I have trained my first CNN model. I took first 100 images of cats and first 100 images of dogs from Kaggle dataset as my custom dataset.
After the model is trained I'm trying to feed the same images back to the model to see predictions. As result I get score from 0.5 to 0.6 on all images. While I though it should be <0.5 for cats and >0.5 for dogs. Is it a problem of my model architecture, the training process or my dataset is just too small? Why no images gets below 0.5 at all?
Here is my code:
First I generate .csv file to be processed:
import pandas as pd
import os
import torch
device = ("cuda" if torch.cuda.is_available() else "cpu")
train_df = pd.DataFrame(columns=["img_name","label"])
train_df["img_name"] = os.listdir("train/")
for idx, i in enumerate(os.listdir("train/")):
if "cat" in i:
train_df["label"][idx] = 0
if "dog" in i:
train_df["label"][idx] = 1
train_df.to_csv (r'train_csv.csv', index = False, header=True)
Then I prepare the dataset:
from torch.utils.data import Dataset
import pandas as pd
import os
from PIL import Image
import torch
class CatsAndDogsDataset(Dataset):
def __init__(self, root_dir, annotation_file, transform=None):
self.root_dir = root_dir
self.annotations = pd.read_csv(annotation_file)
self.transform = transform
def __len__(self):
return len(self.annotations)
def __getitem__(self, index):
img_id = self.annotations.iloc[index, 0]
img = Image.open(os.path.join(self.root_dir, img_id)).convert("RGB")
y_label = torch.tensor(float(self.annotations.iloc[index, 1]))
if self.transform is not None:
img = self.transform(img)
return (img, y_label)
This is my model:
import torch.nn as nn
import torchvision.models as models
class CNN(nn.Module):
def __init__(self, train_CNN=False, num_classes=1):
super(CNN, self).__init__()
self.train_CNN = train_CNN
self.inception = models.inception_v3(pretrained=True, aux_logits=False)
self.inception.fc = nn.Linear(self.inception.fc.in_features, num_classes)
self.relu = nn.ReLU()
self.dropout = nn.Dropout(0.5)
self.sigmoid = nn.Sigmoid()
def forward(self, images):
features = self.inception(images)
return self.sigmoid(self.dropout(self.relu(features))).squeeze(1)
This is my hyper-params, transformations and dataloaders:
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
num_epochs = 10
learning_rate = 0.00001
train_CNN = False
batch_size = 32
shuffle = True
pin_memory = True
num_workers = 0
transform = transforms.Compose(
[
transforms.Resize((356, 356)),
transforms.CenterCrop((299, 299)),
transforms.ToTensor(),
transforms.Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
),
]
)
dataset = CatsAndDogsDataset("train","train_csv.csv",transform=transform)
train_size = int(0.8 * len(dataset))
validation_size = len(dataset) - train_size
train_set, validation_set = torch.utils.data.random_split(dataset, [train_size, validation_size])
train_loader = DataLoader(dataset=train_set, shuffle=shuffle, batch_size=batch_size,num_workers=num_workers,pin_memory=pin_memory)
validation_loader = DataLoader(dataset=validation_set, shuffle=shuffle, batch_size=batch_size,num_workers=num_workers, pin_memory=pin_memory)
model = CNN().to(device)
criterion = nn.BCELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
for name, param in model.inception.named_parameters():
if "fc.weight" in name or "fc.bias" in name:
param.requires_grad = True
else:
