예제 #1
0
    def update_stats(self):
        """
        Update the model with precise statistics. Users can manually call this method.
        """
        if self._disabled:
            return

        def data_loader():
            for num_iter in itertools.count(1):
                if num_iter % 100 == 0:
                    self._logger.info(
                        "Running precise-BN ... {}/{} iterations.".format(
                            num_iter, self._num_iter))
                # This way we can reuse the same iterator
                try:
                    item = next(self._data_iter)
                except StopIteration:
                    self._data_iter = iter(self._data_loader)
                    item = next(self._data_iter)

                yield item

        with EventStorage():  # capture events in a new storage to discard them
            self._logger.info(
                "Running precise-BN for {} iterations...  ".format(
                    self._num_iter) +
                "Note that this could produce different statistics every time."
            )
            update_bn_stats(self._model, data_loader(), self._num_iter)
예제 #2
0
    def testScalarMismatchedPeriod(self):
        with tempfile.TemporaryDirectory(
                prefix="cvpods_tests") as dir, EventStorage() as storage:
            json_file = os.path.join(dir, "test.json")

            writer = JSONWriter(json_file)
            for k in range(60):
                if k % 17 == 0:  # write in a differnt period
                    storage.put_scalar("key2", k, smoothing_hint=False)
                storage.put_scalar("key", k, smoothing_hint=False)
                if (k + 1) % 20 == 0:
                    writer.write()
                storage.step()
            writer.close()
            with open(json_file) as f:
                data = [json.loads(line) for line in f]
                print([int(k.get("key2", 0)) for k in data])
                print([int(k.get("key", 0)) for k in data])
                print([int(k.get("iteration", 0)) for k in data])
                self.assertTrue([int(k.get("key2", 0))
                                 for k in data] == [17, 0, 34, 0, 51, 0])
                self.assertTrue([int(k.get("key", 0))
                                 for k in data] == [0, 19, 0, 39, 0, 59])
                self.assertTrue([int(k["iteration"])
                                 for k in data] == [17, 19, 34, 39, 51, 59])
예제 #3
0
    def test_rroi_heads(self):
        torch.manual_seed(121)
        cfg = RCNNConfig()
        cfg.MODEL.ANCHOR_GENERATOR.NAME = "RotatedAnchorGenerator"
        # PROPOSAL_GENERATOR: "RRPN"
        # ROI_HEADS: "RROIHeads"
        # ROI_BOX_HEAD.NAME: "FastRCNNConvFCHead"

        def build_box_head(cfg, input_shape):
            return FastRCNNConvFCHead(cfg, input_shape)
        cfg.build_box_head = build_box_head

        cfg.MODEL.RESNETS.DEPTH = 50
        cfg.MODEL.ROI_BOX_HEAD.NUM_FC = 2
        cfg.MODEL.RPN.BBOX_REG_WEIGHTS = (1, 1, 1, 1, 1)
        cfg.MODEL.RPN.HEAD_NAME = "StandardRPNHead"
        cfg.MODEL.ROI_BOX_HEAD.POOLER_TYPE = "ROIAlignRotated"
        cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_WEIGHTS = (10, 10, 5, 5, 1)
        backbone = build_backbone(cfg)
        num_images = 2
        images_tensor = torch.rand(num_images, 20, 30)
        image_sizes = [(10, 10), (20, 30)]
        images = ImageList(images_tensor, image_sizes)
        num_channels = 1024
        features = {"res4": torch.rand(num_images, num_channels, 1, 2)}

        image_shape = (15, 15)
        gt_boxes0 = torch.tensor([[2, 2, 2, 2, 30], [4, 4, 4, 4, 0]], dtype=torch.float32)
        gt_instance0 = Instances(image_shape)
        gt_instance0.gt_boxes = RotatedBoxes(gt_boxes0)
        gt_instance0.gt_classes = torch.tensor([2, 1])
        gt_boxes1 = torch.tensor([[1.5, 5.5, 1, 3, 0], [8.5, 4, 3, 2, -50]], dtype=torch.float32)
        gt_instance1 = Instances(image_shape)
        gt_instance1.gt_boxes = RotatedBoxes(gt_boxes1)
        gt_instance1.gt_classes = torch.tensor([1, 2])
        gt_instances = [gt_instance0, gt_instance1]

