace.CreateNet(model.mask_net)
    if cfg.MODEL.KEYPOINTS_ON:
        workspace.CreateNet(model.keypoint_net)
    return model
Example #13
Source File: train_net.py    From masktextspotter.caffe2 with Apache License 2.0 6 votes vote down vote up 
def setup_model_for_training(model, output_dir):
    """Loaded saved weights and create the network in the C2 workspace."""
    logger = logging.getLogger(__name__)
    add_model_training_inputs(model)

    if cfg.TRAIN.WEIGHTS:
        # Override random weight initialization with weights from a saved model
        nu.initialize_gpu_0_from_weights_file(model, cfg.TRAIN.WEIGHTS)
    # Even if we're randomly initializing we still need to synchronize
    # parameters across GPUs
    nu.broadcast_parameters(model)
    workspace.CreateNet(model.net)

    logger.info('Outputs saved to: {:s}'.format(os.path.abspath(output_dir)))
    dump_proto_files(model, output_dir)

    # Start loading mini-batches and enqueuing blobs
    model.roi_data_loader.register_sigint_handler()
    model.roi_data_loader.start(prefill=True)
    return output_dir
Example #14
Source File: train.py    From Detectron-Cascade-RCNN with Apache License 2.0 6 votes vote down vote up 
def setup_model_for_training(model, weights_file, output_dir):
    """Loaded saved weights and create the network in the C2 workspace."""
    logger = logging.getLogger(__name__)
    add_model_training_inputs(model)

    if weights_file:
        # Override random weight initialization with weights from a saved model
        nu.initialize_gpu_from_weights_file(model, weights_file, gpu_id=0)
    # Even if we're randomly initializing we still need to synchronize
    # parameters across GPUs
    nu.broadcast_parameters(model)
    workspace.CreateNet(model.net)

    logger.info('Outputs saved to: {:s}'.format(os.path.abspath(output_dir)))
    dump_proto_files(model, output_dir)

    # Start loading mini-batches and enqueuing blobs
    model.roi_data_loader.register_sigint_handler()
    model.roi_data_loader.start(prefill=True)
    return output_dir
Example #15
Source File: test_batch_permutation_op.py    From Detectron-Cascade-RCNN with Apache License 2.0 6 votes vote down vote up 
def _run_speed_test(self, iters=5, N=1024):
        """This function provides an example of how to benchmark custom
        operators using the Caffe2 'prof_dag' network execution type. Please
        note that for 'prof_dag' to work, Caffe2 must be compiled with profiling
        support using the `-DUSE_PROF=ON` option passed to `cmake` when building
        Caffe2.
        """
        net = core.Net('test')
        net.Proto().type = 'prof_dag'
        net.Proto().num_workers = 2
        Y = net.BatchPermutation(['X', 'I'], 'Y')
        Y_flat = net.FlattenToVec([Y], 'Y_flat')
        loss = net.AveragedLoss([Y_flat], 'loss')
        net.AddGradientOperators([loss])
        workspace.CreateNet(net)

        X = np.random.randn(N, 256, 14, 14)
        for _i in range(iters):
            I = np.random.permutation(N)
            workspace.FeedBlob('X', X.astype(np.float32))
            workspace.FeedBlob('I', I.astype(np.int32))
            workspace.RunNet(net.Proto().name)
            np.testing.assert_allclose(
                workspace.FetchBlob('Y'), X[I], rtol=1e-5, atol=1e-08
            )
Example #16
Source File: model_utils.py    From models with Apache License 2.0 6 votes vote down vote up 
def load_model_pb(net_file, init_file=None, is_run_init=True, is_create_net=True):
    net = core.Net("net")
    if net_file is not None:
        net.Proto().ParseFromString(open(net_file, "rb").read())

    if init_file is None:
        fn, ext = os.path.splitext(net_file)
        init_file = fn + "_init" + ext

    init_net = caffe2_pb2.NetDef()
    init_net.ParseFromString(open(init_file, "rb").read())

