Python caffe.SGDSolver() Examples

def __init__(self, solver, output_dir, pretrained_model=None, gpu_id=0, data=None):
        """Initialize the SolverWrapper."""
        self.output_dir = output_dir

        caffe.set_mode_gpu()
        caffe.set_device(gpu_id)
        self.solver = caffe.SGDSolver(solver)
        if pretrained_model is not None:
            print(('Loading pretrained model '
                   'weights from {:s}').format(pretrained_model))
            self.solver.net.copy_from(pretrained_model)

        self.solver_param = caffe_pb2.SolverParameter()
        with open(solver, 'rt') as f:
            pb2.text_format.Merge(f.read(), self.solver_param)

        self.solver.net.layers[0].set_data(data) 

def __init__(self, solver_prototxt, roidb, output_dir, pretrained_model=None):
        """Initialize the SolverWrapper."""
        self.output_dir = output_dir

        print 'Computing bounding-box regression targets...'
        if cfg.TRAIN.BBOX_REG:
            if cfg.IS_RPN:
                self.bbox_means, self.bbox_stds = gdl_roidb.add_bbox_regression_targets(roidb)
            else:
                self.bbox_means, self.bbox_stds = rdl_roidb.add_bbox_regression_targets(roidb)
        print 'done'

        self.solver = caffe.SGDSolver(solver_prototxt)
        if pretrained_model is not None:
            print ('Loading pretrained model '
                   'weights from {:s}').format(pretrained_model)
            self.solver.net.copy_from(pretrained_model)

        self.solver_param = caffe_pb2.SolverParameter()
        with open(solver_prototxt, 'rt') as f:
            pb2.text_format.Merge(f.read(), self.solver_param)

        self.solver.net.layers[0].set_roidb(roidb) 

def setUp(self):
        self.num_output = 13
        net_f = simple_net_file(self.num_output)
        f = tempfile.NamedTemporaryFile(delete=False)
        f.write("""net: '""" + net_f + """'
        test_iter: 10 test_interval: 10 base_lr: 0.01 momentum: 0.9
        weight_decay: 0.0005 lr_policy: 'inv' gamma: 0.0001 power: 0.75
        display: 100 max_iter: 100 snapshot_after_train: false""")
        f.close()
        self.solver = caffe.SGDSolver(f.name)
        # also make sure get_solver runs
        caffe.get_solver(f.name)
        caffe.set_mode_cpu()
        # fill in valid labels
        self.solver.net.blobs['label'].data[...] = \
                np.random.randint(self.num_output,
                    size=self.solver.net.blobs['label'].data.shape)
        self.solver.test_nets[0].blobs['label'].data[...] = \
                np.random.randint(self.num_output,
                    size=self.solver.test_nets[0].blobs['label'].data.shape)
        os.remove(f.name)
        os.remove(net_f) 

def setUp(self):
        self.num_output = 13
        net_f = simple_net_file(self.num_output)
        f = tempfile.NamedTemporaryFile(mode='w+', delete=False)
        f.write("""net: '""" + net_f + """'
        test_iter: 10 test_interval: 10 base_lr: 0.01 momentum: 0.9
        weight_decay: 0.0005 lr_policy: 'inv' gamma: 0.0001 power: 0.75
        display: 100 max_iter: 100 snapshot_after_train: false
        snapshot_prefix: "model" """)
        f.close()
        self.solver = caffe.SGDSolver(f.name)
        # also make sure get_solver runs
        caffe.get_solver(f.name)
        caffe.set_mode_cpu()
        # fill in valid labels
        self.solver.net.blobs['label'].data[...] = \
                np.random.randint(self.num_output,
                    size=self.solver.net.blobs['label'].data.shape)
        self.solver.test_nets[0].blobs['label'].data[...] = \
                np.random.randint(self.num_output,
                    size=self.solver.test_nets[0].blobs['label'].data.shape)
        os.remove(f.name)
        os.remove(net_f) 

def solve(proto, snapshot, gpus, timing, uid, rank):
    caffe.set_mode_gpu()
    caffe.set_device(gpus[rank])
    caffe.set_solver_count(len(gpus))
    caffe.set_solver_rank(rank)
    caffe.set_multiprocess(True)

    solver = caffe.SGDSolver(proto)
    if snapshot and len(snapshot) != 0:
        solver.restore(snapshot)

    nccl = caffe.NCCL(solver, uid)
    nccl.bcast()

    if timing and rank == 0:
        time(solver, nccl)
    else:
        solver.add_callback(nccl)

