Seq2Seq in Python using tensorflow and tensorlayer - python

I am trying to build a chatbot in python using tensorflow and tensorlayer. My code is the following:
from sklearn.feature_extraction.text import CountVectorizer
from nltk.tokenize import word_tokenize
import os
import time
import re
import tensorflow as tf
import tensorlayer as tl
import cPickle as pickle
FILE_DIR = os.path.dirname(os.path.realpath(__file__))
PAD_TOKEN = '<PAD>'
START_TOKEN = '<START>'
END_TOKEN = '<END>'
UNK_TOKEN = '<UNK>'
PAD_ID = 0
START_ID = 1
END_ID = 2
UNK_ID = 3
STARTING_VOCAB = {PAD_TOKEN: PAD_ID, START_TOKEN: START_ID, END_TOKEN: END_ID, UNK_TOKEN: UNK_ID}
_DIGIT_RE = re.compile(br"\d")
class Chatbot(object):
def __init__(self, embedding_dim, n_layers=3):
self.embedding_dim = embedding_dim
self.n_layers = n_layers
self.w2idx = STARTING_VOCAB
self.idx2w = {}
self.encode_seqs = None
self.decode_seqs = None
self.net = None
self.net_rnn = None
self.y = None
#staticmethod
def load():
with open(os.path.join(location, 'object.pkl'), 'rb') as pickle_file:
obj = pickle.load(pickle_file)
obj.encode_seqs = tf.placeholder(dtype=tf.int64, shape=[1, None], name="encode_seqs")
obj.decode_seqs = tf.placeholder(dtype=tf.int64, shape=[1, None], name="decode_seqs")
obj.net, obj.net_rnn = Chatbot.model(obj.encode_seqs, obj.decode_seqs, obj.idx2w, obj.embedding_dim, obj.n_layers, is_train=False, reuse=True)
obj.y = tf.nn.softmax(obj.net.outputs)
new_saver = tf.train.import_meta_graph(os.path.join(location, 'my-model.meta'))
new_saver.restore(sess, tf.train.latest_checkpoint(location))
return obj
#staticmethod
def model(encode_seqs, decode_seqs, idx2w, embedding_dim, n_layers, is_train=True, reuse=False):
with tf.variable_scope("model", reuse=reuse):
# for chatbot, you can use the same embedding layer,
# for translation, you may want to use 2 seperated embedding layers
with tf.variable_scope("embedding") as vs:
net_encode = tl.layers.EmbeddingInputlayer(inputs=encode_seqs,
vocabulary_size=len(idx2w),
embedding_size=embedding_dim,
name='seq_embedding')
vs.reuse_variables()
tl.layers.set_name_reuse(True)
net_decode = tl.layers.EmbeddingInputlayer(inputs=decode_seqs,
vocabulary_size=len(idx2w),
embedding_size=embedding_dim,
name='seq_embedding')
net_rnn = tl.layers.Seq2Seq(net_encode,
net_decode,
cell_fn=tf.contrib.rnn.BasicLSTMCell,
n_hidden=embedding_dim,
initializer=tf.random_uniform_initializer(-0.1, 0.1),
encode_sequence_length=tl.layers.retrieve_seq_length_op2(encode_seqs),
decode_sequence_length=tl.layers.retrieve_seq_length_op2(decode_seqs),
initial_state_encode=None,
dropout=(0.5 if is_train else None),
n_layer=n_layers,
return_seq_2d=True, name='seq2seq')
net_out = tl.layers.DenseLayer(net_rnn, n_units=len(idx2w), act=tf.identity, name='output')
return net_out, net_rnn
def train(self, X_train, y_train, sess, batch_size, n_epochs):
n_step = int(len(X_train) / batch_size)
# Create vocabulary
X_train = [re.sub(_DIGIT_RE, UNK_TOKEN, x.decode('utf-8')) for x in X_train]
y_train = [re.sub(_DIGIT_RE, UNK_TOKEN, x.decode('utf-8')) for x in y_train]
vectorizer = CountVectorizer(tokenizer=word_tokenize)
all_sentences = X_train + y_train
vectorizer.fit_transform(all_sentences)
for k, v in vectorizer.vocabulary_.iteritems():
vectorizer.vocabulary_[k] = v + len(self.w2idx)
self.w2idx.update(vectorizer.vocabulary_)
self.idx2w = dict((v, k) for k, v in self.w2idx.iteritems())
# Transform data from sentences to sequences of ids
for i in range(len(X_train)):
X_train_id_seq, y_train_id_seq = [], []