    if is_run_init:
        workspace.RunNetOnce(init_net)
        create_blobs_if_not_existed(net.external_inputs)
        if net.Proto().name == "":
            net.Proto().name = "net"
    if is_create_net:
        workspace.CreateNet(net)

    return (net, init_net)
Example #17
Source File: train.py    From Detectron with Apache License 2.0 6 votes vote down vote up 
def setup_model_for_training(model, weights_file, output_dir):
    """Loaded saved weights and create the network in the C2 workspace."""
    logger = logging.getLogger(__name__)
    add_model_training_inputs(model)

    if weights_file:
        # Override random weight initialization with weights from a saved model
        nu.initialize_gpu_from_weights_file(model, weights_file, gpu_id=0)
    # Even if we're randomly initializing we still need to synchronize
    # parameters across GPUs
    nu.broadcast_parameters(model)
    workspace.CreateNet(model.net)

    logger.info('Outputs saved to: {:s}'.format(os.path.abspath(output_dir)))
    dump_proto_files(model, output_dir)

    # Start loading mini-batches and enqueuing blobs
    model.roi_data_loader.register_sigint_handler()
    model.roi_data_loader.start(prefill=True)
    return output_dir
Example #18
Source File: test_batch_permutation_op.py    From Detectron with Apache License 2.0 6 votes vote down vote up 
def _run_speed_test(self, iters=5, N=1024):
        """This function provides an example of how to benchmark custom
        operators using the Caffe2 'prof_dag' network execution type. Please
        note that for 'prof_dag' to work, Caffe2 must be compiled with profiling
        support using the `-DUSE_PROF=ON` option passed to `cmake` when building
        Caffe2.
        """
        net = core.Net('test')
        net.Proto().type = 'prof_dag'
        net.Proto().num_workers = 2
        Y = net.BatchPermutation(['X', 'I'], 'Y')
        Y_flat = net.FlattenToVec([Y], 'Y_flat')
        loss = net.AveragedLoss([Y_flat], 'loss')
        net.AddGradientOperators([loss])
        workspace.CreateNet(net)

        X = np.random.randn(N, 256, 14, 14)
        for _i in range(iters):
            I = np.random.permutation(N)
            workspace.FeedBlob('X', X.astype(np.float32))
            workspace.FeedBlob('I', I.astype(np.int32))
            workspace.RunNet(net.Proto().name)
            np.testing.assert_allclose(
                workspace.FetchBlob('Y'), X[I], rtol=1e-5, atol=1e-08
            )
Example #19
Source File: test_engine.py    From Detectron with Apache License 2.0 6 votes vote down vote up 
def initialize_model_from_cfg(weights_file, gpu_id=0):
    """Initialize a model from the global cfg. Loads test-time weights and
    creates the networks in the Caffe2 workspace.
    """
    model = model_builder.create(cfg.MODEL.TYPE, train=False, gpu_id=gpu_id)
    net_utils.initialize_gpu_from_weights_file(
        model, weights_file, gpu_id=gpu_id,
    )
    model_builder.add_inference_inputs(model)
    workspace.CreateNet(model.net)
    workspace.CreateNet(model.conv_body_net)
    if cfg.MODEL.MASK_ON:
        workspace.CreateNet(model.mask_net)
    if cfg.MODEL.KEYPOINTS_ON:
        workspace.CreateNet(model.keypoint_net)
    return model
Example #20
Source File: train.py    From Detectron-DA-Faster-RCNN with Apache License 2.0 6 votes vote down vote up 
def setup_model_for_training(model, weights_file, output_dir):
    """Loaded saved weights and create the network in the C2 workspace."""
    logger = logging.getLogger(__name__)
    if cfg.TRAIN.DOMAIN_ADAPTATION:
        add_model_da_training_inputs(model)
    else:
        add_model_training_inputs(model)

    if weights_file:
        # Override random weight initialization with weights from a saved model
        nu.initialize_gpu_from_weights_file(model, weights_file, gpu_id=0)
    # Even if we're randomly initializing we still need to synchronize
    # parameters across GPUs
    nu.broadcast_parameters(model)
    workspace.CreateNet(model.net)

    logger.info('Outputs saved to: {:s}'.format(os.path.abspath(output_dir)))
    dump_proto_files(model, output_dir)

