def main():
data_TRAINING = PetsDataset("/home/helmuth/dlvc/cifar-10-batches-py", Subset.TRAINING)
data_VALIDATION = PetsDataset("/home/helmuth/dlvc/cifar-10-batches-py", Subset.VALIDATION)
data_TEST = PetsDataset("/home/helmuth/dlvc/cifar-10-batches-py", Subset.TEST)
# check length of datasets
assert(len(data_TRAINING) == 7959)
assert(len(data_VALIDATION) == 2041)
assert(len(data_TEST) == 2000)
# count cats and dogs
cat_count = 0
dog_count = 0
for s in data_TRAINING:
if s.label == 0:
cat_count += 1
else:
dog_count += 1
for s in data_TEST:
if s.label == 0:
cat_count += 1
else:
dog_count += 1
for s in data_VALIDATION:
if s.label == 0:
cat_count += 1
else:
dog_count += 1
assert(cat_count == 6000)
assert(dog_count == 6000)
assert(data_TRAINING[0].data.shape == (32,32,3))
assert(data_TRAINING[0].data.dtype == np.uint8)
labels = [data_TRAINING[i].label for i in range(10)]
assert(labels == [0, 0, 0, 0, 1, 0, 0, 0, 0, 1])
for i in range(10):
cv2.imwrite('sample' + str(i) + '.png', data_TRAINING[i].data)
def test_correctness_of_data(self):
training_set = PetsDataset(os.path.join(os.getcwd(), self._data_dir),
Subset.TRAINING)
validation_set = PetsDataset(os.path.join(os.getcwd(), self._data_dir),
Subset.VALIDATION)
test_set = PetsDataset(os.path.join(os.getcwd(), self._data_dir),
Subset.TEST)
# Test number of samples in the individual data sets:
self.assertEqual(len(training_set), 7959)
self.assertEqual(len(validation_set), 2041)
self.assertEqual(len(test_set), 2000)
# #Test image shape and type
self.assertEqual(test_set[3].data.shape, (32, 32, 3))
self.assertEqual(test_set[3].data.dtype, 'uint8')
#Test labels of first 10 training samples
test_samples = []
for i in range(0, 10):
test_samples.append(training_set[i].label)
self.assertEqual(test_samples, [0, 0, 0, 0, 1, 0, 0, 0, 0, 1])
#Make sure that color channels are in BGR order by displaying images
#Open CV follows BGR order while Matlab follows RGB order
my_little_sweet_dog = training_set[2].data
channels = cv.split(my_little_sweet_dog)
my_little_sweet_blue_dog = channels[0]
my_little_sweet_red_dog = channels[2]
self.assertTrue(
np.sum(my_little_sweet_red_dog) > np.sum(my_little_sweet_blue_dog))
def load_dataset_into_batches(file_dir_path: str, subset: Subset, subset_size: int, shuffle: bool = False):
op = ops.chain([
ops.vectorize(),
ops.type_cast(np.float32)
])
dataset = PetsDataset(file_dir_path, subset)
return BatchGenerator(dataset, subset_size, shuffle, op)
def main():
data = PetsDataset("/home/helmuth/dlvc/cifar-10-batches-py", Subset.TRAINING)
# ops chain
op = ops.chain([
ops.vectorize(),
ops.type_cast(np.float32),
ops.add(-127.5),
ops.mul(1/127.5),
])
# batch generator #1
bg1 = BatchGenerator(data, len(data), False)
assert(len(bg1) == 1)
# batch generator #2
bg2 = BatchGenerator(data, 500, False, op)
assert(len(bg2) == 16)
# first batch
cnt = 0
for batch in bg2:
cnt += 1
if cnt < 16:
assert(batch.data.shape == (500, 3072))
assert(batch.labels.shape == (500,))
assert(batch.data.dtype == np.float32)
assert(np.issubdtype(batch.labels.dtype, np.integer))
if cnt == 1:
print("First batch, first sample, not shuffled")
print(batch.data[0])
# batch generator #3
bg3 = BatchGenerator(data, 500, True, op)
# run 5 times through first sample of shuffled batch generator
for i in range(5):