param.requires_grad = train_CNN
and accuracy check:
def check_accuracy(loader, model):
num_correct = 0
num_samples = 0
model.eval()
with torch.no_grad():
for x, y in loader:
x = x.to(device=device)
y = y.to(device=device)
scores = model(x)
predictions = torch.tensor([1.0 if i >= 0.5 else 0.0 for i in scores]).to(device)
num_correct += (predictions == y).sum()
num_samples += predictions.size(0)
model.train()
return f"{float(num_correct)/float(num_samples)*100:.2f}"
And this is my training function:
from tqdm import tqdm
def train():
model.train()
for epoch in range(num_epochs):
loop = tqdm(train_loader, total = len(train_loader), leave = True)
for imgs, labels in loop:
imgs = imgs.to(device)
labels = labels.to(device)
outputs = model(imgs)
loss = criterion(outputs, labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
loop.set_description(f"Epoch [{epoch}/{num_epochs}]")
loop.set_postfix(loss = loss.item(), val_acc = check_accuracy(validation_loader, model))
if __name__ == "__main__":
train()
Epoch [0/10]: 100%|██████████| 6/6 [12:00<00:00, 120.10s/it, loss=0.652, val_acc=39.02]
Epoch [1/10]: 100%|██████████| 6/6 [11:51<00:00, 118.61s/it, loss=0.497, val_acc=39.02]
Epoch [2/10]: 100%|██████████| 6/6 [11:27<00:00, 114.51s/it, loss=0.693, val_acc=39.02]
Epoch [3/10]: 100%|██████████| 6/6 [11:04<00:00, 110.77s/it, loss=0.531, val_acc=39.02]
Epoch [4/10]: 100%|██████████| 6/6 [10:58<00:00, 109.68s/it, loss=0.693, val_acc=39.02]
Epoch [5/10]: 100%|██████████| 6/6 [12:03<00:00, 120.51s/it, loss=0.803, val_acc=39.02]
Epoch [6/10]: 100%|██████████| 6/6 [11:33<00:00, 115.62s/it, loss=0.693, val_acc=39.02]
Epoch [7/10]: 100%|██████████| 6/6 [11:27<00:00, 114.56s/it, loss=0.675, val_acc=39.02]
Epoch [8/10]: 100%|██████████| 6/6 [11:42<00:00, 117.10s/it, loss=0.806, val_acc=39.02]
Epoch [9/10]: 100%|██████████| 6/6 [12:15<00:00, 122.58s/it, loss=0.768, val_acc=39.02]
Then I loop through the model checking predictions on each image (the dataset variable is available because it is in the same Jupyter Notebook):
import numpy as np
with torch.no_grad():
for index in range(len(dataset)):
item = dataset[index]
image_tensor = item[0]
true_target = item[1]
img_np = np.array(image_tensor)
img_normalized = img_np.transpose(1, 2, 0)
image = torch.unsqueeze(image_tensor, 0)
prediction = model(image)
predicted_class = prediction[0]
print("class: " + str(true_target.item()) + " score: " + str(predicted_class.item()))
The output:
class: 0.0 score: 0.547210156917572
class: 0.0 score: 0.5
class: 0.0 score: 0.5348594188690186
class: 0.0 score: 0.5336627960205078
class: 0.0 score: 0.5178861618041992
class: 0.0 score: 0.5692692995071411
class: 0.0 score: 0.5
class: 0.0 score: 0.5381814241409302
class: 0.0 score: 0.54604572057724
class: 0.0 score: 0.5157472491264343
class: 0.0 score: 0.5257323980331421
class: 0.0 score: 0.5137990713119507
class: 0.0 score: 0.5247158408164978
class: 0.0 score: 0.5320644378662109
class: 0.0 score: 0.5775637626647949
class: 0.0 score: 0.528205156326294
class: 0.0 score: 0.5457945466041565
class: 0.0 score: 0.5301501154899597
class: 0.0 score: 0.5102765560150146
class: 0.0 score: 0.5069065690040588
class: 0.0 score: 0.519408106803894
class: 0.0 score: 0.5414850115776062
class: 0.0 score: 0.5041879415512085
class: 0.0 score: 0.5055546760559082
show more (open the raw output data in a text editor) ...
