I'm encoding a keras layer named A where I need Two tensor a,b . How should I do to fix the inputs [a,b] to get a correct return (the return of A are also tow tesor)?
def get_model(latent_dim):
# Input variables
u = Input(shape=(k,), dtype='float32', name = 'u]')
i = Input(shape=(k,), dtype='float32', name = 'i]')
LA=A(latent_dim)
list = A([u ,i])
u_return = list_co[-2]
i_return = list_co[-1]
encoding environment : For simply , I just set A as flows:
class A(latent_dim):
def call(inputs):
m = inputs[0]
n = inputs[1]
return [m,n]
but it still wrong
File "C:\ProgramData\Anaconda3\envs\network\lib\site-packages\keras\engine\topology.py", line 703, in _add_inbound_node
output_tensors[i]._keras_shape = output_shapes[i]
IndexError: list index out of range
Related
Any help will be highly appreciated
I'm trying to load two lists containing image paths and their corresponding labels. Something like this:
p0 = ['a','b',....] #paths to images .tif format
p1 = [1,2,3,......] #paths to images .tif format
labels = [0,1,1,...] #corresponding labels w.r.t both the lists
I used a tf.data in the following way:
def TFData(p_0, p_1, batch_size, labels=None, is_train=True):
dset = tf.data.Dataset.from_tensor_slices((p_0,p_1))
if labels is not None:
label = tf.data.Dataset.from_tensor_slices(labels)
AUTO = tf.data.experimental.AUTOTUNE
final_dset = tf.data.Dataset.zip((dset, label))
final_dset = final_dset.batch(batch_size, drop_remainder=is_train).prefetch(AUTO)
return final_dset
This returns:
<PrefetchDataset shapes: (((64,), (64,)), (64,)), types: ((tf.string, tf.string), tf.int32)>
My question is how to apply a function to convert the paths to arrays using cv2 as the images are .tif files? such that the result will be:
<PrefetchDataset shapes: (((64,256,256,3), (64,256,256,3)), (64,)), types: ((tf.float64, tf.float64), tf.int32)>
I'm using a dataset.map. However it's throwing error:
def to_array(p_0):
im_1 = cv2.imread(p_0,1)
#im = tfio.experimental.image.decode_tiff(paths)
im_1 = cv2.resize(im_1,(img_w,img_h)) #img_w=img_h=256
im_1 = np.asarray(im_1, dtype=np.float64)
im_1 /= 255
return im_1
def parse_fn(p_0):
[p_0,] = tf.py_function(to_array, [p_0], [tf.float64])
return p_0
def TFData(p_0, p_1, batch_size, labels=None, is_train=True):
dset_1 = tf.data.Dataset.from_tensor_slices(p_0)
dset_1 = dset_1.map(parse_fn)
dset_2 = tf.data.Dataset.from_tensor_slices(p_1)
dset_2 = dset_2.map(parse_fn)
if labels is not None:
label = tf.data.Dataset.from_tensor_slices(labels)
AUTO = tf.data.experimental.AUTOTUNE
final_dset = tf.data.Dataset.zip((dset_1, dset_2, label))
final_dset = final_dset.batch(batch_size, drop_remainder=is_train).prefetch(AUTO)
return final_dset
print(train_data) #where train_data is defined as TFData()
<PrefetchDataset shapes: ((<unknown>, <unknown>), (64,)), types: ((tf.float64, tf.float64), tf.int32)>
This throws an error:
for (t,p),l in train_data.as_numpy_iterator():
print(t)
print(p)
print(l)
print(type(t))
break
SystemError: <built-in function imread> returned NULL without setting an error
[[{{node EagerPyFunc}}]] [Op:IteratorGetNext]
Any help will be highly appreciated
I think your problem is in cv2.imread.
Have you checked outside the functions to see if it is reading and plotting the data accordingly?
