# Feature extractor CNN
CNN_arch = {'input_dim': wlen,
'fs': fs,
'cnn_N_filt': cnn_N_filt,
'cnn_len_filt': cnn_len_filt,
'cnn_max_pool_len':cnn_max_pool_len,
'cnn_use_laynorm_inp': cnn_use_laynorm_inp,
'cnn_use_batchnorm_inp': cnn_use_batchnorm_inp,
'cnn_use_laynorm':cnn_use_laynorm,
'cnn_use_batchnorm':cnn_use_batchnorm,
'cnn_act': cnn_act,
'cnn_drop':cnn_drop,
}
CNN_net=CNN(CNN_arch)
CNN_net.cuda()
# Loading label dictionary
lab_dict=np.load(class_dict_file).item()
print(CNN_net.out_dim)
DNN1_arch = {'input_dim': CNN_net.out_dim,
'fc_lay': fc_lay,
'fc_drop': fc_drop,
'fc_use_batchnorm': fc_use_batchnorm,
'fc_use_laynorm': fc_use_laynorm,
'fc_use_laynorm_inp': fc_use_laynorm_inp,
'fc_use_batchnorm_inp':fc_use_batchnorm_inp,
'fc_act': fc_act,
}
'cnn_N_filt': cnn_N_filt,
'cnn_len_filt': cnn_len_filt,
'cnn_max_pool_len': cnn_max_pool_len,
'cnn_use_laynorm_inp': cnn_use_laynorm_inp,
'cnn_use_batchnorm_inp': cnn_use_batchnorm_inp,
'cnn_use_laynorm': cnn_use_laynorm,
'cnn_use_batchnorm': cnn_use_batchnorm,
'cnn_act': cnn_act,
'cnn_drop': cnn_drop,
}
CNN_net = CNN(CNN_arch)
CNN_net_out_dim = CNN_net.out_dim
if IS_DATA_PARALLEL:
CNN_net = nn.DataParallel(CNN_net, device_ids=DEVICE_IDS)
CNN_net.cuda(device)
# Loading label dictionary
lab_dict = np.load(class_dict_file, allow_pickle=True).item()
DNN1_arch = {'input_dim': CNN_net_out_dim,
'fc_lay': fc_lay,
'fc_drop': fc_drop,
'fc_use_batchnorm': fc_use_batchnorm,
'fc_use_laynorm': fc_use_laynorm,
'fc_use_laynorm_inp': fc_use_laynorm_inp,
'fc_use_batchnorm_inp': fc_use_batchnorm_inp,
'fc_act': fc_act,
}
DNN1_net = MLP(DNN1_arch)
