SNIPER 获取固定参数并创建模块

Get list of fixed parameters

    sym_inst = eval('{}.{}'.format(config.symbol, config.symbol))(n_proposals=400, momentum=args.momentum)
    sym = sym_inst.get_symbol_rcnn(config)
    fixed_param_names = get_fixed_param_names(config.network.FIXED_PARAMS, sym)

configs/faster/default_configs.py

config.network.FIXED_PARAMS = ['gamma', 'beta']

Creating the module

    for k in train_iter.provide_data_single:
        print k[0]
    mod = mx.mod.Module(symbol=sym,
                        context=context,
                        data_names=[k[0] for k in train_iter.provide_data_single],
                        label_names=[k[0] for k in train_iter.provide_label_single],
                        fixed_param_names=fixed_param_names)

    shape_dict = dict(train_iter.provide_data_single + train_iter.provide_label_single)
    sym_inst.infer_shape(shape_dict)
    arg_params, aux_params = load_param(config.network.pretrained, config.network.pretrained_epoch, convert=True)
    sym_inst.init_weight_rcnn(config, arg_params, aux_params)

mxnet的module模块训练神经网络