Please, try with -1 instead:
im_1 = cv2.imread(p_0,-1)
I have implemented sequence to sequence model with attention layer if I 300000 data points I'm not getting any error if I use all of my data points I'm getting following error model.fit
TypeError: Expected int32, got None of type 'NoneType' instead.
what would be the reason for this?
the code before model.fit is
class encoder_decoder(tf.keras.Model):
def __init__(self,embedding_size,encoder_inputs_length,output_length,vocab_size,output_vocab_size,score_fun,units):
super(encoder_decoder,self).__init__()
self.vocab_size = vocab_size
self.enc_units = units
self.embedding_size = embedding_size
self.encoder_inputs_length = encoder_inputs_length
self.output_length = output_length
self.lstm_output = 0
self.state_h = 0
self.state_c = 0
self.output_vocab_size = output_vocab_size
self.dec_units = units
self.score_fun = score_fun
self.att_units = units
self.encoder=Encoder(self.vocab_size,self.embedding_size,self.enc_units,self.encoder_inputs_length)
self.decoder = Decoder(self.output_vocab_size, self.embedding_size, self.output_length, self.dec_units ,self.score_fun ,self.att_units)
# self.dense = Dense(self.output_vocab_size,activation = "softmax")
def call(self,data):
input,output = data[0],data[1]
encoder_hidden = self.encoder.initialize_states(input.shape[0])
encoder_output,encoder_hidden,encoder_cell = self.encoder(input,encoder_hidden)
decoder_hidden = encoder_hidden
decoder_cell =encoder_cell
decoder_output = self.decoder(output,encoder_output,decoder_hidden,decoder_cell)
return decoder_output
Inside the call function I'm initializing states for the encoder where I'm getting
the number of rows from input using the following line of code
encoder_hidden = self.encoder.initialize_states(input.shape[0])
If I print input, I'm getting shape as (None,55)
That's the reason I'm getting this error.
Here my total number data points is 330614 when I use all my data I getting this
error, when I use only 330000 data points I'm getting this error,
if I print batch inside def method I'm getting shape as (64,55)
Please find my below code for creating dataset for my sequence to sequence model
the function to reprocess the data and the function to create the dataset
and a function the load the dataset
def preprocess_sentence(w):
# w = unicode_to_ascii(w.lower().strip())
w = re.sub(r"([?.!,¿])", r" \1 ", w)
w = re.sub(r'[" "]+', " ", w)
w = re.sub(r"[^a-zA-Z?.!,¿]+", " ", w)
w = w.strip()
w = '<start> ' + w + ' <end>'
return w
def create_dataset(path, num_examples):
lines = io.open(path, encoding='UTF-8').read().strip().split('\n')
# lines1 = lines[330000:]
# lines = lines[0:323386]+lines1
word_pairs = [[preprocess_sentence(w) for w in l.split('\t')] for l in lines[:num_examples]]
word_pairs = [[i[0],i[1]] for i in word_pairs]
return zip(*word_pairs)
def tokenize(lang):
lang_tokenizer = tf.keras.preprocessing.text.Tokenizer(
filters='')
lang_tokenizer.fit_on_texts(lang)
tensor = lang_tokenizer.texts_to_sequences(lang)
tensor = tf.keras.preprocessing.sequence.pad_sequences(tensor,padding='post')
return tensor, lang_tokenizer
def load_dataset(path, num_examples=None):
# creating cleaned input, output pairs
targ_lang, inp_lang = create_dataset(path, num_examples)
input_tensor, inp_lang_tokenizer = tokenize(inp_lang)
target_tensor, targ_lang_tokenizer = tokenize(targ_lang)
return input_tensor, target_tensor, inp_lang_tokenizer, targ_lang_tokenizer,targ_lang,inp_lang
# Try experimenting with the size of that dataset
num_examples = None
input_tensor, target_tensor, inp_lang, targ_lang,targ_lang_text,inp_lang_text = load_dataset(path, num_examples)
# Calculate max_length of the target tensors
max_length_targ, max_length_inp = target_tensor.shape[1], input_tensor.shape[1]
max_length_targ,max_length_inp
input_tensor_train, input_tensor_val, target_tensor_train, target_tensor_val = train_test_split(input_tensor, target_tensor, test_size=0.2)
the shape of datasets as follows
shape of input train (269291, 55)
shape of target train (269291, 53)
shape of input test (67323, 55)
shape of target test (67323, 53)
You can share the code block before the model.fit.
