模型推理FPS计算

场景

很多模型的性能比较，不只是指标的提升，还需要考虑模型的效率、速度；
计算模型的推理速度FPS是一项重要的指标，记录如下：

 # the first several iterations may be very slow so skip them
    parser.add_argument(
        '--max-iter', type=int, default=2000, help='num of max iter')
    parser.add_argument(
        '--log-interval', type=int, default=50, help='interval of logging')
    num_warmup = 5
    pure_inf_time = 0
    fps = 0

    # benchmark with 2000 image and take the average
    for i, data in enumerate(data_loader):

        torch.cuda.synchronize()
        start_time = time.perf_counter()

        with torch.no_grad():
            model(return_loss=False, rescale=True, **data)

        torch.cuda.synchronize()
        elapsed = time.perf_counter() - start_time

        if i >= num_warmup:
            pure_inf_time  = elapsed
            if (i   1) % log_interval == 0:
                fps = (i   1 - num_warmup) / pure_inf_time
                print(
                    f'Done image [{i   1:<3}/ {max_iter}], '
                    f'fps: {fps:.1f} img / s, '
                    f'times per image: {1000 / fps:.1f} ms / img',
                    flush=True)

        if (i   1) == max_iter:
            fps = (i   1 - num_warmup) / pure_inf_time
            print(
                f'Overall fps: {fps:.1f} img / s, '
                f'times per image: {1000 / fps:.1f} ms / img',
                flush=True)
            break
    return fps

思路

FPS的计算，主要是对模型前向传播的耗时平均数进行计算，不包含读取数据和计算指标耗时。

1. 计算每一次、每张图进行推理是耗时
2. 将耗时累加并除以累加次数得到平均值

这篇好文章是转载于：学新通技术网