it = iter(bg3)
print("First batch, first sample, shuffled")
print(next(it).data[0])
def test_data_transformation(self):
op = ops.chain([ops.vectorize(), ops.type_cast(np.float32)])
dataset = PetsDataset(os.path.join(os.getcwd(), self._data_dir),
Subset.TRAINING)
batch_gen = BatchGenerator(dataset, 100, False, op)
self.assertEqual(len(batch_gen), 80)
iter_gen = iter(batch_gen)
iter_result = next(iter_gen)
self.assertEqual(iter_result.data[0].shape, (3072, ))
self.assertTrue(np.issubdtype(iter_result.data.dtype, np.float32))
def test_create_batch(self):
dataset = PetsDataset(os.path.join(os.getcwd(), self._data_dir),
Subset.TRAINING)
batch_set = BatchGenerator(dataset, 100, False)
self.assertEqual(len(batch_set), 80)
iter_gen = iter(batch_set)
iter_result = next(iter_gen)
self.assertEqual(iter_result.idx[0], 9)
iter_result = next(iter_gen)
self.assertEqual(iter_result.idx[0], 607)
def test_shuffle(self):
dataset = PetsDataset(os.path.join(os.getcwd(), self._data_dir),
Subset.TRAINING)
batch_set = BatchGenerator(dataset, 100, True)
self.assertEqual(len(batch_set), 80)
iter_gen = iter(batch_set)
iter_result = next(iter_gen)
self.assertFalse(iter_result.idx[0] == 9)
iter_result = next(iter_gen)
self.assertFalse(iter_result.idx[0] == 607)
def test_train_with_proper_data(self):
op = ops.chain([
ops.vectorize(),
ops.type_cast(np.float32)
])
dataset = PetsDataset(os.path.join(os.getcwd(), self._data_dir), Subset.TRAINING)
batch_gen = BatchGenerator(dataset, 7959, False, op)
batch_iter = iter(batch_gen)
iter_result = next(batch_iter)
classifier = KnnClassifier(10, 3072, 2)
classifier.train(iter_result.data, iter_result.label)
def load_dataset(subset: Subset) -> batches.BatchGenerator:
dataset = PetsDataset('../data/cifar-10-batches-py', subset)
op = ops.chain([
ops.hwc2chw(),
ops.add(-127.5),
ops.mul(1 / 127.5),
ops.type_cast(np.float32)
])
return batches.BatchGenerator(dataset, 128, True, op)
def test_train_with_wrong_type_of_labels(self):
op = ops.chain([
ops.vectorize(),
ops.type_cast(np.float32)
])
dataset = PetsDataset(os.path.join(os.getcwd(), self._data_dir), Subset.TRAINING)
batch_gen = BatchGenerator(dataset, 7959, False, op)
batch_iter = iter(batch_gen)
iter_result = next(batch_iter)
classifier = KnnClassifier(10, 3072, 2)
self.assertRaises(TypeError, classifier.train, iter_result.data, [0, 1, 0])
def test_train_wrong_vector_size_in_data(self):
op = ops.chain([
ops.vectorize(),
ops.type_cast(np.float32)
])
dataset = PetsDataset(os.path.join(os.getcwd(), self._data_dir), Subset.TRAINING)
batch_gen = BatchGenerator(dataset, 7959, False, op)
batch_iter = iter(batch_gen)
iter_result = next(batch_iter)
classifier = KnnClassifier(10, 3072, 2)
changed_data = np.delete(iter_result.data, 100, 1)
self.assertRaises(RuntimeError, classifier.train, changed_data, iter_result.label)
def test_correctness_of_data_for_train(self):
op = ops.chain([
ops.vectorize(),
ops.type_cast(np.float32)
])
dataset = PetsDataset(os.path.join(os.getcwd(), self._data_dir), Subset.TRAINING)
one_batch_gen = BatchGenerator(dataset, 7959, False, op)
self.assertEqual(len(one_batch_gen), 1)
many_batch_gen = BatchGenerator(dataset, 500, False, op)
self.assertEqual(len(many_batch_gen), 16)
reference = [116., 125., 125., 91., 101.]