for w in word_tokenize(X_train[i]):
if w.lower() in self.w2idx:
X_train_id_seq.append(self.w2idx[w.lower()])
else:
X_train_id_seq.append(self.w2idx[UNK_TOKEN])
X_train[i] = X_train_id_seq + [PAD_ID]
for w in word_tokenize(y_train[i]):
if w.lower() in self.w2idx:
y_train_id_seq.append(self.w2idx[w.lower()])
else:
y_train_id_seq.append(self.w2idx[UNK_TOKEN])
y_train[i] = y_train_id_seq + [PAD_ID]
training_encode_seqs = tf.placeholder(dtype=tf.int64, shape=[batch_size, None], name="encode_seqs")
training_decode_seqs = tf.placeholder(dtype=tf.int64, shape=[batch_size, None], name="decode_seqs")
training_target_seqs = tf.placeholder(dtype=tf.int64, shape=[batch_size, None], name="target_seqs")
training_target_mask = tf.placeholder(dtype=tf.int64, shape=[batch_size, None], name="target_mask")
training_net_out, _ = Chatbot.model(training_encode_seqs, training_decode_seqs, self.idx2w, self.embedding_dim, self.n_layers, is_train=True, reuse=False)
# model for inferencing
self.encode_seqs = tf.placeholder(dtype=tf.int64, shape=[1, None], name="encode_seqs")
self.decode_seqs = tf.placeholder(dtype=tf.int64, shape=[1, None], name="decode_seqs")
self.net, self.net_rnn = Chatbot.model(self.encode_seqs, self.decode_seqs, self.idx2w, self.embedding_dim, self.n_layers, is_train=False, reuse=True)
self.y = tf.nn.softmax(self.net.outputs)
loss = tl.cost.cross_entropy_seq_with_mask(logits=training_net_out.outputs, target_seqs=training_target_seqs,
input_mask=training_target_mask, return_details=False, name='cost')
lr = 0.0001
train_op = tf.train.AdamOptimizer(learning_rate=lr).minimize(loss)
tl.layers.initialize_global_variables(sess)
for epoch in range(n_epochs):
epoch_time = time.time()
# shuffle training data
from sklearn.utils import shuffle
X_train, y_train = shuffle(X_train, y_train, random_state=0)
# train an epoch
total_err, n_iter = 0, 0
for X, Y in tl.iterate.minibatches(inputs=X_train, targets=y_train, batch_size=batch_size, shuffle=False):
step_time = time.time()
X = tl.prepro.pad_sequences(X)
_target_seqs = tl.prepro.sequences_add_end_id(Y, end_id=END_ID)
_target_seqs = tl.prepro.pad_sequences(_target_seqs)
_decode_seqs = tl.prepro.sequences_add_start_id(Y, start_id=START_ID, remove_last=False)
_decode_seqs = tl.prepro.pad_sequences(_decode_seqs)
_target_mask = tl.prepro.sequences_get_mask(_target_seqs)
_, err = sess.run([train_op, loss],
{training_encode_seqs: X,
training_decode_seqs: _decode_seqs,
training_target_seqs: _target_seqs,
training_target_mask: _target_mask})
print("Epoch[%d/%d] step:[%d/%d] loss:%f took:%.5fs" % (
epoch, n_epochs, n_iter, n_step, err, time.time() - step_time))
total_err += err;
n_iter += 1
print("Epoch[%d/%d] averaged loss:%f took:%.5fs" % (epoch, n_epochs, total_err / n_iter,
time.time() - epoch_time))
def save(self):
if not os.path.exists(location):
os.makedirs(location)
saver = tf.train.Saver()
saver.save(sess, os.path.join(location, 'my-model'))
tf.train.write_graph(sess.graph, location, 'my-graph.pbtxt')
self.net = None
self.net_rnn = None
self.y = None
self.encode_seqs = None
self.decode_seqs = None
with open(os.path.join(location, 'object.pkl'), 'wb') as pickle_file:
pickle.dump(self, pickle_file)
I can do training perfectly fine, I pass a list of sentences as X_train and another as y_train. What I need help with is saving the model and then reloading it later for training or testing. I tried just using pickle but it gives an error. How can I save and load seq2seq models in python using tensorflow and tensorlayer?