        # currently using DefaultAnchorGenerator in RRPN
        proposal_generator = RRPN(cfg, backbone.output_shape())
        roi_heads = RROIHeads(cfg, backbone.output_shape())

        with EventStorage():  # capture events in a new storage to discard them
            proposals, proposal_losses = proposal_generator(images, features, gt_instances)
            _, detector_losses = roi_heads(images, features, proposals, gt_instances)

        expected_losses = {
            "loss_cls": torch.tensor(4.381618499755859),
            "loss_box_reg": torch.tensor(0.0011829272843897343),
        }
        for name in expected_losses.keys():
            err_msg = "detector_losses[{}] = {}, expected losses = {}".format(
                name, detector_losses[name], expected_losses[name]
            )
            self.assertTrue(torch.allclose(detector_losses[name], expected_losses[name]), err_msg)
예제 #4
0
 def testScalar(self):
     with tempfile.TemporaryDirectory(
             prefix="cvpods_tests") as dir, EventStorage() as storage:
         json_file = os.path.join(dir, "test.json")
         writer = JSONWriter(json_file)
         for k in range(60):
             storage.put_scalar("key", k, smoothing_hint=False)
             if (k + 1) % 20 == 0:
                 writer.write()
             storage.step()
         writer.close()
         with open(json_file) as f:
             data = [json.loads(line) for line in f]
             self.assertTrue([int(k["key"]) for k in data] == [19, 39, 59])
예제 #5
0
    def test_roi_heads(self):
        torch.manual_seed(121)
        cfg = RCNNConfig()
        # PROPOSAL_GENERATOR: "RPN"
        # ROI_HEADS: "StandardROIHeads"
        # ROI_BOX_HEAD: "FastRCNNConvFCHead"
        cfg.MODEL.RESNETS.DEPTH = 50
        cfg.MODEL.ROI_BOX_HEAD.NUM_FC = 2
        cfg.MODEL.ROI_BOX_HEAD.POOLER_TYPE = "ROIAlignV2"
        cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_WEIGHTS = (10, 10, 5, 5)

        def build_box_head(cfg, input_shape):
            return FastRCNNConvFCHead(cfg, input_shape)
        cfg.build_box_head = build_box_head

        backbone = build_backbone(cfg)
        num_images = 2
        images_tensor = torch.rand(num_images, 20, 30)
        image_sizes = [(10, 10), (20, 30)]
        images = ImageList(images_tensor, image_sizes)
        num_channels = 1024
        features = {"res4": torch.rand(num_images, num_channels, 1, 2)}

        image_shape = (15, 15)
        gt_boxes0 = torch.tensor([[1, 1, 3, 3], [2, 2, 6, 6]], dtype=torch.float32)
        gt_instance0 = Instances(image_shape)
        gt_instance0.gt_boxes = Boxes(gt_boxes0)
        gt_instance0.gt_classes = torch.tensor([2, 1])
        gt_boxes1 = torch.tensor([[1, 5, 2, 8], [7, 3, 10, 5]], dtype=torch.float32)
        gt_instance1 = Instances(image_shape)
        gt_instance1.gt_boxes = Boxes(gt_boxes1)
        gt_instance1.gt_classes = torch.tensor([1, 2])
        gt_instances = [gt_instance0, gt_instance1]

        proposal_generator = RPN(cfg, backbone.output_shape())
        roi_heads = StandardROIHeads(cfg, backbone.output_shape())

