r'C:\Users\pravi\PycharmProjects\Sentence_similarity\data\sts\sick2014\SICK_train.txt'
)
train_data_1 = res_train['data_1']
train_data_2 = res_train['data_2']
train_length1 = res_train['length1']
train_length2 = res_train['length2']
labels = res_train['label']
word2Id = res_train['word2Id']
Id2Word = res_train['Id2Word']
max_sequence_length = res_train['max_sequence_length']
vocab_size = res_train['vocab_size']
total_classes = res_train['total_classes']
res_test = load_test_data(
r'C:\Users\pravi\PycharmProjects\Sentence_similarity\data\sts\sick2014\SICK_test_annotated.txt',
max_sequence_length, word2Id, Id2Word)
word2Id = res_test['word2Id']
test_data_1 = res_test['data_1']
test_data_2 = res_test['data_2']
test_labels = res_test['label']
test_length1 = res_test['length1']
test_length2 = res_test['length2']
Id2Word = res_test['Id2Word']
Id2Vec = np.zeros([len(Id2Word.keys()), embedding_size])
words_list = word_vecs.word2vec.keys()
for i in range(len(Id2Word.keys())):
word = Id2Word[i]
if word in words_list:
Id2Vec[i, :] = word_vecs.word2vec[word]
alphabet = preprocess.labels()
# Training data
X_train, X_te, y_train, y_te, train_ws = preprocess.load_data()
X_train = np.vstack((X_train, X_te))
y_train = np.hstack((y_train, y_te))
train_data = MyDataset(X_train, y_train,
preprocess.make_transform(mode="eval"))
train_loader = DataLoader(train_data,
batch_size=512,
shuffle=False,
num_workers=8,
pin_memory=True)
# Testing data
X_test, y_test, test_ws = preprocess.load_test_data()
test_data = MyDataset(X_test, y_test, preprocess.make_transform(mode="eval"))
test_loader = DataLoader(test_data,
batch_size=512,
shuffle=False,
num_workers=8,
pin_memory=True)
base_dir = os.getcwd()
model_dir = os.path.join(base_dir, "Code", "model")
model_path = os.path.join(model_dir, "sign_model.pth")
with open(os.path.join(model_dir, "model_specification"), "r") as ms:
model_name = ms.readline()
# Load the trained model
path=r'C:\Users\pravi\PycharmProjects\NLI\data_pickles\data')
print("done")
train_data_1 = res['data_1']
train_data_2 = res['data_2']
train_label = res['labels']
train_data_len_1 = res['data_length_1']
train_data_len_2 = res['data_length_2']
word2Id = res['word2Id']
words_data_list = word2Id.keys()
Id2Word = res['Id2Word']
max_sequence_length = res['max_sequence_length']
total_classes = res['total_classes']
test_res = load_test_data(dev_path, word2Id, Id2Word, max_sequence_length)
test_data_1 = test_res['data_1']
test_data_2 = test_res['data_2']
test_label = test_res['labels']
test_data_len_1 = test_res['data_length_1']
test_data_len_2 = test_res['data_length_2']
word2Id = test_res['word2Id']
Id2Vec = np.zeros([len(Id2Word.keys()), embedding_size])
words_list = word_vecs.word2vec.keys()
for i in range(len(Id2Word.keys())):
word = Id2Word[i]
if word in words_list:
Id2Vec[i, :] = word_vecs.word2vec[word]
else:
Id2Vec[i, :] = word_vecs.word2vec['unknown']
with open(PICKLE_FILENAME, 'wb') as f:
pickle.dump(model, f)
print('Done.')
training_data = np.genfromtxt(LOG_CSV_FILENAME, delimiter=',')
plt.plot(training_data[1:, 0], training_data[1:, 1], label='Train loss')
plt.plot(training_data[1:, 0], training_data[1:, 2], label='Test loss')
plt.legend()
plt.xlabel('Epoch')
plt.show()
# TEST MODE
else:
with open(PICKLE_FILENAME, 'rb') as f:
model = pickle.load(f)
if not TEST_ON_REAL_IMAGES:
test_images = load_test_data(TEST_FILENAME)
for i in range(NUM_EXAMPLES_TO_SHOW):
image = test_images[i][0]
img_tensor = torch.FloatTensor(image)
img_tensor = img_tensor.view(1, 1, 96, 96)
output = model(img_tensor)
output = output.data[0].numpy()
output = (output * 48.0) + 48.0
plot_image_and_predictions(image, output)
else:
img = Image.open(TEST_IMAGES[0]).convert('L')
img = img.resize([96, 96], Image.ANTIALIAS)
img_data = np.asarray(img.getdata()).reshape(img.size)
img_data = img_data / float(PIXEL_MAX_VAL) # normalize to 0..1
img_tensor = torch.FloatTensor(img_data)
img_tensor = img_tensor.view(1, 1, 96, 96)