    if solver.param.layer_wise_reduce:
        solver.net.after_backward(nccl)
    solver.step(solver.param.max_iter) 

def __init__(self, solver_prototxt, output_dir,
                 pretrained_model=None):
        """Initialize the SolverWrapper."""
        self.output_dir = output_dir

        caffe.set_mode_gpu()
        caffe.set_device(0)
        self.solver = caffe.SGDSolver(solver_prototxt)
        if pretrained_model is not None:
            print ('Loading pretrained model '
                   'weights from {:s}').format(pretrained_model)
            self.solver.net.copy_from(pretrained_model)

        self.solver_param = caffe_pb2.SolverParameter()
        with open(solver_prototxt, 'rt') as f:
            pb2.text_format.Merge(f.read(), self.solver_param) 

def solve(proto, snapshot, gpus, timing, uid, rank):
    caffe.set_mode_gpu()
    caffe.set_device(gpus[rank])
    caffe.set_solver_count(len(gpus))
    caffe.set_solver_rank(rank)
    caffe.set_multiprocess(True)

    solver = caffe.SGDSolver(proto)
    if snapshot and len(snapshot) != 0:
        solver.restore(snapshot)

    nccl = caffe.NCCL(solver, uid)
    nccl.bcast()

    if timing and rank == 0:
        time(solver, nccl)
    else:
        solver.add_callback(nccl)

    if solver.param.layer_wise_reduce:
        solver.net.after_backward(nccl)
    solver.step(solver.param.max_iter) 

def solve(proto, snapshot, gpus, timing, uid, rank):
    caffe.set_mode_gpu()
    caffe.set_device(gpus[rank])
    caffe.set_solver_count(len(gpus))
    caffe.set_solver_rank(rank)
    caffe.set_multiprocess(True)

    solver = caffe.SGDSolver(proto)
    if snapshot and len(snapshot) != 0:
        solver.restore(snapshot)

    nccl = caffe.NCCL(solver, uid)
    nccl.bcast()

    if timing and rank == 0:
        time(solver, nccl)
    else:
        solver.add_callback(nccl)

    if solver.param.layer_wise_reduce:
        solver.net.after_backward(nccl)
    solver.step(solver.param.max_iter) 

def solve(proto, snapshot, gpus, timing, uid, rank):
    caffe.set_mode_gpu()
    caffe.set_device(gpus[rank])
    caffe.set_solver_count(len(gpus))
    caffe.set_solver_rank(rank)
    caffe.set_multiprocess(True)

    solver = caffe.SGDSolver(proto)
    if snapshot and len(snapshot) != 0:
        solver.restore(snapshot)

    nccl = caffe.NCCL(solver, uid)
    nccl.bcast()

    if timing and rank == 0:
        time(solver, nccl)
    else:
        solver.add_callback(nccl)

    if solver.param.layer_wise_reduce:
        solver.net.after_backward(nccl)
    solver.step(solver.param.max_iter) 

def __init__(self, solver_prototxt, db, output_dir, do_flip,
                 snapshot_path=None):
        """Initialize the SolverWrapper."""
        self._output_dir = output_dir
        self._solver = caffe.SGDSolver(solver_prototxt)

        self._solver_param = caffe_pb2.SolverParameter()
        with open(solver_prototxt, 'rt') as f:
            pb2.text_format.Merge(f.read(), self._solver_param)

        infix = ('_' + cfg.TRAIN.SNAPSHOT_INFIX
                 if cfg.TRAIN.SNAPSHOT_INFIX != '' else '')
        self._snapshot_prefix = self._solver_param.snapshot_prefix + infix + '_iter_'

        if snapshot_path is not None:
            print ('Loading snapshot weights from {:s}').format(snapshot_path)
            self._solver.net.copy_from(snapshot_path)

            snapshot_path = snapshot_path.split('/')[-1]
            if snapshot_path.startswith(self._snapshot_prefix):
                print 'Warning! Existing snapshots may be overriden by new snapshots!'
 
