本文整理汇总了Python中Network.Network.fit方法的典型用法代码示例。如果您正苦于以下问题：Python Network.fit方法的具体用法？Python Network.fit怎么用？Python Network.fit使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类Network.Network的用法示例。
在下文中一共展示了Network.fit方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: runTest2
# 需要导入模块: from Network import Network [as 别名]
# 或者: from Network.Network import fit [as 别名]
def runTest2():
inputArray = np.array([[[[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3]],
[[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3]],
[[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3]],
[[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3]],
[[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3]],
[[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3]],
[[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3]],
[[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3]],
[[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3],[1,2,3]]]])
labels = [1]
#print(inputArray.shape)
#Conv layer config
numKernels = 4
kernelSize = 3
#Create network
N = Network(sigmoid, ALPHA)
N.addLayer(inputArray[0].shape)
N.addConvLayer(inputArray[0].shape, numKernels, kernelSize, flatten=True) #We flatten it if it's gonna be followed by a FC layer
N.addLayer(10, biased=True)
N.addLayer(1)
## return inputArray
## return N
#Train network
N.fit(inputArray, labels, NUM_EPOCH, verbose=True)
return N示例2: runTest1
# 需要导入模块: from Network import Network [as 别名]
# 或者: from Network.Network import fit [as 别名]
def runTest1():
#SIMPLE TEST
#Gen training data
inputArray = []
labels = []
for i in range(8):
for j in range(8):
t = i**2+j**2
## print(i,j,t)
if (i-2.5)**2 + (j-2.5)**2 < 3: y = 1
## if j >= i and j < i + 3: y = 1
else: y = 0
inputArray.append([i,j])
labels.append(y)
labels = np.array(labels)
inputArray = np.array(inputArray)
#Plot training data
fig = plt.figure()
plt.scatter(inputArray[:,0], inputArray[:,1], c=labels, s=500)
plt.show()
#Create network
N = Network(sigmoid, ALPHA)
N.addLayer(2, biased=True)
N.addLayer(7, biased=True)
#N.addLayer(7, biased=True)
N.addLayer(1)
#Train network
N.fit(inputArray, labels, NUM_EPOCH, verbose=True)
#Plot predictions of training set
newLabels = []
for inputs in inputArray:
label = N.predict(inputs)[0]
newLabels.append(label)
fig = plt.figure()
plt.scatter(inputArray[:,0], inputArray[:,1], c=newLabels, s =500)
plt.show()
return N示例3:
# 需要导入模块: from Network import Network [as 别名]
# 或者: from Network.Network import fit [as 别名]
score = process.calc_score()
logging.debug("Initial score: %f", score)
if score != 1:
fork_score = 0
fork_count = 0
while fork_score <= score and fork_count < settings.MAX_FORK_ATTEMPTS:
logging.debug("Fork attempt %d", fork_count)
fork, fork_step_index = process.get_random_fork()
logging.debug("Running feed forward")
fork.run_to_end()
logging.debug("Fork output: %s", fork.output_struct.root)
fork_score = fork.calc_score()
fork_count += 1
logging.debug("Fork candidate score: %f", fork_score)
if fork_score > score:
logging.debug("Better variation found. Fitting network.")
fork_step = fork.execution_history[fork_step_index]
network.fit(fork_step.token, fork_step.action)
else:
logging.debug("No better variation was found.")
logging.info("Training complete. Evaluating trained network")
mean_f1_score = evaluate_network(network, corpus)
logging.info("Mean score: %f", mean_f1_score)