training = []
bos_cikti = [0] * len(siniflar)
for belge in belgeler:
bag = []
kelime_patternleri = belge[0]
kelime_patternleri = [ayristirici.lemmatize(kelime.lower()) for kelime in kelime_patternleri]
for kelime in kelimeler:
bag.append(1) if kelime in kelime_patternleri else bag.append(0)
cikti_sira = list(bos_cikti)
cikti_sira[siniflar.index(belge[1])] = 1
training.append([bag, cikti_sira])
random.shuffle(training)
training = np.array(training) ------> This line Wrong
It shows the error on this line
train_x = list(training[:, 0])
train_y = list(training[:, 1])
#Neural Network (YSA)
model = Sequential()
model.add(Dense(128, input_shape=(len(train_x[0]),), activation="relu"))
model.add(Dropout(0.5))
model.add(Dense(64, activation="relu"))
model.add(Dropout(0.5))
model.add(Dense(len(train_y[0]), activation="softmax"))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss="categorical_crossentropy", optimizer=sgd, metrics=["accuracy"])
model.fit(np.array(train_x), np.array(train_y), epochs=200, batch_size=5, verbose=1)
model.save("chatbot_model.model")
print("Done")
Super confused. When I run my code, I keep on getting this error:
ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (2,) + inhomogeneous part.
Traceback (most recent call last):
File "C:\Users\Elvan Ersöz\Desktop\Python\Bitirme Projesi\training.py", line 55, in <module>
training = np.array(training)
ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 2 dimensions. The detected shape was (20, 2) + inhomogeneous part.
I am creating a project using neural networks and natural language processing. While I'm writing my model
from line 55 I get the following error: ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 2 dimensions. The detected shape was (20, 2) + inhomogeneous part.
enter image description here
Related
i am trying to run this custom loss function in keras and i always run into this error bellow. This pairwaise constraint loss
def loss(y_true, y_pred):
pw = pairwise_distances(y_true, squared=False)
n, d = y_pred.get_shape()
# generate constraint data points
c1 = y_pred[pw[:, 0], :]
c2 = y_pred[pw[:, 1], :]
loss = np.zeros(dtype=np.float32, shape=(pw.shape[0], d * 2))
loss[:, :d] = np.abs(c1 - c2)
loss[:, d:] = (c1 + c2) / 2
return loss
Bellow is the error i get when i try to implement this loss function
File "C:\Users\Benji\Anaconda2\envs\ben\lib\site-packages\keras\engine\training.py", line 692, in _prepare_total_loss
y_true, y_pred, sample_weight=sample_weight)
File "C:\Users\Benji\Anaconda2\envs\ben\lib\site-packages\keras\losses.py", line 71, in __call__
losses = self.call(y_true, y_pred)
File "C:\Users\Benji\Anaconda2\envs\ben\lib\site-packages\keras\losses.py", line 132, in call
return self.fn(y_true, y_pred, **self._fn_kwargs)
File "C:/Users/Benji/PycharmProjects/Code/NEWWORK6.py", line 73, in loss
c1 = y_pred[pw[:, 0], :]
File "C:\Users\Benji\Anaconda2\envs\ben\lib\site-packages\tensorflow_core\python\ops\array_ops.py", line 766, in _slice_helper
_check_index(s)
File "C:\Users\Benji\Anaconda2\envs\ben\lib\site-packages\tensorflow_core\python\ops\array_ops.py", line 655, in _check_index
raise TypeError(_SLICE_TYPE_ERROR + ", got {!r}".format(idx))
TypeError: Only integers, slices (`:`), ellipsis (`...`), tf.newaxis (`None`) and scalar tf.int32/tf.int64 tensors are valid indices, got <tf.Tensor 'loss/activation_6_loss/loss/strided_slice:0' shape=(?,) dtype=float32>
Process finished with exit code 1
gdd.forward(x) call error, but why?
