def _test_export(self, predictor_type, compare_match=True):
with self._create_data_loader(is_train=False) as data_loader:
inputs = next(iter(data_loader))
# TODO: the export may change model it self, need to fix this
model_to_export = copy.deepcopy(self.test_model)
predictor_path = convert_and_export_predictor(
self.cfg,
model_to_export,
predictor_type,
self.test_dir,
data_loader,
)
predictor = create_predictor(predictor_path)
predictor_outputs = predictor(inputs)
_validate_outputs(inputs, predictor_outputs)
if compare_match:
with torch.no_grad():
pytorch_outputs = self.test_model(inputs)
assert_instances_allclose(
predictor_outputs[0]["instances"],
pytorch_outputs[0]["instances"],
size_as_tensor=True,
)
return predictor_path
def _test_export(self, predictor_type, compare_match=True):
size_divisibility = max(self.test_model.backbone.size_divisibility, 10)
h, w = size_divisibility, size_divisibility * 2
with create_fake_detection_data_loader(h, w, is_train=False) as data_loader:
inputs = next(iter(data_loader))
with make_temp_directory(
"test_export_{}".format(predictor_type)
) as tmp_dir:
# TODO: the export may change model it self, need to fix this
model_to_export = copy.deepcopy(self.test_model)
predictor_path = convert_and_export_predictor(
self.cfg, model_to_export, predictor_type, tmp_dir, data_loader
)
predictor = create_predictor(predictor_path)
predicotr_outputs = predictor(inputs)
_validate_outputs(inputs, predicotr_outputs)
if compare_match:
with torch.no_grad():
pytorch_outputs = self.test_model(inputs)
assert_instances_allclose(
predicotr_outputs[0]["instances"],
pytorch_outputs[0]["instances"],
)
def _export_simple_model(self, cfg, model, data, output_dir,
predictor_type):
predictor_path = convert_and_export_predictor(
cfg,
model,
predictor_type=predictor_type,
output_dir=output_dir,
data_loader=iter([data] * 3),
)
self.assertTrue(os.path.isdir(predictor_path))
# also test loading predictor
predictor = create_predictor(predictor_path)
return predictor
def test_create_predictor(self):
with make_temp_directory("test_model_info") as tmp_dir:
# define the predictor
model_a_path = os.path.join(tmp_dir, "model_A")
predictor_info = PredictorInfo(
model=ModelInfo(path=model_a_path, type="torchscript"),
preprocess_info=FuncInfo.gen_func_info(TestPreprocess,
params={"weight": 2.0}),
)
# simulating exporting to predictor
_save_test_model(model_a_path)
with open(os.path.join(tmp_dir, "predictor_info.json"), "w") as f:
json.dump(predictor_info.to_dict(), f)
predictor = create_predictor(tmp_dir)
# y = (x * 2) + 1
self.assertEqual(torch.tensor(5), predictor(torch.tensor(2)))
def _test_export(self, predictor_type, compare_match=True):
h, w = _get_input_dim(self.test_model)
dl = _get_data_loader(h, w, False)
inputs = next(iter(dl))
output_dir = os.path.join(self.test_dir, "test_export")
predictor_path = convert_and_export_predictor(
self.cfg, self.test_model, predictor_type, output_dir, dl)
predictor = create_predictor(predictor_path)
predicotr_outputs = predictor(inputs)
self.assertEqual(len(predicotr_outputs), len(inputs))
with torch.no_grad():
pytorch_outputs = self.test_model(inputs)
self.assertEqual(len(pytorch_outputs), len(inputs))
if compare_match:
for predictor_output, pytorch_output in zip(
predicotr_outputs, pytorch_outputs):
torch.testing.assert_allclose(predictor_output["sem_seg"],
pytorch_output["sem_seg"])
def main(
cfg,
output_dir,
runner,
# binary specific optional arguments
predictor_path,
num_threads=None,
caffe2_engine=None,
caffe2_logging_print_net_summary=0,
):
torch.backends.quantized.engine = cfg.QUANTIZATION.BACKEND
print("run with quantized engine: ", torch.backends.quantized.engine)
setup_after_launch(cfg, output_dir, runner)
caffe2_global_init(caffe2_logging_print_net_summary, num_threads)
predictor = create_predictor(predictor_path)
metrics = runner.do_test(cfg, predictor)
print_metrics_table(metrics)
return {
"accuracy": metrics,
"metrics": metrics,
}
cfg.merge_from_file(r"/content/config2.yml")
cfg.MODEL.WEIGHTS = os.path.join("/content/torchscript_int8@tracing/data.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)
start = time.time()
#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))
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
frame_width = int(cap.get(3))
frame_height = int(cap.get(4))