pickle object is not the best way to save your model.
After you finished training use
saver = tf.train.Saver()
saver.save(sess, model_name)
and the load it
saver = tf.train.Saver()
sess = tf.Session()
saver.restore(sess = sess, save_path='sentiment_analysis_tsm')
in order to load it, you'll have to previously build an equivalent model to the one you trained with.
To save the graph object, try using tf.train.write_graph

Related

Using a target size (torch.Size([400])) that is different to the input size (torch.Size([400, 1]))

I'm currently switching from tensorflow to pytorch and facing the warning UserWarning: Using a target size (torch.Size([400])) that is different to the input size (torch.Size([400, 1])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size
I came across that unsqueeze(1) on my target could help to resolve my problem, however, I do so obtain problems in regard of the multitarget which results from the shape my loss function (crossentropy) expects.
Here is a minimal example to my code:
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import Dataset, DataLoader, TensorDataset
import torch.nn.functional as F
X1 = torch.randn(400, 1, 9999)
X2 = torch.randn((400,1, 9999))
aux1 = torch.randn(400,1)
aux2 = torch.randn(400,1)
aux3 = torch.randn(400,1)
y1 = torch.rand(400,)
y2 = torch.rand(400,)
y3 = torch.rand(400,)
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import Dataset, DataLoader, TensorDataset
import torch.nn.functional as F
# In[18]:
class MultiTaskDataset:
def __init__(self,
amplitude,
phase,
weight,
temperature,
humidity,
shelf_life_clf,
shelf_life_pred,
thickness_pred
):
self.amplitude = amplitude
self.phase = phase
self.weight = weight
self.temperature = temperature
self.humidity = humidity
self.shelf_life_clf = shelf_life_clf
self.shelf_life_pred = shelf_life_pred
self.thickness_pred = thickness_pred
def __len__(self):
return self.amplitude.shape[0]
def __getitem__(self, idx):
#inputs
amplitude = self.amplitude[idx]
phase = self.phase[idx]
weight = self.weight[idx]
temperature = self.temperature[idx]
humidity = self.humidity[idx]
#outputs
shelf_life_clf = self.shelf_life_clf[idx]
shelf_life_reg = self.shelf_life_pred[idx]
thickness_pred = self.thickness_pred[idx]
return ([torch.tensor(amplitude, dtype=torch.float32),
torch.tensor(phase, dtype=torch.float32),
torch.tensor(weight, dtype=torch.float32),
torch.tensor(temperature, dtype=torch.float32),
torch.tensor(humidity, dtype=torch.float32)],
[torch.tensor(shelf_life_clf, dtype=torch.long),
torch.tensor(shelf_life_reg, dtype=torch.float32),
torch.tensor(thickness_pred, dtype=torch.float32)])
# In[19]:
# train loader
dataset = MultiTaskDataset(X1, X2, aux1, aux2, aux3,
y1,y2,y3)
train_loader = DataLoader(dataset, batch_size=512, shuffle=True, num_workers=0)
# test loader
# In[20]:
class MyModel(nn.Module):
def __init__(self):
super(MyModel, self).__init__()
self.features_amp = nn.Sequential(
nn.LazyConv1d(1, 3, 1),
)
self.features_phase = nn.Sequential(
nn.LazyConv1d(1, 3, 1),
)
self.backbone1 = nn.Sequential(
nn.LazyConv1d(64,3,1),
nn.LazyConv1d(64,3,1),
nn.AvgPool1d(3),
nn.Dropout(0.25),
)
self.backbone2 = nn.Sequential(
nn.Conv1d(64, 32,3,1),
nn.Conv1d(32, 32,3,1),
nn.AvgPool1d(3),
nn.Dropout(0.25),
)
self.backbone3 = nn.Sequential(
nn.Conv1d(32, 16,3,1),
nn.Conv1d(16, 16,3,1),
nn.AvgPool1d(3),
nn.Dropout(0.25),
)
self.classifier = nn.LazyLinear(2)
self.shelf_life_reg = nn.LazyLinear(1)
self.thickness_reg = nn.LazyLinear(1)
def forward(self, x1, x2, aux1, aux2, aux3):
x1 = self.features_amp(x1)
x2 = self.features_phase(x2)
x1 = x1.view(x1.size(0),-1)
x2 = x2.view(x2.size(0),-1)
x = torch.cat((x1, x2), dim=-1)
print(x.size())
x = x.unsqueeze(1)
print(x.size())
x = self.backbone1(x)
print(x.size())
x = torch.flatten(x, start_dim=1, end_dim=-1)
x = torch.cat([x, aux1, aux2, aux3], dim=-1)
shelf_life_clf = self.classifier(x)
shelf_life_reg = self.shelf_life_reg(x)
thickness_reg = self.thickness_reg(x)
return (shelf_life_clf,
shelf_life_reg,
thickness_reg)
model = MyModel()
optimizer = optim.Adam(model.parameters(), lr=0.003)
criterion1 = nn.CrossEntropyLoss()
criterion2 = nn.MSELoss()
criterion3 = nn.MSELoss()
# In[21]:
def train(epoch):
model.train()
#exp_lr_scheduler.step()
arr_loss = []
#first_batch = next(iter(train_loader))
for batch_idx, (data, target) in enumerate(train_loader):
#amp, phase = data
clf, reg1, reg2 = target
#print(amp.shape, phase.shape)
#print(target[2].shape)
if torch.cuda.is_available():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
data = [data[i].cuda() for i in range(len(data))]
target = [target[i].cuda() for i in range(len(target))]
model.to(device)
optimizer.zero_grad()
output1, output2, output3 = model(*data)
#losses
loss = criterion1(output1, target[0].long())
loss1 = criterion2(output2, target[1].float())
loss2 = criterion3(output3, target[2].float())
loss = loss + loss1 + loss2
#metrices
loss.backward()
optimizer.step()
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, (batch_idx + 1) * len(data), len(train_loader.dataset),
100. * (batch_idx + 1) / len(train_loader), loss.data))
arr_loss.append(loss.data)
return arr_loss
def averaged_accuracy(outputs, targets):
assert len(outputs) != len(targets), "number of outputs should equal the number of targets"
accuracy = []
for i in range(len(outputs)):
_, predicted = torch.max(output1.data, 1)
total += target[0].size(0)
correct += (predicted == target[0]).sum()
acc = correct / total *100
accuracy.append(acc)
return torch.mean(accuracy)
# In[22]:
optimizer = optim.Adam(model.parameters(), lr=0.00003)
criterion1 = nn.CrossEntropyLoss()
criterion2 = nn.MSELoss()
criterion3 = nn.MSELoss()
n_epochs = 10
for epoch in range(n_epochs):
train(epoch)
Can anybody provide guidance to resolve this problem?