This code uses imcol to implement the convolution layer
Traceback (most recent call last):
File "E:/PycharmProjects/untitled2/kk.py", line 61, in <module>
gdd.forward(x)
File "E:/PycharmProjects/untitled2/kk.py", line 46, in forward
FN,C,FH,FW=self.W.shape
ValueError: not enough values to unpack (expected 4, got 2)
import numpy as np
class Convolution:
# 卷积核大小
def __init__(self,W,b,stride=1,pad=0):
self.W = W
self.b = b
self.stride = stride
self.pad = pad
def forward(self,x):
FN,C,FH,FW=self.W.shape
N,C,H,W = x.shape
out_h = int(1+(H+ 2*self.pad - FH) / self.stride)
out_w = int(1+(W + 2*self.pad -FW) / self.stride)
e = np.array([[2,0,1],[0,1,2],[1,0,2]])
x = np.array([[1,2,3,0],[0,1,2,3],[3,0,1,2],[2,3,0,1]])
gdd = Convolution(e,3,1,0)
gdd.forward(x)
not enough value to unpack means that there are 2 outputs, but you are expecting 4:
FN,C,FH,FW=self.W.shape
just get rid of 2 of them and you are good to go :)
BTW I'm assuming you speak Chinese? 我说中文， 不懂可以用中文问一下
I am trying to create a CNN implemented with data augmentation in pytorch to classify dogs and cats. The issue that I am having is that when I try to input my dataset and enumerate through it I keep getting this error:
Traceback (most recent call last):
File "<ipython-input-55-6337e0536bae>", line 75, in <module>
for i, (inputs, labels) in enumerate(trainloader):
File "/usr/local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 188, in __next__
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/usr/local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 188, in <listcomp>
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/usr/local/lib/python3.6/site-packages/torchvision/datasets/folder.py", line 124, in __getitem__
img = self.transform(img)
File "/usr/local/lib/python3.6/site-packages/torchvision/transforms/transforms.py", line 42, in __call__
img = t(img)
File "/usr/local/lib/python3.6/site-packages/torchvision/transforms/transforms.py", line 147, in __call__
return F.resize(img, self.size, self.interpolation)
File "/usr/local/lib/python3.6/site-packages/torchvision/transforms/functional.py", line 197, in resize
return img.resize((ow, oh), interpolation)
File "/usr/local/lib/python3.6/site-packages/PIL/Image.py", line 1724, in resize
raise ValueError("unknown resampling filter")
ValueError: unknown resampling filter
and I really dont know whats wrong with my code. I have provided the code below:
# Creating the CNN
# Importing the libraries
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.autograd import Variable
import torchvision
from torchvision import transforms
#Creating the CNN Model
class CNN(nn.Module):
def __init__(self, nb_outputs):
super(CNN, self).__init__() #activates the inheritance and allows the use of all the tools in the nn.Module
#making the 3 convolutional layers that will be used in the convolutional neural network
self.convolution1 = nn.Conv2d(in_channels = 1, out_channels = 32, kernel_size = 5) #kernal_size -> the deminson of the feature detector e.g kernel_size = 5 => feature detector of size 5x5
self.convolution2 = nn.Conv2d(in_channels = 32, out_channels = 64, kernel_size = 2)
#making 2 full connections one to connect the inputs of the ANN to the hidden layer and another to connect the hidden layer to the outputs of the ANN
self.fc1 = nn.Linear(in_features = self.count_neurons((1, 64,64)), out_features = 40)
self.fc2 = nn.Linear(in_features = 40, out_features = nb_outputs)
def count_neurons(self, image_dim):
x = Variable(torch.rand(1, *image_dim)) #this variable repersents a fake image to allow us to compute the number of neruons
#in order to pass the elements of the tuple image_dim into our function as a list of arguments we need to add a * before image_dim
#since x will be going into our neural network we need to convert it into a torch variable using the Variable() function
x = F.relu(F.max_pool2d(self.convolution1(x), 3, 2)) #first we apply the convolution to x then apply max_pooling to the convolutional fake images and then activate all the neurons in the pooling layer
x = F.relu(F.max_pool2d(self.convolution2(x), 3, 2)) #the signals are now propragated up to the thrid convoulational layer
#Now to flatten x to obtain the number of neurons in the flattening layer