        self._db = db
        self._solver.net.layers[0].set_db(self._db, do_flip) 

def solve(proto, snapshot, gpus, timing, uid, rank):
    caffe.set_mode_gpu()
    caffe.set_device(gpus[rank])
    caffe.set_solver_count(len(gpus))
    caffe.set_solver_rank(rank)
    caffe.set_multiprocess(True)

    solver = caffe.SGDSolver(proto)
    if snapshot and len(snapshot) != 0:
        solver.restore(snapshot)

    nccl = caffe.NCCL(solver, uid)
    nccl.bcast()

    if timing and rank == 0:
        time(solver, nccl)
    else:
        solver.add_callback(nccl)

    if solver.param.layer_wise_reduce:
        solver.net.after_backward(nccl)
    solver.step(solver.param.max_iter) 

def load_nets(args, cur_gpu):
    # initialize solver and feature net,
    # RNN should be initialized before CNN, because CNN cudnn conv layers
    # may assume using all available memory
    caffe.set_mode_gpu()
    caffe.set_device(cur_gpu)
    solver = caffe.SGDSolver(args.solver)
    if args.snapshot:
        print "Restoring history from {}".format(args.snapshot)
        solver.restore(args.snapshot)
    net = solver.net
    if args.weights:
        print "Copying weights from {}".format(args.weights)
        net.copy_from(args.weights)

    return solver, net 

def load_nets(args, cur_gpu):
    # initialize solver and feature net,
    # RNN should be initialized before CNN, because CNN cudnn conv layers
    # may assume using all available memory
    caffe.set_mode_gpu()
    caffe.set_device(cur_gpu)
    solver = caffe.SGDSolver(args.solver)
    if args.snapshot:
        print "Restoring history from {}".format(args.snapshot)
        solver.restore(args.snapshot)
    rnn = solver.net
    if args.weights:
        rnn.copy_from(args.weights)
    feature_net = caffe.Net(args.feature_net, args.feature_param, caffe.TEST)

    # apply bbox regression normalization on the net weights
    with open(args.bbox_mean, 'rb') as f:
        bbox_means = cPickle.load(f)
    with open(args.bbox_std, 'rb') as f:
        bbox_stds = cPickle.load(f)
    feature_net.params['bbox_pred_vid'][0].data[...] = \
        feature_net.params['bbox_pred_vid'][0].data * bbox_stds[:, np.newaxis]
    feature_net.params['bbox_pred_vid'][1].data[...] = \
        feature_net.params['bbox_pred_vid'][1].data * bbox_stds + bbox_means
    return solver, feature_net, rnn, bbox_means, bbox_stds 

def solve(proto, gpus, uid, rank, max_iter):
    caffe.set_mode_gpu()
    caffe.set_device(gpus[rank])
    caffe.set_solver_count(len(gpus))
    caffe.set_solver_rank(rank)
    caffe.set_multiprocess(True)

    solver = caffe.SGDSolver(proto)
    if rank == 0:
        # solver.restore(_snapshot)
        solver.net.copy_from(_weights)
    
    solver.net.layers[0].get_gpu_id(gpus[rank])

    nccl = caffe.NCCL(solver, uid)
    nccl.bcast()
    solver.add_callback(nccl)

    if solver.param.layer_wise_reduce:
        solver.net.after_backward(nccl)

    for _ in range(max_iter):
        solver.step(1) 

def __init__(self, solver_prototxt, roidb, output_dir,
                 pretrained_model=None):
        """Initialize the SolverWrapper."""
        self.output_dir = output_dir

        print 'done'

        self.solver = caffe.SGDSolver(solver_prototxt)
        if pretrained_model is not None:
            print ('Loading pretrained model '
                   'weights from {:s}').format(pretrained_model)
            self.solver.net.copy_from(pretrained_model)
        self.solver_param = caffe_pb2.SolverParameter()
        with open(solver_prototxt, 'rt') as f:
            pb2.text_format.Merge(f.read(), self.solver_param)

        self.solver.net.layers[0].set_roidb(roidb) 

def __init__(self, solver_prototxt, roidb, output_dir,
                 pretrained_model=None):
        """Initialize the SolverWrapper."""
        self.output_dir = output_dir

        if (cfg.TRAIN.HAS_RPN and cfg.TRAIN.BBOX_REG and
            cfg.TRAIN.BBOX_NORMALIZE_TARGETS):
            # RPN can only use precomputed normalization because there are no
            # fixed statistics to compute a priori
            assert cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED

        if cfg.TRAIN.BBOX_REG:
            print 'Computing bounding-box regression targets...'
            self.bbox_means, self.bbox_stds = \
                    rdl_roidb.add_bbox_regression_targets(roidb)
            print 'done'

        self.solver = caffe.SGDSolver(solver_prototxt)
        if pretrained_model is not None:
            print ('Loading pretrained model '
                   'weights from {:s}').format(pretrained_model)
            self.solver.net.copy_from(pretrained_model)

        self.solver_param = caffe_pb2.SolverParameter()
        with open(solver_prototxt, 'rt') as f:
            pb2.text_format.Merge(f.read(), self.solver_param)

        self.solver.net.layers[0].set_roidb(roidb) 

def __init__(self, solver_prototxt, pretrained_model=None, snapshot_model=None):
        """Initialize the SolverWrapper."""