NoneType error is indicating that the final array which is passed to the model is for some reason empty. You can add print statements at previous steps to understand where along the way your array became empty.
Compare the scenario to the case where you are taking all your data points so that you can understand where the array is changing and how it is handled prior to passing it through model.fit.
I have a error when trying to call calculate_similarity2 function which in in DocSim.py file from my notebook.
The error message is : 'DocSim' object has no attribute 'calculate_similarity2'
Here the content of my docsim File :
import numpy as np
class DocSim(object):
def __init__(self, w2v_model , stopwords=[]):
self.w2v_model = w2v_model
self.stopwords = stopwords
def vectorize(self, doc):
"""Identify the vector values for each word in the given document"""
doc = doc.lower()
words = [w for w in doc.split(" ") if w not in self.stopwords]
word_vecs = []
for word in words:
try:
vec = self.w2v_model[word]
word_vecs.append(vec)
except KeyError:
# Ignore, if the word doesn't exist in the vocabulary
pass
# Assuming that document vector is the mean of all the word vectors
# PS: There are other & better ways to do it.
vector = np.mean(word_vecs, axis=0)
return vector
def _cosine_sim(self, vecA, vecB):
"""Find the cosine similarity distance between two vectors."""
csim = np.dot(vecA, vecB) / (np.linalg.norm(vecA) * np.linalg.norm(vecB))
if np.isnan(np.sum(csim)):
return 0
return csim
def calculate_similarity(self, source_doc, target_docs=[], threshold=0):
"""Calculates & returns similarity scores between given source document & all
the target documents."""
if isinstance(target_docs, str):
target_docs = [target_docs]
source_vec = self.vectorize(source_doc)
results = []
for doc in target_docs:
target_vec = self.vectorize(doc)
sim_score = self._cosine_sim(source_vec, target_vec)
if sim_score > threshold:
results.append({
'score' : sim_score,
'sentence' : doc
})
# Sort results by score in desc order
results.sort(key=lambda k : k['score'] , reverse=True)
return results
def calculate_similarity2(self, source_doc=[], target_docs=[], threshold=0):
"""Calculates & returns similarity scores between given source document & all the target documents."""
if isinstance(source_doc, str):
target_docs = [source_doc]
if isinstance(target_docs, str):
target_docs = [target_docs]
#source_vec = self.vectorize(source_doc)
results = []
for doc in source_doc:
source_vec = self.vectorize(doc)
for doc1 in target_docs:
target_vec = self.vectorize(doc)
sim_score = self._cosine_sim(source_vec, target_vec)
if sim_score > threshold:
results.append({
'score' : sim_score,
'source sentence' : doc,
'target sentence' : doc1
})
# Sort results by score in desc order
results.sort(key=lambda k : k['score'] , reverse=True)
return results
here in instruction code when i try to call the fucntion :
To create DocSim Object
ds = DocSim(word2vec_model,stopwords=stopwords)
sim_scores = ds.calculate_similarity2(source_doc, target_docs)
the error message is :
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-54-bb0bd1e0e0ad> in <module>()
----> 1 sim_scores = ds.calculate_similarity2(source_doc, target_docs)
AttributeError: 'DocSim' object has no attribute 'calculate_similarity2'
i don't undersantand how to resolve this problem.