ValueError: Target size (torch.Size([16, 2])) must be the same as input size (torch.Size([16, 128, 2]))

I am doing a text classification using pytorch and RoBERTa. The model will classify the text into 2 classes but I got this error while doing the training.
ValueError: Target size (torch.Size([16, 2])) must be the same as input size (torch.Size([16, 128, 2])),And max_len=128,batch_size=16.and this is pretrained model https://huggingface.co/nlp-waseda/roberta-base-japanese
def train_model(dataset_train, dataset_valid, batch_size, model, criterion, optimizer, num_epochs, device=None):
"""モデルの学習を実行し、損失・正解率のログを返す"""
# デバイスの指定
model.to(device)
# dataloaderの作成
dataloader_train = DataLoader(dataset_train, batch_size=batch_size, shuffle=True)
dataloader_valid = DataLoader(dataset_valid, batch_size=len(dataset_valid), shuffle=False)
# 学習
log_train = []
log_valid = []
for epoch in range(num_epochs):
# 開始時刻の記録
s_time = time.time()
# 訓練モードに設定
model.train()
for data in dataloader_train:
# デバイスの指定
ids = data['ids'].to(device)
mask = data['mask'].to(device)
labels = data['labels'].to(device)
# 勾配をゼロで初期化
optimizer.zero_grad()
# 順伝播 + 誤差逆伝播 + 重み更新
outputs = model(ids, mask)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# 損失と正解率の算出
loss_train, acc_train = calculate_loss_and_accuracy(model, dataloader_train, device, criterion=criterion)
loss_valid, acc_valid = calculate_loss_and_accuracy(model, dataloader_valid, device, criterion=criterion)
log_train.append([loss_train, acc_train])
log_valid.append([loss_valid, acc_valid])
# 終了時刻の記録
e_time = time.time()
# ログを出力
print(f'epoch: {epoch + 1}, loss_train: {loss_train:.4f}, accuracy_train: {acc_train:.4f}, loss_valid: {loss_valid:.4f}, accuracy_valid: {acc_valid:.4f}, {(e_time - s_time):.4f}sec')
return {'train': log_train, 'valid': log_valid}
class RoBERTaClass(torch.nn.Module):
def __init__(self, pretrained, drop_rate, otuput_size):
super().__init__()
self.roberta = AutoModelForMaskedLM.from_pretrained(pretrained)
self.drop = torch.nn.Dropout(drop_rate)
self.fc = torch.nn.Linear(32000,otuput_size)
def forward(self, ids, mask):
out= self.roberta(ids, attention_mask=mask,return_dict=False)
out = self.fc(self.drop(out[0]))
return out
class CreateDataset(Dataset):
def __init__(self, X, y, tokenizer, max_len):
self.X = X
self.y = y
self.tokenizer = tokenizer
self.max_len = max_len
def __len__(self): # len(Dataset)で返す値を指定
return len(self.y)
def __getitem__(self, index): # Dataset[index]で返す値を指定
text = self.X[index]
inputs = self.tokenizer.encode_plus(
text,
add_special_tokens=True,
max_length=self.max_len,
pad_to_max_length=True
)
ids = inputs['input_ids']
mask = inputs['attention_mask']
return {
'ids': torch.LongTensor(ids),
'mask': torch.LongTensor(mask),
'labels': torch.Tensor(self.y[index])
}
# 最大系列長の指定
MAX_LEN = 128
# tokenizerの取得
tokenizer = AutoTokenizer.from_pretrained(pretrained)
#tokenizer = T5Tokenizer.from_pretrained(pretrained)
#tokenizer.do_lower_case = True
# Datasetの作成
dataset_train = CreateDataset(train['text'], train[categories].values, tokenizer, MAX_LEN)
dataset_valid = CreateDataset(valid['text'], valid[categories].values, tokenizer, MAX_LEN)
I am very new to this field. Any help and advice is very appreciated. Thanks in advance!

torch.save(model.state_dict()) line comes error while model complated train and trying to save it how can i solve?

