CNN_net = CNN(CNN_arch)
CNN_net.to(device)
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)
DNN1_net.to(device)
checkpoint_load = torch.load(model_file, map_location=device)
model_trained_using_data_parallel = False
if model_trained_using_data_parallel:
new_ckpt = {}
for k, v in checkpoint_load.items():
new_v = collections.OrderedDict()
for kk, vv in v.items():
if kk.startswith('module.'):
kk = '.'.join(kk.split('.')[1:])
else:
assert False
new_v[kk] = vv
new_ckpt[k] = new_v
# 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,
}
DNN1_net=MLP(DNN1_arch)
DNN1_net.cuda()
DNN2_arch = {'input_dim':fc_lay[-1] ,
'fc_lay': class_lay,
'fc_drop': class_drop,
'fc_use_batchnorm': class_use_batchnorm,
'fc_use_laynorm': class_use_laynorm,
'fc_use_laynorm_inp': class_use_laynorm_inp,
'fc_use_batchnorm_inp':class_use_batchnorm_inp,
'fc_act': class_act,
}
DNN2_net=MLP(DNN2_arch)
'cnn_act': ["leaky_relu", "leaky_relu", "leaky_relu"],
'cnn_drop': [0.0, 0.0, 0.0],
}
CNN_net = CNN(CNN_arch)
DNN1_arch = {
'input_dim': CNN_net.out_dim,
'fc_lay': [2048, 2048, 2048],
'fc_drop': [0.2, 0.2, 0.2],
'fc_use_batchnorm': [True, True, True],
'fc_use_laynorm': [False, False, False],
'fc_use_laynorm_inp': True,
'fc_use_batchnorm_inp': False,
'fc_act': ["leaky_relu", "leaky_relu", "leaky_relu"],
}
DNN1_net = MLP(DNN1_arch)
DNN2_arch = {
'input_dim': 2048,
'fc_lay': [8],
'fc_drop': [0.2],
'fc_use_batchnorm': [False],
'fc_use_laynorm': [False],
'fc_use_laynorm_inp': False,
'fc_use_batchnorm_inp': False,
'fc_act': ["softmax"],
}
DNN2_net = MLP(DNN2_arch)
model = nn.Sequential(CNN_net, DNN1_net, DNN2_net)
# Loading label dictionary
lab_dict = np.load(class_dict_file).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)
DNN1_net.cuda()
DNN2_arch = {
'input_dim': fc_lay[-1],
'fc_lay': class_lay,
'fc_drop': class_drop,
'fc_use_batchnorm': class_use_batchnorm,
'fc_use_laynorm': class_use_laynorm,
'fc_use_laynorm_inp': class_use_laynorm_inp,
'fc_use_batchnorm_inp': class_use_batchnorm_inp,
'fc_act': class_act,
}
DNN2_net = MLP(DNN2_arch)
DNN2_net.cuda()
# Loading label dictionary
lab_dict = np.load(class_dict_file).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)
DNN1_net.cuda()
DNN2_arch = {
'input_dim': fc_lay[-1],
'fc_lay': class_lay,
'fc_drop': class_drop,
'fc_use_batchnorm': class_use_batchnorm,
'fc_use_laynorm': class_use_laynorm,
'fc_use_laynorm_inp': class_use_laynorm_inp,
'fc_use_batchnorm_inp': class_use_batchnorm_inp,
'fc_act': class_act,
}
DNN2_net = MLP(DNN2_arch)
DNN2_net.cuda()
lab_dict = np.load(class_dict_file, allow_pickle=True).item()
# print(CNN_net.out_dim) 6420
DNN1_arch = {
'input_dim':
321, # CNN_net.out_dim where 321 means after attention machine 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) # 三次循环
DNN1_net.to(device)
# print(fc_lay[-1]) 2048
DNN2_arch = {
'input_dim': fc_lay[-1],
'fc_lay': class_lay,
'fc_drop': class_drop,
'fc_use_batchnorm': class_use_batchnorm,
'fc_use_laynorm': class_use_laynorm,
'fc_use_laynorm_inp': class_use_laynorm_inp,
'fc_use_batchnorm_inp': class_use_batchnorm_inp,
'fc_act': class_act, # 注意这里使用的就是softmax最后一层
}
DNN2_net = MLP(DNN2_arch) # 1次循环
DNN2_net.to(device)
except:
os.mkdir(output_folder)
# setting seed
torch.manual_seed(seed)
np.random.seed(seed)
# Loading label dictionary
lab_dict = np.load(class_dict_file, allow_pickle=True).item()
# 读取模型
checkpoint = torch.load('exp/SincNet_TIMIT/model_raw')
CNN_net = CNN({})
CNN_net.load_state_dict(checkpoint['CNN_model_par'])
DNN1_net = MLP({})
DNN1_net.load_state_dict(checkpoint['DNN1_model_par'])
DNN2_net = MLP({})
DNN2_net.load_state_dict(checkpoint['DNN2_model_par'])
eer = 0
for i in range(N_batches):
# 将test信号预处理batch TODO data—folder是test数据集
[inp, lab] = create_batches_rnd(batch_size, data_folder, wav_lst_te,
snt_te, wlen, lab_dict, 0.2)
pout = DNN2_net(DNN1_net(CNN_net(inp)))
pred = torch.max(pout, dim=1)[1] # 寻找最大那个就是预测的谁
fpr, tpr, thresholds = roc_curve(lab, pred, pos_label=1)
eer += brentq(lambda x: 1. - x - interp1d(fpr, tpr)(x), 0., 1.)