        with EventStorage():  # capture events in a new storage to discard them
            proposals, proposal_losses = proposal_generator(images, features, gt_instances)
            _, detector_losses = roi_heads(images, features, proposals, gt_instances)

        expected_losses = {
            "loss_cls": torch.tensor(4.4236516953),
            "loss_box_reg": torch.tensor(0.0091214813),
        }
        for name in expected_losses.keys():
            self.assertTrue(torch.allclose(detector_losses[name], expected_losses[name]))
예제 #6
0
    def test_fast_rcnn_empty_batch(self, device="cpu"):
        cfg = RCNNConfig()
        cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_WEIGHTS = (10, 10, 5, 5)
        box2box_transform = Box2BoxTransform(weights=cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_WEIGHTS)

        logits = torch.randn(0, 100, requires_grad=True, device=device)
        deltas = torch.randn(0, 4, requires_grad=True, device=device)

        smooth_l1_beta = cfg.MODEL.ROI_BOX_HEAD.SMOOTH_L1_BETA
        outputs = FastRCNNOutputs(
            box2box_transform, logits, deltas, [], smooth_l1_beta
        )
        with EventStorage():  # capture events in a new storage to discard them
            losses = outputs.losses()

        for value in losses.values():
            self.assertTrue(torch.allclose(value, torch.zeros_like(value)))
예제 #7
0
    def test_fast_rcnn_rotated(self):
        torch.manual_seed(132)
        cfg = RCNNConfig()
        cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_WEIGHTS = (10, 10, 5, 5, 1)
        box2box_transform = Box2BoxTransformRotated(weights=cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_WEIGHTS)

        box_head_output_size = 8
        num_classes = 5
        cls_agnostic_bbox_reg = False

        box_predictor = FastRCNNOutputLayers(
            box_head_output_size, num_classes, cls_agnostic_bbox_reg, box_dim=5
        )
        feature_pooled = torch.rand(2, box_head_output_size)
        pred_class_logits, pred_proposal_deltas = box_predictor(feature_pooled)
        image_shape = (10, 10)
        proposal_boxes = torch.tensor(
            [[2, 1.95, 2.4, 1.7, 0], [4.65, 5.25, 4.7, 5.5, 0]], dtype=torch.float32
        )
        gt_boxes = torch.tensor([[2, 2, 2, 2, 0], [4, 4, 4, 4, 0]], dtype=torch.float32)
        result = Instances(image_shape)
        result.proposal_boxes = RotatedBoxes(proposal_boxes)
        result.gt_boxes = RotatedBoxes(gt_boxes)
        result.gt_classes = torch.tensor([1, 2])
        proposals = []
        proposals.append(result)
        smooth_l1_beta = cfg.MODEL.ROI_BOX_HEAD.SMOOTH_L1_BETA

        outputs = RotatedFastRCNNOutputs(
            box2box_transform, pred_class_logits, pred_proposal_deltas, proposals, smooth_l1_beta
        )
        with EventStorage():  # capture events in a new storage to discard them
            losses = outputs.losses()

        # Note: the expected losses are slightly different even if
        # the boxes are essentially the same as in the FastRCNNOutput test, because
        # bbox_pred in FastRCNNOutputLayers have different Linear layers/initialization
        # between the two cases.
        expected_losses = {
            "loss_cls": torch.tensor(1.7920907736),
            "loss_box_reg": torch.tensor(4.0410838127),
        }
        for name in expected_losses.keys():
            assert torch.allclose(losses[name], expected_losses[name])
예제 #8
0
    def test_fast_rcnn(self):
        torch.manual_seed(132)
        cfg = RCNNConfig()
        cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_WEIGHTS = (10, 10, 5, 5)
        box2box_transform = Box2BoxTransform(weights=cfg.MODEL.ROI_BOX_HEAD.BBOX_REG_WEIGHTS)

        box_head_output_size = 8
        num_classes = 5
        cls_agnostic_bbox_reg = False