    # Start loading mini-batches and enqueuing blobs
    model.roi_data_loader.register_sigint_handler()
    model.roi_data_loader.start(prefill=True)
    return output_dir
Example #21
Source File: test_batch_permutation_op.py    From Detectron-DA-Faster-RCNN with Apache License 2.0 6 votes vote down vote up 
def _run_speed_test(self, iters=5, N=1024):
        """This function provides an example of how to benchmark custom
        operators using the Caffe2 'prof_dag' network execution type. Please
        note that for 'prof_dag' to work, Caffe2 must be compiled with profiling
        support using the `-DUSE_PROF=ON` option passed to `cmake` when building
        Caffe2.
        """
        net = core.Net('test')
        net.Proto().type = 'prof_dag'
        net.Proto().num_workers = 2
        Y = net.BatchPermutation(['X', 'I'], 'Y')
        Y_flat = net.FlattenToVec([Y], 'Y_flat')
        loss = net.AveragedLoss([Y_flat], 'loss')
        net.AddGradientOperators([loss])
        workspace.CreateNet(net)

        X = np.random.randn(N, 256, 14, 14)
        for _i in range(iters):
            I = np.random.permutation(N)
            workspace.FeedBlob('X', X.astype(np.float32))
            workspace.FeedBlob('I', I.astype(np.int32))
            workspace.RunNet(net.Proto().name)
            np.testing.assert_allclose(
                workspace.FetchBlob('Y'), X[I], rtol=1e-5, atol=1e-08
            )
Example #22
Source File: test_engine.py    From Detectron-DA-Faster-RCNN with Apache License 2.0 6 votes vote down vote up 
def initialize_model_from_cfg(weights_file, gpu_id=0):
    """Initialize a model from the global cfg. Loads test-time weights and
    creates the networks in the Caffe2 workspace.
    """
    model = model_builder.create(cfg.MODEL.TYPE, train=False, gpu_id=gpu_id)
    net_utils.initialize_gpu_from_weights_file(
        model, weights_file, gpu_id=gpu_id,
    )
    model_builder.add_inference_inputs(model)
    workspace.CreateNet(model.net)
    workspace.CreateNet(model.conv_body_net)
    if cfg.MODEL.MASK_ON:
        workspace.CreateNet(model.mask_net)
    if cfg.MODEL.KEYPOINTS_ON:
        workspace.CreateNet(model.keypoint_net)
    return model
Example #23
Source File: train.py    From CBNet with Apache License 2.0 6 votes vote down vote up 
def setup_model_for_training(model, weights_file, output_dir):
    """Loaded saved weights and create the network in the C2 workspace."""
    logger = logging.getLogger(__name__)
    add_model_training_inputs(model)

    if weights_file:
        # Override random weight initialization with weights from a saved model
        nu.initialize_gpu_from_weights_file(model, weights_file, gpu_id=0)
        nu.initialize_gpu_from_old_weights_file(model, weights_file, gpu_id=0)
    # Even if we're randomly initializing we still need to synchronize
    # parameters across GPUs
    nu.broadcast_parameters(model)
    workspace.CreateNet(model.net)

    logger.info('Outputs saved to: {:s}'.format(os.path.abspath(output_dir)))
    dump_proto_files(model, output_dir)

