我們剛剛開始使用CNTK創建二元分類器的項目。CNTK二元分類器
我們的數據集是這樣的:
|attribs 1436000 24246.3124164245 |isMatch 1
|attribs 535000 21685.9351529239 |isMatch 1
|attribs 729000 8988.24232231086 |isMatch 1
|attribs 436000 4787.7521169184 |isMatch 1
|attribs 110000 38236394.456649 |isMatch 0
|attribs 808000 39512500.9870238 |isMatch 0
|attribs 108000 28432968.9161523 |isMatch 0
|attribs 816000 39512231.5629576 |isMatch 0
我們正試圖確定一個校車站是否計劃路線一致。第一個值是計劃停止和實際停止之間的增量時間(毫秒),第二個值是計劃位置和實際位置(毫米)之間的增量距離。
我遇到的問題是(可能是對如何使用CNTK的一個基本誤解),無論我如何調整數據,隱藏節點,批量大小或任何其他旋鈕,我都會繼續得到幾乎相同的結果。我可以評估最荒謬的投入,我一直得到1.00。
我該如何修改數據或模型以獲得更準確的結果?
完整的代碼是在這裏:
import numpy as np
import cntk as C
from cntk import Trainer # to train the NN
from cntk.learners import sgd, learning_rate_schedule, \
UnitType
from cntk.ops import * # input_variable() def
from cntk.logging import ProgressPrinter
from cntk.initializer import glorot_uniform
from cntk.layers import default_options, Dense
from cntk.io import CTFDeserializer, MinibatchSource, \
StreamDef, StreamDefs, INFINITELY_REPEAT
def my_print(arr, dec):
# print an array of float/double with dec decimals
fmt = "%." + str(dec) + "f" # like %.4f
for i in range(0, len(arr)):
print(fmt % arr[i] + ' ', end='')
print("\n")
def create_reader(path, is_training, input_dim, output_dim):
return MinibatchSource(CTFDeserializer(path, StreamDefs(
features=StreamDef(field='attribs', shape=input_dim,
is_sparse=False),
labels=StreamDef(field='isMatch', shape=output_dim,
is_sparse=False)
)), randomize=is_training,
max_sweeps=INFINITELY_REPEAT if is_training else 1)
def save_weights(fn, ihWeights, hBiases,
hoWeights, oBiases):
f = open(fn, 'w')
for vals in ihWeights:
for v in vals:
f.write("%s\n" % v)
for v in hBiases:
f.write("%s\n" % v)
for vals in hoWeights:
for v in vals:
f.write("%s\n" % v)
for v in oBiases:
f.write("%s\n" % v)
f.close()
def do_demo():
# create NN, train, test, predict
input_dim = 2
hidden_dim = 30
output_dim = 1
train_file = "trainData_cntk.txt"
test_file = "testData_cntk.txt"
input_Var = C.ops.input_variable(input_dim, np.float32)
label_Var = C.ops.input_variable(output_dim, np.float32)
print("Creating a 2-21 tanh softmax NN for Stop data ")
with default_options(init=glorot_uniform()):
hLayer = Dense(hidden_dim, activation=C.ops.tanh,
name='hidLayer')(input_Var)
oLayer = Dense(output_dim, activation=C.ops.softmax,
name='outLayer')(hLayer)
nnet = oLayer
# ----------------------------------
print("Creating a cross entropy mini-batch Trainer \n")
ce = C.cross_entropy_with_softmax(nnet, label_Var)
pe = C.classification_error(nnet, label_Var)
fixed_lr = 0.05
lr_per_batch = learning_rate_schedule(fixed_lr,
UnitType.minibatch)
learner = C.sgd(nnet.parameters, lr_per_batch)
trainer = C.Trainer(nnet, (ce, pe), [learner])
max_iter = 5000 # 5000 maximum training iterations
batch_size = 100 # mini-batch size 5
progress_freq = 1000 # print error every n minibatches
reader_train = create_reader(train_file, True, input_dim,
output_dim)
my_input_map = {
input_Var: reader_train.streams.features,
label_Var: reader_train.streams.labels
}
pp = ProgressPrinter(progress_freq)
print("Starting training \n")
for i in range(0, max_iter):
currBatch = reader_train.next_minibatch(batch_size,
input_map=my_input_map)
trainer.train_minibatch(currBatch)
pp.update_with_trainer(trainer)
print("\nTraining complete")
# ----------------------------------
print("\nEvaluating test data \n")
reader_test = create_reader(test_file, False, input_dim,
output_dim)
numTestItems = 200
allTest = reader_test.next_minibatch(numTestItems,
input_map=my_input_map)
test_error = trainer.test_minibatch(allTest)
print("Classification error on the test items = %f"
% test_error)
# ----------------------------------
# make a prediction for an unknown flower
# first train versicolor = 7.0,3.2,4.7,1.4,0,1,0
unknown = np.array([[10000002000, 24275329.7232828]], dtype=np.float32)
print("\nPredicting Stop Match for input features: ")
my_print(unknown[0], 1) # 1 decimal
predicted = nnet.eval({input_Var: unknown})
print("Prediction is: ")
my_print(predicted[0], 3) # 3 decimals
# ---------------------------------
print("\nTrained model input-to-hidden weights: \n")
print(hLayer.hidLayer.W.value)
print("\nTrained model hidden node biases: \n")
print(hLayer.hidLayer.b.value)
print("\nTrained model hidden-to-output weights: \n")
print(oLayer.outLayer.W.value)
print("\nTrained model output node biases: \n")
print(oLayer.outLayer.b.value)
save_weights("weights.txt", hLayer.hidLayer.W.value,
hLayer.hidLayer.b.value, oLayer.outLayer.W.value,
oLayer.outLayer.b.value)
return 0 # success
def main():
print("\nBegin Stop Match \n")
np.random.seed(0)
do_demo() # all the work is done in do_demo()
if __name__ == "__main__":
main()
# end script
我真的希望我完全理解你在這裏說的。但作爲一個總的noob,我不這樣做。你有什麼機會讓我讀一些書來加快速度? – Wjdavis5
我不知道比完成http://www.coursera.org/learn/machine-learning/home/welcome更快的路線 –