        box_predictor = FastRCNNOutputLayers(
            box_head_output_size, num_classes, cls_agnostic_bbox_reg, box_dim=4
        )
        feature_pooled = torch.rand(2, box_head_output_size)
        pred_class_logits, pred_proposal_deltas = box_predictor(feature_pooled)
        image_shape = (10, 10)
        proposal_boxes = torch.tensor([[0.8, 1.1, 3.2, 2.8], [2.3, 2.5, 7, 8]], dtype=torch.float32)
        gt_boxes = torch.tensor([[1, 1, 3, 3], [2, 2, 6, 6]], dtype=torch.float32)
        result = Instances(image_shape)
        result.proposal_boxes = Boxes(proposal_boxes)
        result.gt_boxes = Boxes(gt_boxes)
        result.gt_classes = torch.tensor([1, 2])
        proposals = []
        proposals.append(result)
        smooth_l1_beta = cfg.MODEL.ROI_BOX_HEAD.SMOOTH_L1_BETA

        outputs = FastRCNNOutputs(
            box2box_transform, pred_class_logits, pred_proposal_deltas, proposals, smooth_l1_beta
        )
        with EventStorage():  # capture events in a new storage to discard them
            losses = outputs.losses()

        expected_losses = {
            "loss_cls": torch.tensor(1.7951188087),
            "loss_box_reg": torch.tensor(4.0357131958),
        }
        for name in expected_losses.keys():
            assert torch.allclose(losses[name], expected_losses[name])
예제 #9
0
    def train(self, start_iter: int, max_iter: int, max_epoch):
        """
        Args:
            start_iter, max_iter (int): See docs above
        """
        logger = logging.getLogger(__name__)
        logger.info("Starting training from iteration {}".format(start_iter))

        self.iter = self.start_iter = start_iter
        self.max_iter = max_iter
        self.max_epoch = max_epoch

        with EventStorage(start_iter) as self.storage:
            try:
                self.before_train()
                for self.iter in range(start_iter, self.max_iter):
                    self.before_step()
                    self.run_step()
                    self.after_step()
            except Exception:
                logger.exception("Exception during training:")
            finally:
                self.after_train()
예제 #10
0
def do_train(cfg, model, resume=False):
    model.train()
    optimizer = build_optimizer(cfg, model)
    scheduler = build_lr_scheduler(cfg, optimizer)

    checkpointer = DefaultCheckpointer(
        model, cfg.OUTPUT_DIR, optimizer=optimizer, scheduler=scheduler
    )
    start_iter = (
        checkpointer.resume_or_load(cfg.MODEL.WEIGHTS, resume=resume).get("iteration", -1) + 1
    )
    max_iter = cfg.SOLVER.MAX_ITER

    periodic_checkpointer = PeriodicCheckpointer(
        checkpointer, cfg.SOLVER.CHECKPOINT_PERIOD, max_iter=max_iter
    )

    writers = (
        [
            CommonMetricPrinter(max_iter),
            JSONWriter(os.path.join(cfg.OUTPUT_DIR, "metrics.json")),
            TensorboardXWriter(cfg.OUTPUT_DIR),
        ]
        if comm.is_main_process()
        else []
    )

    # compared to "train_net.py", we do not support accurate timing and
    # precise BN here, because they are not trivial to implement
    data_loader = build_train_loader(cfg)
    logger.info("Starting training from iteration {}".format(start_iter))
    with EventStorage(start_iter) as storage:
        for data, iteration in zip(data_loader, range(start_iter, max_iter)):
            iteration = iteration + 1
            storage.step()

            loss_dict = model(data)
            losses = sum(loss for loss in loss_dict.values())
            assert torch.isfinite(losses).all(), loss_dict

            loss_dict_reduced = {k: v.item() for k, v in comm.reduce_dict(loss_dict).items()}
            losses_reduced = sum(loss for loss in loss_dict_reduced.values())
            if comm.is_main_process():
                storage.put_scalars(total_loss=losses_reduced, **loss_dict_reduced)