I'm working on some code about nlp. I want to train and save model but here comes this error. I searched some documentation but i didn't find right solution. How can i solve this problem?
import torch,time
import torch.nn as nn
input_dim = 5
hidden_dim = 10
n_layers = 1
lstm_layer = nn.LSTM(input_dim, hidden_dim, n_layers, batch_first=True)
batch_size = 1
seq_len = 1
inp = torch.randn(batch_size, seq_len, input_dim)
hidden_state = torch.randn(n_layers, batch_size, hidden_dim)
cell_state = torch.randn(n_layers, batch_size, hidden_dim)
hidden = (hidden_state, cell_state)
out, hidden = lstm_layer(inp, hidden)
print("Output shape: ", out.shape)
print("Hidden: ", hidden)
seq_len = 3
inp = torch.randn(batch_size, seq_len, input_dim)
out, hidden = lstm_layer(inp, hidden)
print(out.shape)
# Obtaining the last output
out = out.squeeze()[-1, :]
print(out.shape)
import bz2
from collections import Counter
import re
import nltk
import numpy as np
#nltk.download('punkt')
train_file = bz2.BZ2File('C:/Users/DELL/Dogal-Dil-Isleme/Xml-Files/trwiktionary-20200301-pages-articles-multistream.xml.bz2')
test_file = bz2.BZ2File('C:/Users/DELL/Dogal-Dil-Isleme/Xml-Files/trwikisource-20200601-pages-articles.xml.bz2')
train_file = train_file.readlines()
test_file = test_file.readlines()
num_train = 200
num_test = 50
train_file = [x.decode('utf-8') for x in train_file[:num_train]]
test_file = [x.decode('utf-8') for x in test_file[:num_test]]
train_labels = [0 if x.split(' ')[0] == '__label__1' else 1 for x in train_file]
train_sentences = [x.split(' ', 1)[1][:-1].lower() for x in train_file]
test_labels = [0 if x.split(' ')[0] == '__label__1' else 1 for x in test_file]
test_sentences = [x.split(' ', 1)[1][:-1].lower() for x in test_file]
for i in range(len(train_sentences)):
train_sentences[i] = re.sub('\d','0',train_sentences[i])
for i in range(len(test_sentences)):
test_sentences[i] = re.sub('\d','0',test_sentences[i])
for i in range(len(train_sentences)):
if 'www.' in train_sentences[i] or 'http:' in train_sentences[i] or 'https:' in train_sentences[i] or '.com' in train_sentences[i]:
train_sentences[i] = re.sub(r"([^ ]+(?<=\.[a-z]{3}))", "<url>", train_sentences[i])
for i in range(len(test_sentences)):
if 'www.' in test_sentences[i] or 'http:' in test_sentences[i] or 'https:' in test_sentences[i] or '.com' in test_sentences[i]:
test_sentences[i] = re.sub(r"([^ ]+(?<=\.[a-z]{3}))", "<url>", test_sentences[i])
words = Counter() # Dictionary that will map a word to the number of times it appeared in all the training sentences
for i, sentence in enumerate(train_sentences):
train_sentences[i] = []
for word in nltk.word_tokenize(sentence):
words.update([word.lower()])
train_sentences[i].append(word)
if i%20000 == 0:
print(str((i*100)/num_train) + "% done")
print("100% done")
words = {k:v for k,v in words.items() if v>1}
words = sorted(words, key=words.get, reverse=True)
words = ['_PAD','_UNK'] + words
word2idx = {o:i for i,o in enumerate(words)}
idx2word = {i:o for i,o in enumerate(words)}
for i, sentence in enumerate(train_sentences):
train_sentences[i] = [word2idx[word] if word in word2idx else 0 for word in sentence]
for i, sentence in enumerate(test_sentences):
# For test sentences, we have to tokenize the sentences as well
test_sentences[i] = [word2idx[word.lower()] if word.lower() in word2idx else 0 for word in nltk.word_tokenize(sentence)]
def pad_input(sentences, seq_len):
features = np.zeros((len(sentences), seq_len),dtype=int)
for ii, review in enumerate(sentences):
if len(review) != 0:
features[ii, -len(review):] = np.array(review)[:seq_len]
return features
seq_len = 200 # The length that the sentences will be padded/shortened to
train_sentences = pad_input(train_sentences, seq_len)
test_sentences = pad_input(test_sentences, seq_len)
train_labels = np.array(train_labels)
test_labels = np.array(test_labels)
split_frac = 0.5 # 50% validation, 50% test
split_id = int(split_frac * len(test_sentences))
val_sentences, test_sentences = test_sentences[:split_id], test_sentences[split_id:]
val_labels, test_labels = test_labels[:split_id], test_labels[split_id:]
import torch
from torch.utils.data import TensorDataset, DataLoader
import torch.nn as nn
train_data = TensorDataset(torch.from_numpy(train_sentences), torch.from_numpy(train_labels))
val_data = TensorDataset(torch.from_numpy(val_sentences), torch.from_numpy(val_labels))
test_data = TensorDataset(torch.from_numpy(test_sentences), torch.from_numpy(test_labels))
