def main()

in src/controlnet_aux/normalbae/nets/submodules/efficientnet_repo/onnx_validate.py [0:0]

• 44 lines of code
• 7 McCabe index (conditional complexity)

def main():
    args = parser.parse_args()
    args.gpu_id = 0

    # Set graph optimization level
    sess_options = onnxruntime.SessionOptions()
    sess_options.graph_optimization_level = onnxruntime.GraphOptimizationLevel.ORT_ENABLE_ALL
    if args.profile:
        sess_options.enable_profiling = True
    if args.onnx_output_opt:
        sess_options.optimized_model_filepath = args.onnx_output_opt

    session = onnxruntime.InferenceSession(args.onnx_input, sess_options)

    data_config = resolve_data_config(None, args)
    loader = create_loader(
        Dataset(args.data, load_bytes=args.tf_preprocessing),
        input_size=data_config['input_size'],
        batch_size=args.batch_size,
        use_prefetcher=False,
        interpolation=data_config['interpolation'],
        mean=data_config['mean'],
        std=data_config['std'],
        num_workers=args.workers,
        crop_pct=data_config['crop_pct'],
        tensorflow_preprocessing=args.tf_preprocessing)

    input_name = session.get_inputs()[0].name

    batch_time = AverageMeter()
    top1 = AverageMeter()
    top5 = AverageMeter()
    end = time.time()
    for i, (input, target) in enumerate(loader):
        # run the net and return prediction
        output = session.run([], {input_name: input.data.numpy()})
        output = output[0]

        # measure accuracy and record loss
        prec1, prec5 = accuracy_np(output, target.numpy())
        top1.update(prec1.item(), input.size(0))
        top5.update(prec5.item(), input.size(0))

        # measure elapsed time
        batch_time.update(time.time() - end)
        end = time.time()

        if i % args.print_freq == 0:
            print('Test: [{0}/{1}]\t'
                  'Time {batch_time.val:.3f} ({batch_time.avg:.3f}, {rate_avg:.3f}/s, {ms_avg:.3f} ms/sample) \t'
                  'Prec@1 {top1.val:.3f} ({top1.avg:.3f})\t'
                  'Prec@5 {top5.val:.3f} ({top5.avg:.3f})'.format(
                i, len(loader), batch_time=batch_time, rate_avg=input.size(0) / batch_time.avg,
                ms_avg=100 * batch_time.avg / input.size(0), top1=top1, top5=top5))

    print(' * Prec@1 {top1.avg:.3f} ({top1a:.3f}) Prec@5 {top5.avg:.3f} ({top5a:.3f})'.format(
        top1=top1, top1a=100-top1.avg, top5=top5, top5a=100.-top5.avg))