            optimizer.zero_grad()
            losses.backward()
            optimizer.step()
            storage.put_scalar("lr", optimizer.param_groups[0]["lr"], smoothing_hint=False)
            scheduler.step()

            if (
                cfg.TEST.EVAL_PERIOD > 0
                and iteration % cfg.TEST.EVAL_PERIOD == 0
                and iteration != max_iter
            ):
                do_test(cfg, model)
                # Compared to "train_net.py", the test results are not dumped to EventStorage
                comm.synchronize()

            if iteration - start_iter > 5 and (iteration % 20 == 0 or iteration == max_iter):
                for writer in writers:
                    writer.write()
            periodic_checkpointer.step(iteration)
예제 #11
0
    def test_rpn(self):
        torch.manual_seed(121)
        cfg = RCNNConfig()
        # PROPOSAL_GENERATOR: "RPN"
        # ANCHOR_GENERATOR: "DefaultAnchorGenerator"
        cfg.MODEL.RESNETS.DEPTH = 50
        cfg.MODEL.RPN.BBOX_REG_WEIGHTS = (1, 1, 1, 1)
        backbone = build_backbone(cfg)
        proposal_generator = RPN(cfg, backbone.output_shape())
        num_images = 2
        images_tensor = torch.rand(num_images, 20, 30)
        image_sizes = [(10, 10), (20, 30)]
        images = ImageList(images_tensor, image_sizes)
        image_shape = (15, 15)
        num_channels = 1024
        features = {"res4": torch.rand(num_images, num_channels, 1, 2)}
        gt_boxes = torch.tensor([[1, 1, 3, 3], [2, 2, 6, 6]], dtype=torch.float32)
        gt_instances = Instances(image_shape)
        gt_instances.gt_boxes = Boxes(gt_boxes)
        with EventStorage():  # capture events in a new storage to discard them
            proposals, proposal_losses = proposal_generator(
                images, features, [gt_instances[0], gt_instances[1]]
            )

        expected_losses = {
            "loss_rpn_cls": torch.tensor(0.0804563984),
            "loss_rpn_loc": torch.tensor(0.0990132466),
        }
        for name in expected_losses.keys():
            err_msg = "proposal_losses[{}] = {}, expected losses = {}".format(
                name, proposal_losses[name], expected_losses[name]
            )
            self.assertTrue(torch.allclose(proposal_losses[name], expected_losses[name]), err_msg)

        expected_proposal_boxes = [
            Boxes(torch.tensor([[0, 0, 10, 10], [7.3365392685, 0, 10, 10]])),
            Boxes(
                torch.tensor(
                    [
                        [0, 0, 30, 20],
                        [0, 0, 16.7862777710, 13.1362524033],
                        [0, 0, 30, 13.3173446655],
                        [0, 0, 10.8602609634, 20],
                        [7.7165775299, 0, 27.3875980377, 20],
                    ]
                )
            ),
        ]

        expected_objectness_logits = [
            torch.tensor([0.1225359365, -0.0133192837]),
            torch.tensor([0.1415634006, 0.0989848152, 0.0565387346, -0.0072308783, -0.0428492837]),
        ]

