gesture_classifier.load_state_dict(checkpoint)
gesture_classifier.eval()
# Concatenate feature extractor and met converter
net = Pipe(feature_extractor, gesture_classifier)
# Create inference engine, video streaming and display instances
inference_engine = engine.InferenceEngine(net, use_gpu=use_gpu)
video_source = camera.VideoSource(camera_id=camera_id,
size=inference_engine.expected_frame_size,
filename=path_in)
video_stream = camera.VideoStream(video_source,
inference_engine.fps)
postprocessor = [
PostprocessClassificationOutput(INT2LAB, smoothing=4)
]
display_ops = [
realtimenet.display.DisplayTopKClassificationOutputs(top_k=1, threshold=0.5),
]
display_results = realtimenet.display.DisplayResults(title=title, display_ops=display_ops)
engine.run_inference_engine(inference_engine,
video_stream,
postprocessor,
display_results,
path_out)
gesture_classifier.load_state_dict(checkpoint)
gesture_classifier.eval()
# Load MET value converter
met_value_converter = calorie_estimation.METValueMLPConverter()
checkpoint = torch.load(
'resources/calorie_estimation/mobilenet_features_met_converter.ckpt')
met_value_converter.load_state_dict(checkpoint)
met_value_converter.eval()
# Concatenate feature extractor with downstream nets
net = Pipe(feature_extractor,
feature_converter=[gesture_classifier, met_value_converter])
post_processors = [
PostprocessClassificationOutput(INT2LAB, smoothing=8, indices=[0]),
calorie_estimation.CalorieAccumulator(weight=weight,
height=height,
age=age,
gender=gender,
smoothing=12,
indices=[1])
]
display_ops = [
realtimenet.display.DisplayFPS(expected_camera_fps=net.fps,
expected_inference_fps=net.fps /
net.step_size),
realtimenet.display.DisplayTopKClassificationOutputs(top_k=1,
threshold=0.5),
realtimenet.display.DisplayMETandCalories(y_offset=40),
def _setup_post_processor(self):
self.postprocessors = [
PostprocessClassificationOutput(INT2LAB, smoothing=4)
]