class: 1.0 score: 0.5
class: 1.0 score: 0.5
class: 1.0 score: 0.5166758894920349
class: 1.0 score: 0.5343206524848938
class: 1.0 score: 0.5716230869293213
So no cats get predicted
can you change your model arch to this(just remove dropout and relu)
import torch.nn as nn
import torchvision.models as models
class CNN(nn.Module):
def __init__(self, train_CNN=False, num_classes=1):
super(CNN, self).__init__()
self.train_CNN = train_CNN
self.inception = models.inception_v3(pretrained=True, aux_logits=False)
self.inception.fc = nn.Linear(self.inception.fc.in_features, num_classes)
self.dropout = nn.Dropout(0.5)
self.sigmoid = nn.Sigmoid()
def forward(self, images):
features = self.inception(images)
return self.sigmoid(features).squeeze(1)
And just try with model.eval() before doing inference, Since u have used dropout
Related
I have the following code snippet from PyTorch geometric example. I want to use a learning rate that decreases as the loss value during training decreases. I tried using scheduler but that didn't work for me.
A clean code-snippet is below. Can anyone provide valuable suggestions or help on this matter?
import torch
import torch.nn.functional as F
from torch_geometric.datasets import Planetoid
import torch_geometric.transforms as T
from torch_geometric.nn import AGNNConv
dataset = 'Cora'
path = 'Cora'
dataset = Planetoid(path, dataset, transform=T.NormalizeFeatures())
data = dataset[0]
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.lin1 = torch.nn.Linear(dataset.num_features, 16)
self.prop1 = AGNNConv(requires_grad=False)
self.prop2 = AGNNConv(requires_grad=True)
self.lin2 = torch.nn.Linear(16, dataset.num_classes)
def forward(self):
x = F.dropout(data.x, training=self.training)
x = F.relu(self.lin1(x))
x = self.prop1(x, data.edge_index)
x = self.prop2(x, data.edge_index)
x = F.dropout(x, training=self.training)
x = self.lin2(x)
return F.log_softmax(x, dim=1)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model, data = Net().to(device), data.to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)
def train():
model.train()
optimizer.zero_grad()
F.nll_loss(model()[data.train_mask], data.y[data.train_mask]).backward()
optimizer.step()
def test():
model.eval()
logits, accs = model(), []
for _, mask in data('train_mask', 'val_mask', 'test_mask'):
pred = logits[mask].max(1)[1]
acc = pred.eq(data.y[mask]).sum().item() / mask.sum().item()
accs.append(acc)
return accs
best_val_acc = test_acc = 0
for epoch in range(1, 201):
train()
train_acc, val_acc, tmp_test_acc = test()
if val_acc > best_val_acc:
best_val_acc = val_acc
test_acc = tmp_test_acc
log = 'Epoch: {:03d}, Train: {:.4f}, Val: {:.4f}, Test: {:.4f}'
print(log.format(epoch, train_acc, best_val_acc, test_acc))
When I wrap my model in nn.DataParallel(model) and start training my screen freezes and I have to manually restart the computer every time.
I've tried a few variations, like not adding .to(device) to every x and y, but whenever nn.DataParallel is used I seem to cause the computer to freeze.