batch_size = 200
train_loader = DataLoader(train_data, shuffle=True, batch_size=batch_size)
val_loader = DataLoader(val_data, shuffle=True, batch_size=batch_size)
test_loader = DataLoader(test_data, shuffle=True, batch_size=batch_size)
# torch.cuda.is_available() checks and returns a Boolean True if a GPU is available, else it'll return False
is_cuda = torch.cuda.is_available()
# If we have a GPU available, we'll set our device to GPU. We'll use this device variable later in our code.
if is_cuda:
device = torch.device("cuda")
else:
device = torch.device("cpu")
class SentimentNet(nn.Module):
def __init__(self, vocab_size, output_size, embedding_dim, hidden_dim, n_layers, drop_prob=0.5):
super(SentimentNet, self).__init__()
self.output_size = output_size
self.n_layers = n_layers
self.hidden_dim = hidden_dim
self.embedding = nn.Embedding(vocab_size, embedding_dim)
self.lstm = nn.LSTM(embedding_dim, hidden_dim, n_layers, dropout=drop_prob, batch_first=True)
self.dropout = nn.Dropout(drop_prob)
self.fc = nn.Linear(hidden_dim, output_size)
self.sigmoid = nn.Sigmoid()
def forward(self, x, hidden):
batch_size = x.size(0)
x = x.long()
embeds = self.embedding(x)
lstm_out, hidden = self.lstm(embeds, hidden)
lstm_out = lstm_out.contiguous().view(-1, self.hidden_dim)
out = self.dropout(lstm_out)
out = self.fc(out)
out = self.sigmoid(out)
out = out.view(batch_size, -1)
out = out[:,-1]
return out, hidden
def init_hidden(self, batch_size):
weight = next(self.parameters()).data
hidden = (weight.new(self.n_layers, batch_size, self.hidden_dim).zero_().to(device),
weight.new(self.n_layers, batch_size, self.hidden_dim).zero_().to(device))
return hidden
vocab_size = len(word2idx) + 1
output_size = 1
embedding_dim = 400
hidden_dim = 512
n_layers = 2
model = SentimentNet(vocab_size, output_size, embedding_dim, hidden_dim, n_layers)
model.to(device)
lr=0.005
criterion = nn.BCELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=lr)
epochs = 2
counter = 0
print_every = 1000
clip = 5
valid_loss_min = np.Inf
model.train()
for i in range(epochs):
h = model.init_hidden(batch_size)
for inputs, labels in train_loader:
counter += 1
h = tuple([e.data for e in h])
inputs, labels = inputs.to(device), labels.to(device)
model.zero_grad()
output, h = model(inputs, h)
loss = criterion(output.squeeze(), labels.float())
loss.backward()
nn.utils.clip_grad_norm_(model.parameters(), clip)
optimizer.step()
if counter%print_every == 0:
val_h = model.init_hidden(batch_size)
val_losses = []
model.eval()
for inp, lab in val_loader:
val_h = tuple([each.data for each in val_h])
inp, lab = inp.to(device), lab.to(device)
out, val_h = model(inp, val_h)
val_loss = criterion(out.squeeze(), lab.float())
val_losses.append(val_loss.item())
model.train()
print("Epoch: {}/{}...".format(i+1, epochs),
"Step: {}...".format(counter),
"Loss: {:.6f}...".format(loss.item()),
"Val Loss: {:.6f}".format(np.mean(val_losses)))
if np.mean(val_losses) <= valid_loss_min:
torch.save(model.state_dict(), 'C:/Users/DELL/Dogal-Dil-Isleme/Models/state_dict.pt')
print('Validation loss decreased ({:.6f} --> {:.6f}). Saving model ...'.format(valid_loss_min,np.mean(val_losses)))
valid_loss_min = np.mean(val_losses)
time.sleep(1)
# Loading the best model
model.load_state_dict(torch.load('C:/Users/DELL/Dogal-Dil-Isleme/Models/state_dict.pt'))
test_losses = []
num_correct = 0
h = model.init_hidden(batch_size)
model.eval()
for inputs, labels in test_loader:
h = tuple([each.data for each in h])
inputs, labels = inputs.to(device), labels.to(device)
output, h = model(inputs, h)
test_loss = criterion(output.squeeze(), labels.float())
test_losses.append(test_loss.item())
pred = torch.round(output.squeeze()) # Rounds the output to 0/1
correct_tensor = pred.eq(labels.float().view_as(pred))
correct = np.squeeze(correct_tensor.cpu().numpy())
num_correct += np.sum(correct)
print("Test loss: {:.3f}".format(np.mean(test_losses)))
test_acc = num_correct/len(test_loader.dataset)
print("Test accuracy: {:.3f}%".format(test_acc*100))
i tried a create new folder and change path but all the ways comes error :)
i read pytorch documentation and change recommended code but error still came.
i will share some link for your reading about this issue.
same issue
pytorch documentation
how can i fix or is there any alternative way to save model?
Try changing it to: model.load_state_dict(torch.load('C:/Users/DELL/Dogal-Dil-Isleme/Models/state_dict'))