batch_iter = iter(many_batch_gen)
batch_iter = next(batch_iter)
[self.assertEqual(item, reference[i]) for i, item in enumerate(batch_iter.data[0][:5])]
def test_predict_with_proper_data(self):
op = ops.chain([
ops.vectorize(),
ops.type_cast(np.float32)
])
dataset_training = PetsDataset(os.path.join(os.getcwd(), self._data_dir), Subset.TRAINING)
dataset_valid = PetsDataset(os.path.join(os.getcwd(), self._data_dir), Subset.VALIDATION)
batch_gen_t = BatchGenerator(dataset_training, 795, False, op)
batch_gen_v = BatchGenerator(dataset_valid, 204, False, op)
batch_iter_t = iter(batch_gen_t)
iter_result_t = next(batch_iter_t)
batch_iter_v = iter(batch_gen_v)
iter_result_v = next(batch_iter_v)
classifier = KnnClassifier(10, 3072, 2)
classifier.train(iter_result_t.data, iter_result_t.label)
results = classifier.predict(iter_result_v.data)
self.assertEqual(len(results), 204)
for result in results:
self.assertEqual(np.sum(result), 1.0)
def load_dataset(subset: Subset, augment=False) -> batches.BatchGenerator:
dataset = PetsDataset('../data/cifar-10-batches-py', subset)
ops_list = []
if augment:
ops_list += [ops.hflip(), ops.rcrop(32, 12, 'constant')]
ops_list += [
ops.mul(1 / 255),
ops.type_cast(np.float32),
# Imagenet:
# ops.normalize( mean=np.array([0.485, 0.456, 0.406]),
# std=np.array([0.229, 0.224, 0.225])),
# Cifar-10:
ops.normalize(mean=np.array([0.41477802, 0.45935813, 0.49693552]),
std=np.array([0.25241926, 0.24699265, 0.25279155])),
ops.hwc2chw()
]
op = ops.chain(ops_list)
return batches.BatchGenerator(dataset, 128, True, op)
from dlvc.test import Accuracy
from dlvc.datasets.pets import PetsDataset
from dlvc.dataset import Subset
import dlvc.ops as ops
np.random.seed(0)
torch.manual_seed(0)
DATA_PATH = "../cifar-10-batches-py/"
RESULTS_FILE = "results.txt"
NR_EPOCHS = 100
EARLY_STOPPING = 10
CUDA = torch.cuda.is_available()
train_data = PetsDataset(DATA_PATH, Subset.TRAINING)
val_data = PetsDataset(DATA_PATH, Subset.VALIDATION)
op_all_augmentation = ops.chain([
ops.type_cast(np.float32),
ops.add(-127.5),
ops.mul(1 / 127.5),
ops.hflip(),
ops.rcrop(32, 4, 'constant'),
ops.add_noise(),
ops.hwc2chw()
])
op_augmentation_crop_flip = ops.chain([
ops.type_cast(np.float32),
ops.add(-127.5),
def load_dataset(subset: Subset) -> batches.BatchGenerator:
dataset = PetsDataset('../data/cifar-10-batches-py', subset)
op = ops.chain([ops.vectorize(), ops.type_cast(np.float32)])
return batches.BatchGenerator(dataset, len(dataset), True, op)
from dlvc.batches import BatchGenerator
from dlvc.ops import vectorize, chain, type_cast
import cv2
'''
All small and quick tests go here.