import random
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torchvision import models, datasets, transforms
import torch.utils.data
DataLoader = torch.utils.data.DataLoader
random_split = torch.utils.data.random_split
global_rank = 0
MNIST = datasets.MNIST
class MLPClassifier(nn.Module):
def __init__(self):
super(MLPClassifier, self).__init__()
self.layer_1 = torch.nn.Linear(28 * 28, 128)
self.layer_2 = torch.nn.Linear(128, 444)
self.layer_3 = torch.nn.Linear(444, 333)
self.layer_4 = torch.nn.Linear(333, 10)
def forward(self, x):
x = x.view(x.size(0), -1)
x = self.layer_1(x)
x = F.relu(x)
x = self.layer_2(x)
x = F.relu(x)
x = self.layer_3(x)
x = F.relu(x)
x = self.layer_4(x)
return x
# Download data
if global_rank == 0:
mnist_train = MNIST(os.getcwd(), train=True, download=True)
mnist_test = MNIST(os.getcwd(), train=False, download=True)
# dist.barrier()
#transforms
transform=transforms.Compose([transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))])
mnist_train = MNIST(os.getcwd(), train=True, transform=transform)
# Split dataset
mnist_train, mnist_val = random_split(mnist_train, [55000, 5000])
mnist_test = MNIST(os.getcwd(), train=False, download=True)
# Build dataloaders
mnist_train = DataLoader(mnist_train, batch_size=256)
mnist_val = DataLoader(mnist_val, batch_size=256)
mnist_test = DataLoader(mnist_test, batch_size=256)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = MLPClassifier()
model = nn.DataParallel(model)
model.to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=1e-3)
# Train loop
model.train()
num_epochs = 1
for epoch in range(num_epochs):
for train_batch in mnist_train:
x, y = train_batch
logits = model(x.to(device))
loss = F.cross_entropy(logits, y.to(device))
print('rain loss: ', loss.item())
loss.backward()
optimizer.step()
optimizer.zero_grad()
# EVAL LOOP
model.eval()
with torch.no_grad():
val_loss_a = []
for val_batch in mnist_val:
x, y = val_batch
logits = model(x.to(device))
val_loss = F.cross_entropy(logits, y.to(device))
val_loss_a.append(val_loss)
avg_val_loss = torch.stack(val_loss_a).mean()
model.train()
I have made a chatbot using pytorch and would like to display accuracy on every epoch. I am not quite understanding how to do that. I can display loss but cant figure out how to display my accuracy
Here is my code :-
from nltk_utils import tokenize, stem, bag_of_words
import json
import numpy as np
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
from model import NeuralNet
from torch.autograd import Variable
all_words=[]
tags=[]
xy=[]
questionsP1=[]
questionsP2=[]
questionsP3=[]
questionsP4=[]
questionTag={}
with open('new.json', encoding="utf8") as file:
data = json.load(file)
for intent in data["intents"]:
for proficiency in intent["proficiency"]:
for questions in proficiency["questions"]:
for responses in questions["responses"]:
wrds = tokenize(responses)
all_words.extend(wrds)
xy.append((wrds, questions["tag"]))
if questions["tag"] in tags:
print(questions["tag"])
if questions["tag"] not in tags:
tags.append(questions["tag"])
if proficiency["level"] == "P1":
questionsP1.append(questions["question"])
questionTag[questions["question"]]=questions["tag"]
if proficiency["level"] == "P2":
questionsP2.append(questions["question"])
questionTag[questions["question"]]=questions["tag"]
if proficiency["level"] == "P3":
questionsP3.append(questions["question"])
questionTag[questions["question"]]=questions["tag"]
if proficiency["level"] == "P4":
questionsP4.append(questions["question"])
questionTag[questions["question"]]=questions["tag"]
ignore_words = ['?', '!', '.', ',']
all_words = [stem(x) for x in all_words if x not in ignore_words]
all_words = sorted(set(all_words))
tags = sorted(set(tags))
X_train = []
y_train = []
for tokenized_response, tag in xy:
bag = bag_of_words(tokenized_response, all_words)
print(bag)
X_train.append( bag )
label = tags.index( tag )
y_train.append( label )
print(y_train)
X_train = np.array( X_train )
y_train = np.array( y_train )
class ChatDataset(Dataset):
def __init__(self):
self.n_samples = len(X_train)
self.x_data = X_train
self.y_data = y_train
def __getitem__(self, index):
return self.x_data[index], self.y_data[index]
def __len__(self):
return self.n_samples
#HyperParameters
batch_size = 8
hidden_size = 8
output_size = len(tags)
input_size = len(X_train[0])