        self.solver = caffe.SGDSolver(solver_prototxt)
        if snapshot_model is not None:
            self.solver.restore(snapshot_model)
        elif pretrained_model is not None:
            print ('Loading pretrained model '
                   'weights from {:s}').format(pretrained_model)
            self.solver.net.copy_from(pretrained_model) 

def __init__(self, solver_prototxt, roidb, output_dir,
                 pretrained_model=None):
        """Initialize the SolverWrapper."""
        self.output_dir = output_dir

        self.solver = caffe.SGDSolver(solver_prototxt)
        if pretrained_model is not None:
            print ('Loading pretrained model '
                   'weights from {:s}').format(pretrained_model)
            self.solver.net.copy_from(pretrained_model)
        self.solver_param = caffe_pb2.SolverParameter()
        with open(solver_prototxt, 'rt') as f:
            text_format.Merge(f.read(), self.solver_param)

        self.solver.net.layers[0].set_roidb(roidb) 

def __init__(self, solver_prototxt, pretrained_model=None):
        """Initialize the SolverWrapper."""

        self.solver = caffe.SGDSolver(solver_prototxt)
        if pretrained_model is not None:
            print ('Loading pretrained model '
                   'weights from {:s}').format(pretrained_model)
            self.solver.net.copy_from(pretrained_model) 

def __init__(self, solver_prototxt, pretrained_model=None, snapshot_model=None):
        """Initialize the SolverWrapper."""

        self.solver = caffe.SGDSolver(solver_prototxt)
        if snapshot_model is not None:
            self.solver.restore(snapshot_model)
        elif pretrained_model is not None:
            print ('Loading pretrained model '
                   'weights from {:s}').format(pretrained_model)
            self.solver.net.copy_from(pretrained_model) 

def cpu_solve(proto, snapshot, timing):
    caffe.set_mode_cpu()

    solver = caffe.SGDSolver(proto)
    if snapshot and len(snapshot) != 0:
        solver.restore(snapshot)

    solver.step(solver.param.max_iter) 

def __init__(self, solver_prototxt, roidb, output_dir,
                 pretrained_model=None):
        """Initialize the SolverWrapper."""
        self.output_dir = output_dir

        if (cfg.TRAIN.HAS_RPN and cfg.TRAIN.BBOX_REG and
            cfg.TRAIN.BBOX_NORMALIZE_TARGETS):
            # RPN can only use precomputed normalization because there are no
            # fixed statistics to compute a priori
            assert cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED

        if cfg.TRAIN.BBOX_REG:
            print 'Computing bounding-box regression targets...'
            self.bbox_means, self.bbox_stds = \
                    rdl_roidb.add_bbox_regression_targets(roidb)
            print 'done'

        self.solver = caffe.SGDSolver(solver_prototxt)
        if pretrained_model is not None:
            print ('Loading pretrained model '
                   'weights from {:s}').format(pretrained_model)
            self.solver.net.copy_from(pretrained_model)

        self.solver_param = caffe_pb2.SolverParameter()
        with open(solver_prototxt, 'rt') as f:
            pb2.text_format.Merge(f.read(), self.solver_param)

        self.solver.net.layers[0].set_roidb(roidb) 

def view_blob_label_segm(nb_imgs, path_solver):
    
    solver = caffe.SGDSolver(path_solver)
     
    for _ in xrange(nb_imgs):
         
        solver.net.forward()  # train net
         
        d = solver.net.blobs['data'].data
        print d.shape
        d = np.squeeze(d, axis=(0,)) # get rid of batch elements dimensions
        y = cv2.cvtColor(cv2.merge([ch for ch in d]), cv.CV_RGB2BGR)
         