'''
dir = '/Users/mmatak/dev/college/DLVC/cifar-10/cifar-10-batches-py/'
##########################################
# PART 1 #
##########################################
# Number of samples in the individual datasets: 7959 (training), 2041 (validation), 2000 (test)
dataset_test = PetsDataset(dir, Subset.TEST)
assert (len(dataset_test) == TEST_SIZE
), "Number of elements in test_dataset is different than " % TEST_SIZE
dataset_training = PetsDataset(dir, Subset.TRAINING)
assert(len(dataset_training) == TRAINING_SIZE),\
"Number of elements in training_dataset is different than " % TRAINING_SIZE
dataset_validation = PetsDataset(dir, Subset.VALIDATION)
assert(len(dataset_validation) == VALIDATION_SIZE), \
"Number of elements in validation_dataset is different than " % VALIDATION_SIZE
# Total number of cat and dog samples: 6000 per class
def count_labels(dataset):
def test_batch_size_is_not_integer_exception(self):
dataset = PetsDataset(os.path.join(os.getcwd(), self._data_dir),
Subset.TEST)
self.assertRaises(TypeError, BatchGenerator, dataset, 50.5, False)
from dlvc.dataset import Subset
TrainedModel = namedtuple('TrainedModel', ['model', 'accuracy'])
# initialize RNG for reproducability
random.seed(42)
np.random.seed(42)
torch.manual_seed(42)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
# Batch size to be used
BATCH_SIZE = 128
# Step 1: load the data sets (TRAIN, VALIDATION)
train_data = PetsDataset("../cifar-10-batches-py", Subset.TRAINING)
val_data = PetsDataset("../cifar-10-batches-py", Subset.VALIDATION)
# Operations to standardize
# scale to sample mean=0, sd=1
# calculate average training sample mean & sd
op_calc = ops.chain([
ops.type_cast(np.float32),
ops.mean_sd()
])
# using batch generator (could do it directly but I'm lazy)
train_full_batch_gen = BatchGenerator(
train_data,
len(train_data),
False,
op_calc)
import torch
import torch.nn as nn
from dlvc.models.pytorch import CnnClassifier
from dlvc.batches import BatchGenerator
from dlvc.test import Accuracy
from dlvc.datasets.pets import PetsDataset
from dlvc.dataset import Subset
import dlvc.ops as ops
np.random.seed(0)
torch.manual_seed(0)
DATA_PATH = "../cifar-10-batches-py/"
MODEL_PATH = "best_model.pt"
train_data = PetsDataset(DATA_PATH, Subset.TRAINING)
val_data = PetsDataset(DATA_PATH, Subset.VALIDATION)
op = ops.chain([
ops.type_cast(np.float32),
ops.add(-127.5),
ops.mul(1 / 127.5),
ops.hflip(),
ops.rcrop(32, 4, 'constant'),
ops.add_noise(),
ops.hwc2chw()
])
train_batches = BatchGenerator(train_data, 128, False, op)
val_batches = BatchGenerator(val_data, 128, False, op)
def test_negative_batch_size_exception(self):
dataset = PetsDataset(os.path.join(os.getcwd(), self._data_dir),
Subset.TEST)
self.assertRaises(ValueError, BatchGenerator, dataset, -1, False)
import numpy as np
import torch
import random
from dlvc.datasets.pets import PetsDataset
from dlvc.batches import BatchGenerator
from dlvc.dataset import Subset
TrainedModel = namedtuple('TrainedModel', ['model', 'accuracy'])
# initialize RNG for reproducability
random.seed(42)
np.random.seed(42)
torch.manual_seed(42)
# Step 1: load the data sets (TRAIN, VALIDATION & TEST)
train_data = PetsDataset("../cifar-10-batches-py", Subset.TRAINING)
val_data = PetsDataset("../cifar-10-batches-py", Subset.VALIDATION)
test_data = PetsDataset("../cifar-10-batches-py", Subset.TEST)
# Operations to standardize
op = ops.chain([
ops.vectorize(),
ops.type_cast(np.float32),
ops.add(-127.5),
ops.mul(1/127.5),
])
# Step 2: Create batch generator for each
BATCH_SIZE = 512