learning_rate = 0.001
num_epochs = 994
dataset = ChatDataset()
train_loader = DataLoader(dataset = dataset, batch_size=batch_size, shuffle = True, num_workers = 2)
device = 'cpu'
model = NeuralNet(input_size, hidden_size, output_size).to(device)
#loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr = learning_rate)
for epoch in range( num_epochs ):
for (words, labels) in train_loader:
words = words.to(device)
labels = labels.to(device)
#Forward
outputs = model(words)
loss = criterion(outputs, labels)
#backward and optimizer step
optimizer.zero_grad()
loss.backward()
optimizer.step()
print(f'epoch {epoch + 1}/ {num_epochs}, loss={loss.item(): .4f}')
print(f'final loss, loss={loss.item(): .4f}')
data = {
"model_state": model.state_dict(),
"input_size": input_size,
"output_size": output_size,
"hidden_size": hidden_size,
"all_words": all_words,
"tags": tags,
}
FILE = "data.pth"
torch.save(data, FILE)
with open('new.json', 'r') as f:
intents = json.load(f)
bot_name = "Sam"
while True:
sentence = input("You: ")
if sentence == 'quit':
break
sentence = tokenize(sentence)
X = bag_of_words(sentence, all_words)
X = X.reshape( 1, X.shape[0])
X = torch.from_numpy( X )
output = model( X )
_, predicted = torch.max(output, dim=1)
tag = tags[predicted.item()]
print(tag)
probs = torch.softmax(output, dim=1)
probs = probs[0][predicted.item()]
print( probs.item() )
if probs.item() > 0.75:
for intent in intents["intents"]:
for proficiency in intent["proficiency"]:
for questions in proficiency["questions"]:
if questions["tag"] == tag:
print(f'{bot_name}: {questions["question"]}')
else:
print(f'{bot_name}: Probability Too Low')
print(f'Training Complete. File saved to {FILE}')
My chatbot is working inverselt... i am trying to map the answer to the right question.
Any help would be appreciated.
According to your code labels contains the indices that should have the highest values in outputs in order for the samples to be counted as correct predictions.
So to calculate the validation accuracy:
correct = 0
total = 0
model.eval()
with torch.no_grad():
for (words, labels) in validation_loader:
words = words.to(device)
labels = labels.to(device)
total += labels.shape[0]
outputs = model(words)
correct += torch.sum(labels == outputs.argmax(dim=-1))
accuracy = correct / total
%reset -f
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
import numpy as np
import matplotlib.pyplot as plt
import torch.utils.data as data_utils
import torch.nn as nn
import torch.nn.functional as F
num_epochs = 20
x1 = np.array([0,0])
x2 = np.array([0,1])
x3 = np.array([1,0])
x4 = np.array([1,1])
num_epochs = 200
x = torch.tensor([x1,x2,x3,x4]).float()
y = torch.tensor([0,1,1,0]).long()
train = data_utils.TensorDataset(x,y)
train_loader = data_utils.DataLoader(train , batch_size=2 , shuffle=True)
device = 'cpu'
input_size = 2
hidden_size = 100
num_classes = 2
learning_rate = .0001
torch.manual_seed(24)
def weights_init(m):
m.weight.data.normal_(0.0, 1)
class NeuralNet(nn.Module) :
def __init__(self, input_size, hidden_size, num_classes) :
super(NeuralNet, self).__init__()
self.fc1 = nn.Linear(input_size , hidden_size)
self.relu = nn.ReLU()
self.fc2 = nn.Linear(hidden_size , num_classes)
def forward(self, x) :
out = self.fc1(x)
out = self.relu(out)
out = self.fc2(out)
return out
model = NeuralNet(input_size, hidden_size, num_classes).to(device)
model.apply(weights_init)
criterionCE = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
for i in range(0 , 1) :
total_step = len(train_loader)
for epoch in range(num_epochs) :
for i,(images , labels) in enumerate(train_loader) :
images = images.to(device)
labels = labels.to(device)
outputs = model(images)
loss = criterionCE(outputs , labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
outputs = model(x)
print(outputs.data.max(1)[1])
I'm using to initialize the weights :
def weights_init(m):
m.weight.data.normal_(0.0, 1)
But following error is thrown :
~/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/modules/module.py in __getattr__(self, name)
533 return modules[name]
534 raise AttributeError("'{}' object has no attribute '{}'".format(
--> 535 type(self).__name__, name))
536
537 def __setattr__(self, name, value):
AttributeError: 'ReLU' object has no attribute 'weight'
Is this the correct method to initialize the weights ?