return x.data.view(1, -1).size(1) #this will flatten x into a huge vector and returns the size of the vector, that size repersents the number of neurons that will be inputted into the ANN
#even though x is not a real image from the game since the size of the flattened vector only depends on the dimention of the inputted image we can just set x to have the same dimentions as the image
def forward(self, x):
x = F.relu(F.max_pool2d(self.convolution1(x), 3, 2)) #first we apply the convolution to x then apply max_pooling to the convolutional fake images and then activate all the neurons in the pooling layer
x = F.relu(F.max_pool2d(self.convolution2(x), 3, 2))
#flattening layer of the CNN
x = x.view(x.size(0), -1)
#x is now the inputs to the ANN
x = F.relu(self.fc1(x)) #we propagte the signals from the flatten layer to the full connected layer and activate the neruons by breaking the linearilty with the relu function
x = F.sigmoid(self.fc2(x))
#x is now the output neurons of the ANN
return x
train_tf = transforms.Compose([transforms.RandomHorizontalFlip(),
transforms.Resize(64,64),
transforms.RandomRotation(20),
transforms.RandomGrayscale(.2),
transforms.ToTensor()])
test_tf = transforms.Compose([transforms.Resize(64,64),
transforms.ToTensor()])
training_set = torchvision.datasets.ImageFolder(root = './dataset/training_set',
transform = train_tf)
test_set = torchvision.datasets.ImageFolder(root = './dataset/test_set',
transform = transforms.Compose([transforms.Resize(64,64),
transforms.ToTensor()]) )
trainloader = torch.utils.data.DataLoader(training_set, batch_size=32,
shuffle=True, num_workers=0)
testloader = torch.utils.data.DataLoader(test_set, batch_size= 32,
shuffle=False, num_workers=0)
#training the model
cnn = CNN(1)
cnn.train()
loss = nn.BCELoss()
optimizer = optim.Adam(cnn.parameters(), lr = 0.001) #the optimizer => Adam optimizer
nb_epochs = 25
for epoch in range(nb_epochs):
train_loss = 0.0
train_acc = 0.0
total = 0.0
for i, (inputs, labels) in enumerate(trainloader):
inputs, labels = Variable(inputs), Variable(labels)
cnn.zero_grad()
outputs = cnn(inputs)
loss_error = loss(outputs, labels)
optimizer.step()
_, pred = torch.max(outputs.data, 1)
total += labels.size(0)
train_loss += loss_error.data[0]
train_acc += (pred == labels).sum()
train_loss = train_loss/len(training_loader)
train_acc = train_acc/total
print('Epoch: %d, loss: %.4f, accuracy: %.4f' %(epoch+1, train_loss, train_acc))
The folder arrangement for the code is /dataset/training_set and inside the training_set folder are two more folders one for all the cat images and the other for all the dog images. Each image is name either dog.xxxx.jpg or cat.xxxx.jpg, where the xxxx represents the number so for the first cat image it would be cat.1.jpg up to cat.4000.jpg. This is the same format for the test_set folder. The number of training images is 8000 and the number of test images is 2000. If anyone can point out my error I would greatly appreciate it.
Thank you
Try to set the desired size in transforms.Resize as a tuple:
transforms.Resize((64, 64))
PIL is using the second argument (in your case 64) as the interpolation method.
in torchvision.transforms.Compose([put every transform in these brackets]),
This, will not give the error.
I have varying length inputs. (below is the sample inputs)
[0.501757009346, 0.554708349218]
[0.460997102135, 0.554708349218]
[0.377844867627]
[0.328125, 0.554708349218]
[-0.266091572661, 0.554708349218, 0.554708349218]
[0.514723203769]
[0.104587155963, 0.554708349218]
[0.247003647733, 0.554708349218]
[0.586212380233]
[0.559979406212, 0.554708349218]
[0.412262156448, 0.554708349218]
So, I have padded the input sequence as follows-
In [115]: from keras.preprocessing.sequence import pad_sequences
In [116]: max_sequence_length = max([len(i) for i in X])
In [117]: padded_sequences = pad_sequences(X, max_sequence_length).tolist()
In [118]: X_padd=np.array(padded_sequences)
In [119]: X_padd.shape
Out[119]: (13189, 694)
Now I need to reshape the input to be of [samples, time steps, features] to implement LSTM layer as per keras documentation.
But when i reshape the input padded array as -
X_reshaped = X_padd.reshape(X_padd.shape[1], max_sequence_length, X_padd.shape[0])
It throws the below error. Please help me resolve this. Thanks.