        for proposal, expected_proposal_box, im_size, expected_objectness_logit in zip(
            proposals, expected_proposal_boxes, image_sizes, expected_objectness_logits
        ):
            self.assertEqual(len(proposal), len(expected_proposal_box))
            self.assertEqual(proposal.image_size, im_size)
            self.assertTrue(
                torch.allclose(proposal.proposal_boxes.tensor, expected_proposal_box.tensor)
            )
            self.assertTrue(torch.allclose(proposal.objectness_logits, expected_objectness_logit))
예제 #12
0
    def test_rrpn(self):
        torch.manual_seed(121)
        cfg = RCNNConfig()
        # PROPOSAL_GENERATOR: "RRPN"
        # ANCHOR_GENERATOR: "RotatedAnchorGenerator"
        cfg.MODEL.RESNETS.DEPTH = 50
        cfg.MODEL.ANCHOR_GENERATOR.SIZES = [[32, 64]]
        cfg.MODEL.ANCHOR_GENERATOR.ASPECT_RATIOS = [[0.25, 1]]
        cfg.MODEL.ANCHOR_GENERATOR.ANGLES = [[0, 60]]
        cfg.MODEL.RPN.BBOX_REG_WEIGHTS = (1, 1, 1, 1, 1)
        # cfg.MODEL.RPN.HEAD_NAME = "StandardRPNHead"
        backbone = build_backbone(cfg)
        # currently using DefaultAnchorGenerator in RRPN
        proposal_generator = RRPN(cfg, backbone.output_shape())
        num_images = 2
        images_tensor = torch.rand(num_images, 20, 30)
        image_sizes = [(10, 10), (20, 30)]
        images = ImageList(images_tensor, image_sizes)
        image_shape = (15, 15)
        num_channels = 1024
        features = {"res4": torch.rand(num_images, num_channels, 1, 2)}
        gt_boxes = torch.tensor([[2, 2, 2, 2, 0], [4, 4, 4, 4, 0]], dtype=torch.float32)
        gt_instances = Instances(image_shape)
        gt_instances.gt_boxes = RotatedBoxes(gt_boxes)
        with EventStorage():  # capture events in a new storage to discard them
            proposals, proposal_losses = proposal_generator(
                images, features, [gt_instances[0], gt_instances[1]]
            )

        expected_losses = {
            "loss_rpn_cls": torch.tensor(0.043263837695121765),
            "loss_rpn_loc": torch.tensor(0.14432406425476074),
        }
        for name in expected_losses.keys():
            err_msg = "proposal_losses[{}] = {}, expected losses = {}".format(
                name, proposal_losses[name], expected_losses[name]
            )
            self.assertTrue(torch.allclose(proposal_losses[name], expected_losses[name]), err_msg)

        expected_proposal_boxes = [
            RotatedBoxes(
                torch.tensor(
                    [
                        [0.60189795, 1.24095452, 61.98131943, 18.03621292, -4.07244873],
                        [15.64940453, 1.69624567, 59.59749603, 16.34339333, 2.62692475],
                        [-3.02982378, -2.69752932, 67.90952301, 59.62455750, 59.97010040],
                        [16.71863365, 1.98309708, 35.61507797, 32.81484985, 62.92267227],
                        [0.49432933, -7.92979717, 67.77606201, 62.93098450, -1.85656738],
                        [8.00880814, 1.36017394, 121.81007385, 32.74150467, 50.44297409],
                        [16.44299889, -4.82221127, 63.39775848, 61.22503662, 54.12270737],
                        [5.00000000, 5.00000000, 10.00000000, 10.00000000, -0.76943970],
                        [17.64130402, -0.98095351, 61.40377808, 16.28918839, 55.53118134],
                        [0.13016054, 4.60568953, 35.80157471, 32.30180359, 62.52872086],
                        [-4.26460743, 0.39604485, 124.30079651, 31.84611320, -1.58203125],
                        [7.52815342, -0.91636634, 62.39784622, 15.45565224, 60.79549789],
                    ]
                )
            ),
            RotatedBoxes(
                torch.tensor(
                    [
                        [0.07734215, 0.81635046, 65.33510590, 17.34688377, -1.51821899],
                        [-3.41833067, -3.11320257, 64.17595673, 60.55617905, 58.27033234],
                        [20.67383385, -6.16561556, 63.60531998, 62.52315903, 54.85546494],
                        [15.00000000, 10.00000000, 30.00000000, 20.00000000, -0.18218994],
                        [9.22646523, -6.84775209, 62.09895706, 65.46472931, -2.74307251],
                        [15.00000000, 4.93451595, 30.00000000, 9.86903191, -0.60272217],
                        [8.88342094, 2.65560246, 120.95362854, 32.45022202, 55.75970078],
                        [16.39088631, 2.33887148, 34.78761292, 35.61492920, 60.81977463],
                        [9.78298569, 10.00000000, 19.56597137, 20.00000000, -0.86660767],
                        [1.28576660, 5.49873352, 34.93610382, 33.22600174, 60.51599884],
                        [17.58912468, -1.63270092, 62.96052551, 16.45713997, 52.91245270],
                        [5.64749718, -1.90428460, 62.37649155, 16.19474792, 61.09543991],
                        [0.82255805, 2.34931135, 118.83985901, 32.83671188, 56.50753784],
                        [-5.33874989, 1.64404404, 125.28501892, 33.35424042, -2.80731201],
                    ]
                )
            ),
        ]