Also, should object be of type nn.Module , not Relu ?
In addition to what Fabio mentioned about checking the layer type and ReLU being an activation and not a trainable layer, as it is about initialization, you can do the weight initialization in the __init__ method itself like its done here:
https://github.com/pytorch/vision/blob/master/torchvision/models/vgg.py
def __init__(self, features, num_classes=1000,...):
----snip---
self._initialize_weights()
def _initialize_weights(self):
if isinstance(m, nn.Linear):
m.weight.data.normal_(0.0, 1)
You are trying to set the weights of a weight-free layer (ReLU).
Inside weights_init, you should check the type of layers before initializing weights. For instance:
def weights_init(m):
if type(m) == nn.Linear:
m.weight.data.normal_(0.0, 1)
See How to initialize weights in PyTorch?.
I'm using Keras with the TensorFlow backend. I've just figured out how to train and classify sequences of different lengths without masking, because I can't get masking to work. In the toy example I'm working with, I'm trying to train an LSTM to detect whether a sequence of arbitrary length starts with a 1 or not.
from keras.models import Sequential
from keras.layers import LSTM, Dense
import numpy as np
def gen_sig(num_samples, seq_len):
one_indices = np.random.choice(a=num_samples, size=num_samples // 2, replace=False)
x_val = np.zeros((num_samples, seq_len), dtype=np.bool)
x_val[one_indices, 0] = 1
y_val = np.zeros(num_samples, dtype=np.bool)
y_val[one_indices] = 1
return x_val, y_val
N_train = 100
N_test = 10
recall_len = 20
X_train, y_train = gen_sig(N_train, recall_len)
X_test, y_test = gen_sig(N_train, recall_len)
print('Build STATEFUL model...')
model = Sequential()
model.add(LSTM(10, batch_input_shape=(1, 1, 1), return_sequences=False, stateful=True))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print('Train...')
for epoch in range(15):
mean_tr_acc = []
mean_tr_loss = []
for seq_idx in range(X_train.shape[0]):
start_val = X_train[seq_idx, 0]
assert y_train[seq_idx] == start_val
assert tuple(np.nonzero(X_train[seq_idx, :]))[0].shape[0] == start_val
y_in = np.array([y_train[seq_idx]], dtype=np.bool)
for j in range(np.random.choice(a=np.arange(5, recall_len+1))):
x_in = np.array([[[X_train[seq_idx][j]]]])
tr_loss, tr_acc = model.train_on_batch(x_in, y_in)
mean_tr_acc.append(tr_acc)
mean_tr_loss.append(tr_loss)
model.reset_states()
print('accuracy training = {}'.format(np.mean(mean_tr_acc)))
print('loss training = {}'.format(np.mean(mean_tr_loss)))
print('___________________________________')
mean_te_acc = []
mean_te_loss = []
for seq_idx in range(X_test.shape[0]):
start_val = X_test[seq_idx, 0]
assert y_test[seq_idx] == start_val
assert tuple(np.nonzero(X_test[seq_idx, :]))[0].shape[0] == start_val
y_in = np.array([y_test[seq_idx]], dtype=np.bool)
for j in range(np.random.choice(a=np.arange(5, recall_len+1))):
te_loss, te_acc = model.test_on_batch(np.array([[[X_test[seq_idx][j]]]], dtype=np.bool), y_in)
mean_te_acc.append(te_acc)
mean_te_loss.append(te_loss)
model.reset_states()
print('accuracy testing = {}'.format(np.mean(mean_te_acc)))
print('loss testing = {}'.format(np.mean(mean_te_loss)))