softmax_cross_entropy_with_logits nan

I have extracted CNN features from a pretrain vgg19 with size 4096. Then I am using a shallower architecture to train a classifier with softmax and center losses. Unfortunately, the softmax loss function returns nan. There is detailed discussion available here, however I am not able to resolve the problem with clip because labels and logits are in two different data format (int64, float32). Furthermore, I also changed the learning rate but still got the same error.
Can some please let me know, how to resolve this situation.
from __future__ import division
from __future__ import print_function
import csv
import numpy as np
import tensorflow as tf
from retrieval_model import setup_train_model
FLAGS = None
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
def get_name(read_file):
feat_lst = []
identifier_lst = []
with open(read_file, 'r') as csvfile:
read_file = csv.reader(csvfile, delimiter=',')
for row in read_file:
feat = row[:-1]
s_feat = [float(i) for i in feat]
identifier = row[-1]
feat_lst.append(s_feat)
identifier_lst.append(identifier)
return feat_lst, identifier_lst
def get_batch(batch_index, batch_size, labels, f_lst):
start_ind = batch_index * batch_size
end_ind = start_ind + batch_size
return f_lst[start_ind:end_ind], labels[start_ind:end_ind]
def creat_dict(orig_labels):
dict = {}
count = 0
for x in orig_labels:
n_label = dict.get(x, None)
if n_label is None:
dict[x] = count
count += 1
return dict
def main(_):
save_dir = 'model/one-branch-ckpt'
train_file = 'gtrain.csv'
img_feat, img_labels = get_name(train_file)
map_dict = creat_dict(img_labels)
img_labels = [map_dict.get(x) for x in img_labels]
im_feat_dim = 4096
batch_size = 50
max_num_epoch = 10
steps_per_epoch = len(img_feat) // batch_size
num_steps = steps_per_epoch * max_num_epoch
# Setup placeholders for input variables.
im_feat_plh = tf.placeholder(tf.float32, shape=[batch_size, im_feat_dim])
label_plh = tf.placeholder(tf.int64, shape=(batch_size), name='labels')
train_phase_plh = tf.placeholder(tf.bool)
# Setup training operation.
t_l = setup_train_model(im_feat_plh, train_phase_plh, label_plh, classes)
# Setup optimizer.
global_step = tf.Variable(0, trainable=False)
init_learning_rate = 0.0001
learning_rate = tf.train.exponential_decay(init_learning_rate, global_step,
steps_per_epoch, 0.794, staircase=True)
optim = tf.train.AdamOptimizer(init_learning_rate)
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
train_step = optim.minimize(t_l, global_step=global_step)
# Setup model saver.
saver = tf.train.Saver(save_relative_paths=True,max_to_keep=1)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(num_steps):
im_feats, labels = get_batch(
i % steps_per_epoch, batch_size, img_labels, img_feat)
feed_dict = {
im_feat_plh: im_feats,
label_plh: labels,
train_phase_plh: True,
}
[_, loss_val] = sess.run([train_step, t_l], feed_dict=feed_dict)
if i % 100 == 0:
print('Epoch: %d Step: %d Loss: %f' % (i // steps_per_epoch, i, loss_val))
if i % steps_per_epoch == 0 and i > 0:
print('Saving checkpoint at step %d' % i)
saver.save(sess, save_dir, global_step=global_step)
if __name__ == '__main__':
np.random.seed(0)
tf.set_random_seed(0)
tf.app.run(main=main)
**************************retrieval_model********************************
def setup_train_model(im_feats, train_phase, im_labels, nrof_classes):
alfa = 0.9
# nrof_classes = 28783
i_embed = embedding_model(im_feats, train_phase, im_labels)
c_l = embedding_loss(i_embed, im_labels, alfa, nrof_classes)
loss = softmax_loss(i_embed, im_labels)
total_loss = loss + c_l
return total_loss
def add_fc(inputs, outdim, train_phase, scope_in):
fc = fully_connected(inputs, outdim, activation_fn=None, scope=scope_in + '/fc')
fc_bnorm = tf.layers.batch_normalization(fc, momentum=0.1, epsilon=1e-5,
training=train_phase, name=scope_in + '/bnorm')
fc_relu = tf.nn.relu(fc_bnorm, name=scope_in + '/relu')
fc_out = tf.layers.dropout(fc_relu, seed=0, training=train_phase, name=scope_in + '/dropout')
return fc_out
def embedding_loss(features, label, alfa, nrof_classes):
nrof_features = features.get_shape()[1]
centers = tf.get_variable('centers', [nrof_classes, nrof_features], dtype=tf.float32,
initializer=tf.constant_initializer(0), trainable=False)
label = tf.reshape(label, [-1])
centers_batch = tf.gather(centers, label)
diff = (1 - alfa) * (centers_batch - features)
#centers = tf.scatter_sub(centers, label, diff)
center_loss = tf.reduce_mean(tf.square(features - centers_batch))
#softmax_loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(labels=label, logits=features))
#total_loss = softmax_loss + center_loss
return center_loss
def embedding_model(im_feats, train_phase, im_labels,
fc_dim=2048, embed_dim=512):
# Image branch.
im_fc1 = add_fc(im_feats, fc_dim, train_phase, 'im_embed_1')
im_fc2 = fully_connected(im_fc1, embed_dim, activation_fn=None,
scope='im_embed_2')
return tf.nn.l2_normalize(im_fc2, 1, epsilon=1e-10)
def softmax_loss(feat, im_labels):
label = tf.reshape(im_labels, [-1])
softmax = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(labels=label, logits=feat))
return softmax

