コンピュータービジョンモデル

    def process_media(self, stream):
        """Runs inference on a frame of video."""
        image_data = preprocess(stream.image,self.MODEL_DIM)
        logger.debug('Image data: {}'.format(image_data))
        # Run inference
        inference_start = time.time()
        inference_results = self.call({"data":image_data}, self.MODEL_NODE)
         # Log metrics
        inference_time = (time.time() - inference_start) * 1000
        if inference_time > self.inference_time_max:
            self.inference_time_max = inference_time
        self.inference_time_ms += inference_time
        # Process results (classification)
        self.process_results(inference_results, stream)

    def process_results(self, inference_results, stream):
        """Processes output tensors from a computer vision model and annotates a video frame."""
        if inference_results is None:
            logger.warning("Inference results are None.")
            return
        max_results = 5
        logger.debug('Inference results: {}'.format(inference_results))
        class_tuple = inference_results[0]
        enum_vals = [(i, val) for i, val in enumerate(class_tuple[0])]
        sorted_vals = sorted(enum_vals, key=lambda tup: tup[1])
        top_k = sorted_vals[::-1][:max_results]
        indexes =  [tup[0] for tup in top_k]

        for j in range(max_results):
            label = 'Class [%s], with probability %.3f.'% (self.classes[indexes[j]], class_tuple[0][indexes[j]])
            stream.add_label(label, 0.1, 0.1 + 0.1*j)

{
    "mlModelDescriptor": {
        "envelopeVersion": "2021-01-01",
        "framework": "PYTORCH",
        "frameworkVersion": "1.8",
        "precisionMode": "FP16",
        "inputs": [
            {
                "name": "data",
                "shape": [
                    1,
                    3,
                    224,
                    224
                ]
            }
        ]
    }
}