        #print y.dtype, y.max()
         
        cv2.imshow('data', y)
         
        d = solver.net.blobs['label'].data
        print d.shape
        d = np.squeeze(d, axis=(0,))
        
        print d
        
        cv2.waitKey()
        
    return 0 

def cpu_solve(proto, snapshot, timing):
    caffe.set_mode_cpu()

    solver = caffe.SGDSolver(proto)
    if snapshot and len(snapshot) != 0:
        solver.restore(snapshot)

    solver.step(solver.param.max_iter) 

def __init__(self, solver_prototxt, roidb, output_dir,
                 pretrained_model=None):
        """Initialize the SolverWrapper."""
        self.output_dir = output_dir

        if (cfg.TRAIN.HAS_RPN and cfg.TRAIN.BBOX_REG and
            cfg.TRAIN.BBOX_NORMALIZE_TARGETS):
            # RPN can only use precomputed normalization because there are no
            # fixed statistics to compute a priori
            assert cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED

        if cfg.TRAIN.BBOX_REG:
            print 'Computing bounding-box regression targets...'
            self.bbox_means, self.bbox_stds = \
                    rdl_roidb.add_bbox_regression_targets(roidb)
            print 'done'

        self.solver = caffe.SGDSolver(solver_prototxt)
        if pretrained_model is not None:
            print ('Loading pretrained model '
                   'weights from {:s}').format(pretrained_model)
            self.solver.net.copy_from(pretrained_model)

        self.solver_param = caffe_pb2.SolverParameter()
        with open(solver_prototxt, 'rt') as f:
            pb2.text_format.Merge(f.read(), self.solver_param)

        self.solver.net.layers[0].set_roidb(roidb) 

def cpu_solve(proto, snapshot, timing):
    caffe.set_mode_cpu()

    solver = caffe.SGDSolver(proto)
    if snapshot and len(snapshot) != 0:
        solver.restore(snapshot)

    solver.step(solver.param.max_iter) 

def cpu_solve(proto, snapshot, timing):
    caffe.set_mode_cpu()

    solver = caffe.SGDSolver(proto)
    if snapshot and len(snapshot) != 0:
        solver.restore(snapshot)

    solver.step(solver.param.max_iter) 

def text_save(content,filename,mode='a'):
    # Try to save a list variable in txt file.
    file = open(filename,mode)
    for i in range(len(content)):
        file.write(str(content[i])+' ')
    file.write('\n')
    file.close()

# savefile = 'frame_feat_flow.txt'
# if os.path.isfile(savefile):
#     os.remove(savefile)
#
# solver = caffe.SGDSolver(relative_path + '/deeptemporal/models/ucf101/flow_feat_solver.prototxt')
# solver.net.copy_from(relative_path + "/ucf101_split_1_rgb_flow_models/ucf101_split_1_tsn_flow_reference_bn_inception.caffemodel") 

def __init__(self, solver_prototxt, roidb, output_dir,
                 pretrained_model=None):
        """Initialize the SolverWrapper."""
        self.output_dir = output_dir

        if (cfg.TRAIN.HAS_RPN and cfg.TRAIN.BBOX_REG and
            cfg.TRAIN.BBOX_NORMALIZE_TARGETS):
            # RPN can only use precomputed normalization because there are no
            # fixed statistics to compute a priori
            assert cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED

        if cfg.TRAIN.BBOX_REG:
            print 'Computing bounding-box regression targets...'
            self.bbox_means, self.bbox_stds = \
                    rdl_roidb.add_bbox_regression_targets(roidb)
            print 'done'

        self.solver = caffe.SGDSolver(solver_prototxt)
        if pretrained_model is not None:
            print ('Loading pretrained model '
                   'weights from {:s}').format(pretrained_model)
            self.solver.net.copy_from(pretrained_model)

        self.solver_param = caffe_pb2.SolverParameter()
        with open(solver_prototxt, 'rt') as f:
            pb2.text_format.Merge(f.read(), self.solver_param)

        self.solver.net.layers[0].set_roidb(roidb) 

def __init__(self, solver_prototxt, roidb, output_dir,
                 pretrained_model=None):
        """Initialize the SolverWrapper."""
        self.output_dir = output_dir

        if (cfg.TRAIN.HAS_RPN and cfg.TRAIN.BBOX_REG and
            cfg.TRAIN.BBOX_NORMALIZE_TARGETS):
            # RPN can only use precomputed normalization because there are no
            # fixed statistics to compute a priori
            assert cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED

        if cfg.TRAIN.BBOX_REG:
            print 'Computing bounding-box regression targets...'
            self.bbox_means, self.bbox_stds = \
                    rdl_roidb.add_bbox_regression_targets(roidb)
            print 'done'

        self.solver = caffe.SGDSolver(solver_prototxt)
        if pretrained_model is not None:
            print ('Loading pretrained model '
                   'weights from {:s}').format(pretrained_model)
            self.solver.net.copy_from(pretrained_model)

        self.solver_param = caffe_pb2.SolverParameter()
        with open(solver_prototxt, 'rt') as f:
            pb2.text_format.Merge(f.read(), self.solver_param)

        self.solver.net.layers[0].set_roidb(roidb)