def setUp(self):
runner = GeneralizedRCNNRunner()
self.cfg = runner.get_default_cfg()
self.is_mcs = False
self.setup_custom_test()
# NOTE: change some config to make the model run fast
self.cfg.merge_from_list(get_quick_test_config_opts())
self.cfg.merge_from_list(["MODEL.DEVICE", "cpu"])
self.test_model = runner.build_model(self.cfg, eval_only=True)
def test_export_torchvision_format(self):
runner = GeneralizedRCNNRunner()
cfg = runner.get_default_cfg()
cfg.merge_from_file("detectron2go://mask_rcnn_fbnetv3a_dsmask_C4.yaml")
cfg.merge_from_list(get_quick_test_config_opts())
cfg.merge_from_list(["MODEL.DEVICE", "cpu"])
pytorch_model = runner.build_model(cfg, eval_only=True)
from typing import Dict, List
class Wrapper(torch.nn.Module):
def __init__(self, model):
super().__init__()
self.model = model
def forward(self, inputs: List[torch.Tensor]):
x = inputs[0].unsqueeze(0) * 255
scale = 320.0 / min(x.shape[-2], x.shape[-1])
x = torch.nn.functional.interpolate(
x,
scale_factor=scale,
mode="bilinear",
align_corners=True,
recompute_scale_factor=True,
)
out = self.model(x[0])
res: Dict[str, torch.Tensor] = {}
res["boxes"] = out[0] / scale
res["labels"] = out[2]
res["scores"] = out[1]
return inputs, [res]
size_divisibility = max(pytorch_model.backbone.size_divisibility, 10)
h, w = size_divisibility, size_divisibility * 2
with create_detection_data_loader_on_toy_dataset(
cfg, h, w, is_train=False) as data_loader:
with make_temp_directory(
"test_export_torchvision_format") as tmp_dir:
predictor_path = convert_and_export_predictor(
cfg,
copy.deepcopy(pytorch_model),
"torchscript",
tmp_dir,
data_loader,
)
orig_model = torch.jit.load(
os.path.join(predictor_path, "model.jit"))
wrapped_model = Wrapper(orig_model)
# optionally do a forward
wrapped_model([torch.rand(3, 600, 600)])
scripted_model = torch.jit.script(wrapped_model)
scripted_model.save(os.path.join(tmp_dir, "new_file.pt"))
#cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.yaml"))
#cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.yaml")
cfg.merge_from_file(
r"/home/pi/Desktop/project xcv/torchscript_int8@tracing/config2.yml")
cfg.MODEL.WEIGHTS = os.path.join(
r"/home/pi/Desktop/project xcv/torchscript_int8@tracing/data.pth")
cfg.MODEL.DEVICE = "cpu" #"cuda"
#cfg.merge_from_file(model_zoo.get_config_file("COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x.yaml"))
#cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x.yaml")
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.6 # set threshold for this model
#model = runner.build_model(cfg)
#predictor = DefaultPredictor(cfg)
model = runner.build_model(cfg)
#model = create_predictor(predictor_path)
predictor = DemoPredictor(model)
#model = create_predictor(predictor_path)
#predictor = DemoPredictor(model)
#cap=cv2.VideoCapture(0)
cap = cv2.VideoCapture("/home/pi/Desktop/project xcv/video-clip.mp4")
fps = cap.get(cv2.CAP_PROP_FPS)
num_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
frame_width = int(cap.get(3))
frame_height = int(cap.get(4))
class TestKmeansAnchors(unittest.TestCase):
def setUp(self):
self.runner = GeneralizedRCNNRunner()
def _get_default_cfg(self):
cfg = self.runner.get_default_cfg()
add_kmeans_anchors_cfg(cfg)
return cfg
@unittest.skip("This can only run locally and takes significant of time")
def test_matching_previous_results(self):
cfg = self._get_default_cfg()
cfg.INPUT.MIN_SIZE_TRAIN = (144, )
cfg.MODEL.KMEANS_ANCHORS.KMEANS_ANCHORS_ON = True
cfg.MODEL.KMEANS_ANCHORS.NUM_CLUSTERS = 10
cfg.MODEL.KMEANS_ANCHORS.NUM_TRAINING_IMG = 512
cfg.MODEL.KMEANS_ANCHORS.DATASETS = ()