    # Start loading mini-batches and enqueuing blobs
    model.roi_data_loader.register_sigint_handler()
    model.roi_data_loader.start(prefill=True)
    return output_dir
Example #24
Source File: test_batch_permutation_op.py    From CBNet with Apache License 2.0 6 votes vote down vote up 
def _run_speed_test(self, iters=5, N=1024):
        """This function provides an example of how to benchmark custom
        operators using the Caffe2 'prof_dag' network execution type. Please
        note that for 'prof_dag' to work, Caffe2 must be compiled with profiling
        support using the `-DUSE_PROF=ON` option passed to `cmake` when building
        Caffe2.
        """
        net = core.Net('test')
        net.Proto().type = 'prof_dag'
        net.Proto().num_workers = 2
        Y = net.BatchPermutation(['X', 'I'], 'Y')
        Y_flat = net.FlattenToVec([Y], 'Y_flat')
        loss = net.AveragedLoss([Y_flat], 'loss')
        net.AddGradientOperators([loss])
        workspace.CreateNet(net)

        X = np.random.randn(N, 256, 14, 14)
        for _i in range(iters):
            I = np.random.permutation(N)
            workspace.FeedBlob('X', X.astype(np.float32))
            workspace.FeedBlob('I', I.astype(np.int32))
            workspace.RunNet(net.Proto().name)
            np.testing.assert_allclose(
                workspace.FetchBlob('Y'), X[I], rtol=1e-5, atol=1e-08
            )
Example #25
Source File: test_engine.py    From CBNet with Apache License 2.0 6 votes vote down vote up 
def initialize_model_from_cfg(weights_file, gpu_id=0):
    """Initialize a model from the global cfg. Loads test-time weights and
    creates the networks in the Caffe2 workspace.
    """
    model = model_builder.create(cfg.MODEL.TYPE, train=False, gpu_id=gpu_id)
    net_utils.initialize_gpu_from_weights_file(
        model, weights_file, gpu_id=gpu_id,
    )
    model_builder.add_inference_inputs(model)
    workspace.CreateNet(model.net)
    workspace.CreateNet(model.conv_body_net)
    if cfg.MODEL.MASK_ON:
        workspace.CreateNet(model.mask_net)
    if cfg.MODEL.KEYPOINTS_ON:
        workspace.CreateNet(model.keypoint_net)
    return model
Example #26
Source File: test_batch_permutation_op.py    From NucleiDetectron with Apache License 2.0 6 votes vote down vote up 
def _run_speed_test(self, iters=5, N=1024):
        """This function provides an example of how to benchmark custom
        operators using the Caffe2 'prof_dag' network execution type. Please
        note that for 'prof_dag' to work, Caffe2 must be compiled with profiling
        support using the `-DUSE_PROF=ON` option passed to `cmake` when building
        Caffe2.
        """
        net = core.Net('test')
        net.Proto().type = 'prof_dag'
        net.Proto().num_workers = 2
        Y = net.BatchPermutation(['X', 'I'], 'Y')
        Y_flat = net.FlattenToVec([Y], 'Y_flat')
        loss = net.AveragedLoss([Y_flat], 'loss')
        net.AddGradientOperators([loss])
        workspace.CreateNet(net)

        X = np.random.randn(N, 256, 14, 14)
        for _i in range(iters):
            I = np.random.permutation(N)
            workspace.FeedBlob('X', X.astype(np.float32))
            workspace.FeedBlob('I', I.astype(np.int32))
            workspace.RunNet(net.Proto().name)
            np.testing.assert_allclose(
                workspace.FetchBlob('Y'), X[I], rtol=1e-5, atol=1e-08
            )
Example #27
Source File: test_engine.py    From NucleiDetectron with Apache License 2.0 6 votes vote down vote up 
def initialize_model_from_cfg(gpu_id=0):
    """Initialize a model from the global cfg. Loads test-time weights and
    creates the networks in the Caffe2 workspace.
    """
    model = model_builder.create(cfg.MODEL.TYPE, train=False, gpu_id=gpu_id)
    net_utils.initialize_gpu_from_weights_file(
        model, cfg.TEST.WEIGHTS, gpu_id=gpu_id,
    )
    model_builder.add_inference_inputs(model)
    workspace.CreateNet(model.net)
    workspace.CreateNet(model.conv_body_net)
    if cfg.MODEL.MASK_ON:
        workspace.CreateNet(model.mask_net)
    if cfg.MODEL.KEYPOINTS_ON:
        workspace.CreateNet(model.keypoint_net)
    return model
Example #28
Source File: train_net.py    From NucleiDetectron with Apache License 2.0 6 votes vote down vote up 
def setup_model_for_training(model, output_dir):
    """Loaded saved weights and create the network in the C2 workspace."""
    logger = logging.getLogger(__name__)
    add_model_training_inputs(model)