Projector in Tensorboard python application

I have the following code and sample which is working fine and exactly I want it to:
import numpy as np
import pandas as pd
import sklearn
import sklearn.preprocessing
import datetime
import os
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.contrib.tensorboard.plugins import projector
valid_set_size_percentage = 3
test_set_size_percentage = 3
seq_len = 5 # choose sequence length
df = pd.read_csv("Test.csv", encoding = 'utf-16',sep=',',index_col = 0)
df.head()
def normalize_data(df):
cols = list(df_stock.columns.values)
min_max_scaler = sklearn.preprocessing.MinMaxScaler()
df = pd.DataFrame(min_max_scaler.fit_transform(df.values))
df.columns = cols
return df
def load_data(stock, seq_len):
data_raw = stock.as_matrix() # convert to numpy array
data = []
print(data_raw.shape)
for index in range(len(data_raw) - seq_len):
data.append(data_raw[index: index + seq_len])
data = np.array(data);
valid_set_size = int(np.round(valid_set_size_percentage/100*data.shape[0]));
test_set_size = int(np.round(test_set_size_percentage/100*data.shape[0]));
train_set_size = data.shape[0] - (valid_set_size + test_set_size);
x_train = data[:train_set_size,:-1,:]
y_train = data[:train_set_size,-1,:4]
x_valid = data[train_set_size:train_set_size+valid_set_size,:-1,:]
y_valid = data[train_set_size:train_set_size+valid_set_size,-1,:4]
x_test = data[train_set_size+valid_set_size:,:-1,:]
y_test = data[train_set_size+valid_set_size:,-1,:4]
return [x_train, y_train, x_valid, y_valid, x_test, y_test]
df_stock = df.copy()
cols = list(df_stock.columns.values)
print('df_stock.columns.values = ', cols)
df_stock_norm = df_stock.copy()
df_stock_norm = normalize_data(df_stock_norm)
x_train, y_train, x_valid, y_valid, x_test, y_test = load_data(df_stock_norm, seq_len)
print(y_train[:2])
print('x_train.shape = ',x_train.shape)
print('y_train.shape = ', y_train.shape)
print('Inputs = ',x_train.shape[2])
print('Outputs = ', y_train.shape[1])
print('x_valid.shape = ',x_valid.shape)
print('y_valid.shape = ', y_valid.shape)
print('x_test.shape = ', x_test.shape)
print('y_test.shape = ',y_test.shape)
index_in_epoch = 0;
perm_array = np.arange(x_train.shape[0])
np.random.shuffle(perm_array)
def get_next_batch(batch_size):
global index_in_epoch, x_train, perm_array
if index_in_epoch > x_train.shape[0]:
start = 0 # start next epoch
index_in_epoch = 0#batch_size
start = index_in_epoch
index_in_epoch += batch_size
end = index_in_epoch
return x_train[perm_array[start:end]], y_train[perm_array[start:end]]
n_steps = seq_len -1
n_inputs = x_train.shape[2]
n_neurons = 100
n_outputs = y_train.shape[-1]
n_layers = 2
learning_rate = 0.001
batch_size =10
n_epochs = 100
train_set_size = x_train.shape[0]
test_set_size = x_test.shape[0]
tf.reset_default_graph()
X = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None,n_outputs])
layers = [tf.contrib.rnn.LSTMCell(num_units=n_neurons,
activation=tf.nn.leaky_relu, use_peepholes = True)
for layer in range(n_layers)]
multi_layer_cell = tf.contrib.rnn.MultiRNNCell(layers)
rnn_outputs, states = tf.nn.dynamic_rnn(multi_layer_cell, X, dtype=tf.float32)
stacked_rnn_outputs = tf.reshape(rnn_outputs, [-1, n_neurons])
stacked_outputs = tf.layers.dense(stacked_rnn_outputs, n_outputs)
outputs = tf.reshape(stacked_outputs, [-1, n_steps, n_outputs])
outputs = outputs[:,n_steps-1,:] # keep only last output of sequence
loss = tf.reduce_mean(tf.squared_difference(outputs, y)) # loss function = mean squared error
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
training_op = optimizer.minimize(loss)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for iteration in range(int(n_epochs*train_set_size/batch_size)):
x_batch, y_batch = get_next_batch(batch_size) # fetch the next training batch
sess.run(training_op, feed_dict={X: x_batch, y: y_batch})
if iteration % int(1*train_set_size/batch_size) == 0:
mse_train = loss.eval(feed_dict={X: x_train, y: y_train})
mse_valid = loss.eval(feed_dict={X: x_valid, y: y_valid})
mse_test = loss.eval(feed_dict={X: x_test, y: y_test})
print('%.2f epochs: MSE train/valid/test = %.3f/%.3f/%.3f'%(
iteration*batch_size/train_set_size, mse_train, mse_valid,mse_test))
try:
save_path = saver.save(sess, "modelfile\\model"+str(iteration)+".ckpt")
except Exception as e:
print(e)
if not os.path.exists("modelfile\\"):
os.makedirs("modelfile\\")
save_path = saver.save(sess, "modelfile\\model"+str(iteration)+".ckpt")
The following is my sample of what I am trying to execute:
Same data Please click and see
I am willing to add the Projector of the Tensorboard to my code. But I could not understand how I can make it. I want to visualize the different inputs I am giving for my training. I am supplying the following columns and trying to predict the ohlc values.
'o', 'h', 'l', 'c', 'rel1', 'rel2', 'rel3', 'rel4', 'rel5', 'rel6', 'rel7', 'rel8'
I want to visualize the above columns in the projector to know how they are relating with each other to give me the output.
Please let me know what I can do to get what I am willing to.
EDITED:
I have tried something as follows but cannot see the projector tab:
tf.reset_default_graph()
X = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None,n_outputs])
symbols = tf.placeholder(tf.int32, [None, 1], name='stock_labels')
embed_matrix = tf.Variable(
tf.random_uniform([1, n_inputs],0.0, 1.0),
name="embed_matrix"
)
stacked_symbols = tf.tile(symbols, [batch_size,n_steps], name='stacked_stock_labels')
stacked_embeds = tf.nn.embedding_lookup(embed_matrix, stacked_symbols)
# stacked_embeds = tf.nn.embedding_lookup(embed_matrix)
# After concat, inputs.shape = (batch_size, num_steps, input_size + embed_size)
inputs_with_embed = tf.concat([X, stacked_embeds], axis=2, name="inputs_with_embed")
embed_matrix_summ = tf.summary.histogram("embed_matrix", embed_matrix)
And edited the following lines in the session code:
merged_sum = tf.summary.merge_all()
global_step = 0
# Set up the logs folder
writer = tf.summary.FileWriter('logs')
writer.add_graph(sess.graph)
projector_config = projector.ProjectorConfig()
# You can add multiple embeddings. Here we add only one.
added_embed = projector_config.embeddings.add()
added_embed.tensor_name = embed_matrix.name
# Link this tensor to its metadata file (e.g. labels).
shutil.copyfile("logs\\metadata.tsv",
"logs\\metadata1.tsv")
added_embed.metadata_path = "metadata.tsv"
# The next line writes a projector_config.pbtxt in the LOG_DIR. TensorBoard will
# read this file during startup.
projector.visualize_embeddings(writer, projector_config)
sess.run(tf.global_variables_initializer())
if iteration % int(1*train_set_size/batch_size) == 0:
global_step += 1
mse_train = loss.eval(feed_dict={X: x_train, y: y_train})
mse_valid = loss.eval(feed_dict={X: x_valid, y: y_valid})
mse_test = loss.eval(feed_dict={X: x_test, y: y_test})
_,train_merge = sess.run([outputs,merged_sum], feed_dict={X: x_train, y: y_train})
writer.add_summary(train_merge, global_step=global_step)
Here is teh metadata.tsv file
Please let me know what I missed.

Categories

Resources