I can access to all function except calculate_similarity2
Can you help me please?
thanks
You have defined the calculate_similarity2 function inside the __init__ scope. Try getting it out of there
I am trying to use a function (from another module) inside tensorflow. The function accepts a numpy array and returns the changepoints. My main goal is to deploy this model on tensorflow serving. I am running into error
AttributeError: 'DType' object has no attribute 'type'
There are 2 functions, one is create_data() that creates a numpy array and returns it, another is change() which accepts numpy array and uses the before mentioned function to return changepoints. I have created a placeholder to accept input data, an operation to execute the function. Problem is, if i try to send data through placeholder, i run into error. If i send the data directly into the function, it runs. Following is my code.
def create_data():
np.random.seed(0)
size = 100
mean_a = 0.0
mean_b = 10.0
mean_c = 0
var = 0.1
data_a = np.random.normal(mean_a, var, size)
data_b = np.random.normal(mean_b, var, size)
data_c = np.random.normal(mean_c, var, size)
data = np.concatenate([data_a, data_b, data_c])
return data
def change(data):
# what else i tried
# data = np.array(data, dtype=np.float)
# above line gives another error mentioned after code
cpts = (pelt(normal_mean(x, np.var(x)), len(x)))
return cpts
sess = tf.Session()
x = tf.placeholder(tf.float32, shape=[300, ], name="myInput")
y = tf.convert_to_tensor(change(x),np.float32,name="myOutput")
z = sess.run(y,feed_dict={x:create_data()})
If i try the code data = np.array(data, dtype=np.float) in the function change(), it gives me error
ValueError: setting an array element with a sequence.
I also tried data = np.hstack((data)).astype(np.float) and data = np.vstack((data)).astype(np.float) but it runs into a separate error that says use tf.map_fn. I also tried to use tf.eval() to convert the numbers but i couldn't get them to run inside a function with placeholders.
But if i send in the output directly,
y = tf.convert_to_tensor(change(create_data()),np.float32,name="myOutput")
It works.
How should i send in the input to make it work?
EDIT: The function in question is this if anyone wants to know.
This error is raised when you try to pass a Tensor into a numpy function
You need to use tf.py_func to include python function into tensorflow graph
(also, your change() functin uses data as argument instead of x)
Here is the code that worked for me
import numpy as np
import tensorflow as tf
from changepy import pelt
from changepy.costs import normal_mean
def create_data():
np.random.seed(0)
size = 100
mean_a = 0.0
mean_b = 10.0
mean_c = 0
var = 0.1
data_a = np.random.normal(mean_a, var, size)
data_b = np.random.normal(mean_b, var, size)
data_c = np.random.normal(mean_c, var, size)
data = np.concatenate([data_a, data_b, data_c])
return data
def change(x):
# what else i tried
# data = np.array(data, dtype=np.float)
# above line gives another error mentioned after code
cpts = (pelt(normal_mean(x, np.var(x)), len(x)))
return cpts
sess = tf.Session()
x = tf.placeholder(tf.float32, shape=[300, ], name="myInput")
y = tf.convert_to_tensor(tf.compat.v1.py_func(change, [x], 3*[tf.int64]),np.float32,name="myOutput")
z = sess.run(y,feed_dict={x:create_data()})
print(z)
I have a text file which has 110 rows and 1024 columns of float values. I am trying to load the textfile and it doesnt read any thing.
filename = '300_faults.txt'
filename_queue = tf.train.string_input_producer([filename])
reader = tf.TextLineReader()
_,a = reader.read(filename_queue)
#x = np.loadtxt('300_faults.txt') # working
#a = tf.constant(x,tf.float32) # working
model = tf.initialize_all_variables()
with tf.Session() as session:
session.run(model)
print(session.run(tf.shape(a)))
printing the shape of the variable returns [].
Firstly - tf.shape(a) == [] doesn't mean that variable is empty. All scalars and strings have shape [].
https://www.tensorflow.org/programmers_guide/dims_types
May be you can check "rank" instead - it would be 0 for scalars and strings.
Other than that it looks like string_input_producer is a queue and it needs additional wiring to make ti work.
Please try this
filename = '300_faults.txt'
filename_queue = tf.train.string_input_producer([filename])
reader = tf.TextLineReader()
_,a = reader.read(filename_queue)
#x = np.loadtxt('300_faults.txt') # working
#a = tf.constant(x,tf.float32) # working
model = tf.initialize_all_variables()
with tf.Session() as session:
session.run(model)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
print(session.run(tf.shape(a)))
print(session.run((a)))
coord.request_stop()
coord.join(threads)