    if cfg.TRAIN.WEIGHTS:
        # Override random weight initialization with weights from a saved model
        nu.initialize_gpu_from_weights_file(model, cfg.TRAIN.WEIGHTS, gpu_id=0)
    # Even if we're randomly initializing we still need to synchronize
    # parameters across GPUs
    nu.broadcast_parameters(model)
    workspace.CreateNet(model.net)

    logger.info('Outputs saved to: {:s}'.format(os.path.abspath(output_dir)))
    dump_proto_files(model, output_dir)

    # Start loading mini-batches and enqueuing blobs
    model.roi_data_loader.register_sigint_handler()
    model.roi_data_loader.start(prefill=True)
    return output_dir
Example #29
Source File: test_batch_permutation_op.py    From DetectAndTrack with Apache License 2.0 6 votes vote down vote up 
def _run_speed_test(self, iters=5, N=1024):
        """This function provides an example of how to benchmark custom
        operators using the Caffe2 'prof_dag' network execution type. Please
        note that for 'prof_dag' to work, Caffe2 must be compiled with profiling
        support using the `-DUSE_PROF=ON` option passed to `cmake` when building
        Caffe2.
        """
        net = core.Net('test')
        net.Proto().type = 'prof_dag'
        net.Proto().num_workers = 2
        Y = net.BatchPermutation(['X', 'I'], 'Y')
        Y_flat = net.FlattenToVec([Y], 'Y_flat')
        loss = net.AveragedLoss([Y_flat], 'loss')
        net.AddGradientOperators([loss])
        workspace.CreateNet(net)

        X = np.random.randn(N, 256, 14, 14)
        for _i in range(iters):
            I = np.random.permutation(N)
            workspace.FeedBlob('X', X.astype(np.float32))
            workspace.FeedBlob('I', I.astype(np.int32))
            workspace.RunNet(net.Proto().name)
            np.testing.assert_allclose(
                workspace.FetchBlob('Y'), X[I], rtol=1e-5, atol=1e-08
            )
Example #30
Source File: test_engine.py    From DetectAndTrack with Apache License 2.0 6 votes vote down vote up 
def initialize_model_from_cfg():
    def create_input_blobs(net_def):
        for op in net_def.op:
            for blob_in in op.input:
                if not workspace.HasBlob(blob_in):
                    workspace.CreateBlob(blob_in)

    model = model_builder.create(
        cfg.MODEL.TYPE, train=False,
        init_params=cfg.TEST.INIT_RANDOM_VARS_BEFORE_LOADING)
    model_builder.add_inputs(model)
    if cfg.TEST.INIT_RANDOM_VARS_BEFORE_LOADING:
        workspace.RunNetOnce(model.param_init_net)
    net_utils.initialize_from_weights_file(
        model, cfg.TEST.WEIGHTS, broadcast=False)
    create_input_blobs(model.net.Proto())
    workspace.CreateNet(model.net)
    workspace.CreateNet(model.conv_body_net)
    if cfg.MODEL.MASK_ON:
        create_input_blobs(model.mask_net.Proto())
        workspace.CreateNet(model.mask_net)
    if cfg.MODEL.KEYPOINTS_ON:
        create_input_blobs(model.keypoint_net.Proto())
        workspace.CreateNet(model.keypoint_net)
    return model