print('___________________________________')
As seen in the code, my error is being batched over each time-step. This is bad for multiple reasons. How do I train the network in two steps? For example:
Run a bunch of values through the network to accumulate the error
Adjust the weights of the network given this accumulated error
To do what is described in the original question, the easiest way is to train the original network with masking, but then test with a stateful network so any length input can be classified:
import numpy as np
np.random.seed(1)
import tensorflow as tf
tf.set_random_seed(1)
from keras import models
from keras.layers import Dense, Masking, LSTM
import matplotlib.pyplot as plt
def stateful_model():
hidden_units = 256
model = models.Sequential()
model.add(LSTM(hidden_units, batch_input_shape=(1, 1, 1), return_sequences=False, stateful=True))
model.add(Dense(1, activation='relu', name='output'))
model.compile(loss='binary_crossentropy', optimizer='rmsprop')
return model
def train_rnn(x_train, y_train, max_len, mask):
epochs = 10
batch_size = 200
vec_dims = 1
hidden_units = 256
in_shape = (max_len, vec_dims)
model = models.Sequential()
model.add(Masking(mask, name="in_layer", input_shape=in_shape,))
model.add(LSTM(hidden_units, return_sequences=False))
model.add(Dense(1, activation='relu', name='output'))
model.compile(loss='binary_crossentropy', optimizer='rmsprop')
model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs,
validation_split=0.05)
return model
def gen_train_sig_cls_pair(t_stops, num_examples, mask):
x = []
y = []
max_t = int(np.max(t_stops))
for t_stop in t_stops:
one_indices = np.random.choice(a=num_examples, size=num_examples // 2, replace=False)
sig = np.zeros((num_examples, max_t), dtype=np.int8)
sig[one_indices, 0] = 1
sig[:, t_stop:] = mask
x.append(sig)
cls = np.zeros(num_examples, dtype=np.bool)
cls[one_indices] = 1
y.append(cls)
return np.concatenate(x, axis=0), np.concatenate(y, axis=0)
def gen_test_sig_cls_pair(t_stops, num_examples):
x = []
y = []
for t_stop in t_stops:
one_indices = np.random.choice(a=num_examples, size=num_examples // 2, replace=False)
sig = np.zeros((num_examples, t_stop), dtype=np.bool)
sig[one_indices, 0] = 1
x.extend(list(sig))
cls = np.zeros((num_examples, t_stop), dtype=np.bool)
cls[one_indices] = 1
y.extend(list(cls))
return x, y
if __name__ == '__main__':
noise_mag = 0.01
mask_val = -10
signal_lengths = (10, 15, 20)
x_in, y_in = gen_train_sig_cls_pair(signal_lengths, 10, mask_val)
mod = train_rnn(x_in[:, :, None], y_in, int(np.max(signal_lengths)), mask_val)
testing_dat, expected = gen_test_sig_cls_pair(signal_lengths, 3)
state_mod = stateful_model()
state_mod.set_weights(mod.get_weights())
res = []
for s_i in range(len(testing_dat)):
seq_in = list(testing_dat[s_i])
seq_len = len(seq_in)
for t_i in range(seq_len):
res.extend(state_mod.predict(np.array([[[seq_in[t_i]]]])))
state_mod.reset_states()
fig, axes = plt.subplots(2)
axes[0].plot(np.concatenate(testing_dat), label="input")
axes[1].plot(res, "ro", label="result", alpha=0.2)
axes[1].plot(np.concatenate(expected, axis=0), "bo", label="expected", alpha=0.2)
axes[1].legend(bbox_to_anchor=(1.1, 1))
plt.show()