In [120]: X_reshaped = X_padd.reshape(X_padd.shape[1], max_sequence_length, X_padd.shape[0])
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-120-86980292fb31> in <module>()
----> 1 X_reshaped = X_padd.reshape(X_padd.shape[1], max_sequence_length, X_padd.shape[0])
ValueError: total size of new array must be unchanged
------updated-----
max_sequence_length = max([len(i) for i in X])
padded_sequences = pad_sequences(X, max_sequence_length).tolist()
X_padd=np.array(padded_sequences) # shape -> (13023, 694)
X_reshaped = X_padd.reshape(X_padd.shape[0],X_padd.shape[1],1)
X_train, X_test, Y_train, Y_test = cross_validation.train_test_split(X_reshaped,Y,test_size=0.2,random_state=42)
input_length = X_train.shape[0]
input_dim = X_train.shape[1]
model=Sequential()
model.add(LSTM(4, input_dim=input_dim, input_length=input_length))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(X_train, Y_train, nb_epoch=50, batch_size=12)
on fitting data to the model, below is the error I am getting-
Exception: Error when checking model input: expected lstm_input_4 to have shape (None, 10418, 694) but got array with shape (10418, 694, 1)
As I understand it you don't have features here. You have sequences of numbers, not sequences of vectors. Your shape is (n_samples, time_step).
So If you want to make a 3D tensor to input :
X_Reshaped = X_pad.reshape(X_pad[0], X_pad[1], 1)
Remember that X_pad[1] is your max_sequence_length. So you were trying to reshape a tensor shape(13189,694) into a (13189,694,694). The second one has more values, hence the complaining.
I hope this helps
EDIT :
Your training data has a shape (n_samples, time_steps, num_feat) after the reshape.
Therefore, the input data to your lstm will have a shape of (batch_size, time_steps, features). So when you specify input_length and input_dim you should put the time_steps and the num_feat values instead of n_samples and time_steps.
So change :
input_length = X_train.shape[1]
input_dim = X_train.shape[2]
So I'm trying to create a generator to iterate through a data set for use in training with Keras's fit_generator. Here's the definition of the generator, the model, and the call to fit_generator:
import numpy as np
from queue import Queue, deque
from keras.models import Sequential
from keras.layers import Dense
num_features = 40
len_data = 100
data = np.random.rand(len_data, num_features)
def train_generator(train_idxs):
while True:
i = train_idxs.get(block=False)
training_example = data[i,:]
training_example.shape = (1, len(training_example))
yield (training_example, training_example)
layer0_size = num_features
layer1_size = layer0_size / 2
layer2_size = layer1_size / 2
layers = []
layers.append(
Dense(input_dim=layer0_size, output_dim=layer1_size, activation='relu'))
layers.append(
Dense(input_dim=layer1_size, output_dim=layer2_size, activation='relu'))
layers.append(
Dense(input_dim=layer2_size, output_dim=layer1_size, activation='relu'))
layers.append(
Dense(input_dim=layer1_size, output_dim=layer0_size, activation='sigmoid'))
model = Sequential()
for layer in layers:
model.add(layer)
model.compile(optimizer='adam', loss='binary_crossentropy')
train_idxs = Queue()
train_idxs.queue = deque(range(len_data))
train_gen = train_generator(train_idxs)
max_q_size = 2
model.fit_generator(train_gen, samples_per_epoch=len(data), max_q_size=max_q_size, nb_epoch=1)
Keras will then successfully train 98/100 training examples and throw this error
98/100 [============================>.] - ETA: 0s - loss: 0.6930Exception in thread Thread-1:
Traceback (most recent call last):
File "/usr/lib/python3.5/threading.py", line 914, in _bootstrap_inner
self.run()
File "/usr/lib/python3.5/threading.py", line 862, in run
self._target(*self._args, **self._kwargs)
File "/usr/local/lib/python3.5/dist-packages/keras/engine/training.py", line 429, in data_generator_task
generator_output = next(self._generator)
File "scrap.py", line 12, in train_generator
i = train_idxs.get(block=False)
File "/usr/lib/python3.5/queue.py", line 161, in get
raise Empty
queue.Empty
Traceback (most recent call last):
File "scrap.py", line 43, in <module>
model.fit_generator(train_gen, samples_per_epoch=len(data), max_q_size=max_q_size, nb_epoch=1)
File "/usr/local/lib/python3.5/dist-packages/keras/models.py", line 935, in fit_generator
initial_epoch=initial_epoch)
File "/usr/local/lib/python3.5/dist-packages/keras/engine/training.py", line 1528, in fit_generator
str(generator_output))
ValueError: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None
It seems like what's happening is that it popped of all of the training_idxs and it's still trying to get more until Keras exhaust the training examples in its internal queue. Is there a way to get it to stop trying to get more training examples from the generator?