Python Solver.predict方法代码示例

# 需要导入模块: from solver import Solver [as 别名]
# 或者: from solver.Solver import predict [as 别名]
def train(param=PARAMS, sv=SOLVE, small=False):

    sv['name'] = __file__.rstrip('.py')
    input_var = raw_input('Are you testing now? ')
    
    if 'no' in input_var:
        sv.pop('name')
    else:
        sv['name'] += input_var

    out = get(1) 
    from my_layer import LSTM
    sym = LSTM(e_net.l3_4, 64*64, 1, 64, 64)
    sym = list(sym)
    sym[0] = mx.sym.LogisticRegressionOutput(data=sym[0], name='softmax')
    sym = mx.symbol.Group(list(sym))

    param['eval_data'] = out['val'] 
    param['marks'] = param['e_marks'] = out['marks'] 
    param['ctx'] = mu.gpu(1)

    print out['train'].label[0][1].shape
  
    s = Solver(sym, out['train'], sv, **param)
    s.train()
    s.predict()

# 需要导入模块: from solver import Solver [as 别名]
# 或者: from solver.Solver import predict [as 别名]
def train(param=PARAMS, sv=SOLVE, small=False):

    sv['name'] = 'TEST'
    input_var = raw_input('Are you testing now? ')
    
    if 'no' in input_var:
        sv.pop('name')
    else:
        sv['name'] += input_var


    #out = u.get(6,small=True, aug=True) 
    imgs, ll = load_rnn_pk(files)
    imgs = imgs.reshape((-1,1,256,256))
    ll   = ll.reshape((-1,1,256,256))
    datas = u.prepare_set(imgs, ll)

    out = u.create_iter(*datas, batch_size=5)
    net = cnn_net(
        use_logis=True
        )

    param['eval_data'] = out[1] 
  
    s = Solver(net, out[0], sv, **param)
    s.train()
    s.predict()
    s.all_to_png()
    s.save_best_model()
    s.plot_process()

# 需要导入模块: from solver import Solver [as 别名]
# 或者: from solver.Solver import predict [as 别名]
def train(param=PARAMS, sv=SOLVE, small=False):

    net = make_net()

    out = R.get(2, rate=0.05) 
    train, param['eval_data'] = out['train'], out['val']  
    param['marks'] = param['e_marks'] = out['marks'] 

    s = Solver(net, train, sv, **param)
    s.train()
    s.predict()

# 需要导入模块: from solver import Solver [as 别名]
# 或者: from solver.Solver import predict [as 别名]
def train(param=PARAMS, sv=SOLVE, small=False):

    sv['name'] = __file__.rstrip('.py')
    input_var = raw_input('Are you testing now? ')
    
    if 'no' in input_var:
        sv.pop('name')
    else:
        sv['name'] += input_var

    out = get(6, aug=True) 
    sym = net()

    param['eval_data'] = out['val'] 
  
    s = Solver(sym, out['train'], sv, **param)
    s.train()
    s.predict()

# 需要导入模块: from solver import Solver [as 别名]
# 或者: from solver.Solver import predict [as 别名]
def train(param=PARAMS, sv=SOLVE, small=False):
    # prepare net
    net = unroll_lstm(10, 64*64, 1, 64, 64)

    # prepare data
    from Evol.load_e import reshape_label
    from RNN.rnn_load import load_rnn_pk
    img, ll = load_rnn_pk(['../DATA/PK/NEW/[T10,N10]<8-11:42:11>.pk'])

    ll = reshape_label(ll)
    lt, lv = ll[:8], ll[8:]
    train = UnrollIter(lt, label=lt, batch_size=2, num_hidden=64*64)
    val   = UnrollIter(lv, label=lv, batch_size=2, num_hidden=64*64)

    # train
    s = Solver(net, train, sv, **param)
    print 'Start Training...'
    s.train()
    s.predict()

# 需要导入模块: from solver import Solver [as 别名]
# 或者: from solver.Solver import predict [as 别名]
def train(param=PARAMS, sv=SOLVE, small=False):

    sv['name'] = 'TEST'
    input_var = raw_input('Are you testing now? ')
    
    if 'no' in input_var:
        sv.pop('name')
    else:
        sv['name'] += input_var

    out = get(6, small=True, aug=True) 
    net = net()

    param['eval_data'] = out['eval'] 
  
    s = Solver(net, out['train'], sv, **param)
    s.train()
    s.predict()
    s.all_to_png()
    s.save_best_model()
    s.plot_process()

# 需要导入模块: from solver import Solver [as 别名]
# 或者: from solver.Solver import predict [as 别名]
def train(base_model, param=PARAMS, sv=SOLVE, small=False):

    # prepare data
    if small:
        files = rnn_load.f10
        param['ctx'] = mu.gpu(1)
    else:
        files = rnn_load.files

    imgs, labels = rnn_load.load_rnn_pk(files)
    it, lt, iv, lv = mu.prepare_set(imgs, labels)
    N, T = it.shape[:2]

    # cnn process
    model = mx.model.FeedForward.load(*base_model, ctx=mu.gpu(1))
    rnn_input = np.zeros_like(it)
    for n in range(1):
        rnn_input[n], imgs, labels = mu.predict_draw(model, it[n])

    # prepare params
    #datas = [rnn_input, lt, iv, lv]
    datas = [ lt, lt, lv, lv]
    for i, d in enumerate(datas):
        #datas[i] = np.transpose(d,axes=(1,0,2,3,4))

        # make T become one
        datas[i] = d.reshape((-1,1)+d.shape[2:])

    iters = rnn_load.create_rnn_iter(*datas, batch_size=1, num_hidden=1000)
    param['eval_data'] = iters[1]
    mark = param['marks'] = param['e_marks'] = [1]*T
    rnet = rnn_net(begin=mx.sym.Variable('data'), num_hidden=1000)
    s = Solver(rnet, iters[0], sv, **param)

    # train
    print 'Start Training...'
    s.train()
    s.predict()

# 需要导入模块: from solver import Solver [as 别名]
# 或者: from solver.Solver import predict [as 别名]
tll  = np.concatenate(labels[:-split], axis=1)
print timg.shape, tll.shape
vimg = np.concatenate(images[-split:], axis=1)
vll  = np.concatenate(labels[-split:], axis=1)


from r_lstm import R_LSTM_Iter
train = R_LSTM_Iter(timg, label=tll, num_hidden=3, batch_size=1)
val =   R_LSTM_Iter(vimg, label=vll, num_hidden=3, batch_size=1)

from solver import Solver
from train import make_net
from settings import PARAMS, SOLVE

SOLVE['is_rnn'] = True
SOLVE['load']   = True
SOLVE['load_perfix'] = '/home/zijia/HeartDeepLearning/R_LSTM/Result/<26-12:43:22>[E5]/[ACC-0.97747 E4]'
SOLVE['load_epoch']  = 4
 
PARAMS['eval_data'] = val 
PARAMS['marks'] = marks[:-split]
PARAMS['e_marks'] = marks[-split:]
PARAMS['ctx'] = mu.gpu(1)

PARAMS['learning_rate'] = 1

s = Solver(make_net(), train, SOLVE, **PARAMS)

s.train()
s.predict()