# NOTE: create a data loader that samples exact the same as previous
# implementation. In D2Go, we will rely on the train loader instead.
# NOTE: in order to load OV580_XRM dataset, change the IM_DIR to:
# "/mnt/vol/gfsai-east/aml/mobile-vision//dataset/oculus/hand_tracking//torch/Segmentation/OV580_XRM_640x480_V3_new_rerun/images" # noqa
data_loader = build_sequence_loader(
cfg,
# dataset_name="coco_2014_valminusminival",
# dataset_name="OV580_XRM_640x480_V3_train",
dataset_name="OV580_XRM_640x480_V3_heldOut_small_512",
mapper=self.runner.get_mapper(cfg, is_train=True),
total_samples=cfg.MODEL.KMEANS_ANCHORS.NUM_TRAINING_IMG,
batch_size=3,
)
kmeans_anchors = compute_kmeans_anchors(cfg,
data_loader,
sort_by_area=False,
_stride=16,
_legacy_plus_one=True)
# Taken from D9849940
reference_anchors = np.array([
[-15.33554182, -15.29361029, 31.33554182, 31.29361029], # noqa
[-9.34156693, -9.32553548, 25.34156693, 25.32553548], # noqa
[-6.03052776, -6.02034167, 22.03052776, 22.02034167], # noqa
[-2.25951741, -2.182888, 18.25951741, 18.182888], # noqa
[-18.93553378, -18.93553403, 34.93553378, 34.93553403], # noqa
[-12.69068356, -12.73989029, 28.69068356, 28.73989029], # noqa
[-24.73489189, -24.73489246, 40.73489189, 40.73489246], # noqa
[-4.06014466, -4.06014469, 20.06014466, 20.06014469], # noqa
[-7.61036119, -7.60467538, 23.61036119, 23.60467538], # noqa
[-10.88200579, -10.87634414, 26.88200579, 26.87634414], # noqa
])
np.testing.assert_allclose(kmeans_anchors,
reference_anchors,
atol=1e-6)
def test_build_model(self):
cfg = self._get_default_cfg()
cfg.INPUT.MIN_SIZE_TRAIN = (60, )
cfg.MODEL.KMEANS_ANCHORS.KMEANS_ANCHORS_ON = True
cfg.MODEL.KMEANS_ANCHORS.NUM_CLUSTERS = 3
cfg.MODEL.KMEANS_ANCHORS.NUM_TRAINING_IMG = 5
cfg.MODEL.KMEANS_ANCHORS.DATASETS = ("toy_dataset", )
cfg.MODEL.DEVICE = "cpu"
cfg.MODEL.ANCHOR_GENERATOR.NAME = "KMeansAnchorGenerator"
with register_toy_coco_dataset(
"toy_dataset",
image_size=(80, 60), # w, h
num_images=cfg.MODEL.KMEANS_ANCHORS.NUM_TRAINING_IMG,
):
model = self.runner.build_model(cfg)
trainer = SimpleTrainer(model, data_loader=[], optimizer=None)
trainer_hooks = [compute_kmeans_anchors_hook(self.runner, cfg)]
trainer.register_hooks(trainer_hooks)
trainer.before_train()
anchor_generator = model.proposal_generator.anchor_generator
cell_anchors = list(anchor_generator.cell_anchors)
gt_anchors = np.array([
[-20, -15, 20, 15] # toy_dataset's bbox is half size of image
for _ in range(cfg.MODEL.KMEANS_ANCHORS.NUM_CLUSTERS)
])
np.testing.assert_allclose(cell_anchors[0], gt_anchors)
#cfg.merge_from_file(model_zoo.get_config_file("COCO-Detection/faster_rcnn_R_50_C4_1x.yaml"))
#cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-Detection/faster_rcnn_R_50_C4_1x.yaml")
#cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.yaml"))
#cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.yaml")
cfg.merge_from_file(r"/content/config1.yml")
cfg.MODEL.WEIGHTS = os.path.join("/content/output/model_final.pth")
cfg.MODEL.DEVICE = "cuda"
#cfg.merge_from_file(model_zoo.get_config_file("COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x.yaml"))
#cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x.yaml")
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.6 # set threshold for this model
model = runner.build_model(cfg)
predictor = DefaultPredictor(cfg)
#model = runner.build_model(cfg)
#model = create_predictor(predictor_path)
#predictor = DemoPredictor(model)
#model = create_predictor(predictor_path)
#predictor = DemoPredictor(model)
#cap=cv2.VideoCapture('/content/video.mp4')
cap=cv2.VideoCapture("/content/drive/MyDrive/d2go/VID_20210701_130909.mp4")
fps = cap.get(cv2.CAP_PROP_FPS)
num_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))