        expected_objectness_logits = [
            torch.tensor(
                [
                    0.10111768,
                    0.09112845,
                    0.08466332,
                    0.07589971,
                    0.06650183,
                    0.06350251,
                    0.04299347,
                    0.01864817,
                    0.00986163,
                    0.00078543,
                    -0.04573630,
                    -0.04799230,
                ]
            ),
            torch.tensor(
                [
                    0.11373727,
                    0.09377633,
                    0.05281663,
                    0.05143715,
                    0.04040275,
                    0.03250912,
                    0.01307789,
                    0.01177734,
                    0.00038105,
                    -0.00540255,
                    -0.01194804,
                    -0.01461012,
                    -0.03061717,
                    -0.03599222,
                ]
            ),
        ]

        torch.set_printoptions(precision=8, sci_mode=False)

        for proposal, expected_proposal_box, im_size, expected_objectness_logit in zip(
            proposals, expected_proposal_boxes, image_sizes, expected_objectness_logits
        ):
            self.assertEqual(len(proposal), len(expected_proposal_box))
            self.assertEqual(proposal.image_size, im_size)
            # It seems that there's some randomness in the result across different machines:
            # This test can be run on a local machine for 100 times with exactly the same result,
            # However, a different machine might produce slightly different results,
            # thus the atol here.
            err_msg = "computed proposal boxes = {}, expected {}".format(
                proposal.proposal_boxes.tensor, expected_proposal_box.tensor
            )
            self.assertTrue(
                torch.allclose(
                    proposal.proposal_boxes.tensor, expected_proposal_box.tensor, atol=1e-5
                ),
                err_msg,
            )

            err_msg = "computed objectness logits = {}, expected {}".format(
                proposal.objectness_logits, expected_objectness_logit
            )
            self.assertTrue(
                torch.allclose(proposal.objectness_logits, expected_objectness_logit, atol=1e-5),
                err_msg,
            )
예제 #13
0
        if xylabels[1]: plt.ylabel(xylabels[1])
        ax.set_title(prefix)
        if not label:
            label = range(len(tensor_list))
        ax.hist(array_list, bincount, histtype='bar', label=label)
        ax.legend()


if __name__ == "__main__":
    _dict = dict(VISDOM=dict(
        HOST="192.168.1.1",
        PORT="8082",
        TURN_ON=True,
        ENV_PREFIX='test',
    ), )

    import torch
    from easydict import EasyDict
    cfg = EasyDict(_dict)
    from cvpods.utils import (CommonMetricPrinter, JSONWriter, PathManager,
                              TensorboardXWriter, collect_env_info, comm,
                              seed_all_rng, setup_logger, VisdomWriter)
    from cvpods.utils import EventStorage
    with EventStorage() as storage:
        hist = PltHistogram()
        hist.mode = 'data'
        visdom_writer = VisdomWriter(cfg.VISDOM.HOST, cfg.VISDOM.PORT, 1, [],
                                     cfg.VISDOM.ENV_PREFIX)
        storage.put_image('histo', hist(torch.rand((1000, ))))
        visdom_writer.write()