train_batches = BatchGenerator(train_data, BATCH_SIZE, True, op)
val_batches = BatchGenerator(val_data, BATCH_SIZE, True, op)
test_batches = BatchGenerator(test_data, BATCH_SIZE, True, op)
import numpy as np
from dlvc.dataset import Subset
from dlvc.datasets.pets import PetsDataset
from dlvc import ops, batches
dataset = PetsDataset('../data/cifar-10-batches-py', Subset.TRAINING)
op = ops.chain([ops.mul(1 / 255), ops.type_cast(np.float32)])
batch_generator = batches.BatchGenerator(dataset, 7959, True, op)
training_images = []
for batch in batch_generator:
training_images.append(batch.data)
training_images = np.array(training_images, dtype=np.float32)
training_images = training_images.reshape(training_images.shape[1:])
train_mean = np.mean(training_images, axis=(0, 1, 2))
train_std = np.std(training_images, axis=(0, 1, 2))
print(train_mean, train_std)
from dlvc.test import Accuracy
import numpy as np
from dlvc.ops import *
from dlvc.datasets.pets import PetsDataset
from dlvc.batches import BatchGenerator
from dlvc.dataset import Subset
import matplotlib.pyplot as plt
from mpl_toolkits import mplot3d
TrainedModel = namedtuple('TrainedModel', ['model', 'accuracy'])
# TODO implement steps 1-2
data_path = "" #something ending with "...\\cifar-10-batches.py"
trainingDataset = PetsDataset(data_path, Subset.TRAINING)
validationDataset = PetsDataset(data_path, Subset.VALIDATION)
testDataset = PetsDataset(data_path, Subset.TEST)
op = chain([
vectorize(),
type_cast(np.float32),
add(-127.5),
mul(1 / 127.5),
])
bg_training = BatchGenerator(dataset=trainingDataset,
num=32,
shuffle=True,
op=op)
bg_validation = BatchGenerator(dataset=validationDataset,
from dlvc.batches import BatchGenerator
from dlvc.ops import vectorize, chain, type_cast
import time
'''
Tests in this file should test the whole pipeline. They take more time than unit tests.
'''
# make sure the whole pipeline works:
# when k=1 and
# training and predict subset are equal and
# kNN must have accuracy 100%
start = time.time()
pets = PetsDataset(
'/Users/mmatak/dev/college/DLVC/cifar-10/cifar-10-batches-py/',
Subset.TEST)
num_classes = 2
k = 1
knn = KnnClassifier(k, 32 * 32 * 3, num_classes)
batchGenerator = BatchGenerator(pets,
512,
False,
op=chain(
[type_cast(dtype=np.float32),
vectorize()]))
groundTruthLabels = None
for batch in batchGenerator:
knn.train(batch.data, batch.label)
groundTruthLabels = batch.label
def test_bigger_batch_then_dataset_exception(self):
dataset = PetsDataset(os.path.join(os.getcwd(), self._data_dir),
Subset.TEST)
self.assertRaises(ValueError, BatchGenerator, dataset, 5000, False)
import numpy as np
import cv2
from dlvc.datasets.pets import PetsDataset
from dlvc.models.linear import LinearClassifier
from dlvc.batches import BatchGenerator
from dlvc.test import Accuracy
from dlvc.dataset import Subset
import dlvc.ops as ops
np.random.seed(0)
pets_train = PetsDataset("../cifar-10-batches-py/", Subset.TRAINING)
pets_val = PetsDataset("../cifar-10-batches-py/", Subset.VALIDATION)
random_accuracy = Accuracy()
validation_accuracy = Accuracy()
train_accuracy = Accuracy()
print('Number of Classes = {}'.format(pets_train.num_classes()))
print('Number of Images = {}'.format(pets_train.__len__()))
print('First 10 Classes >>> {}'.format(pets_train.labels[:10]))
op = ops.chain([
ops.vectorize(),
ops.type_cast(np.float32),
ops.add(-127.5),
ops.mul(1 / 127.5),
])
NUM_CHANNELS = 3
BATCH_SIZE = 128
NUM_CLASSES = 2
EPOCHS = 1000
lr = 0.001
wd = 0.00000001
EARLY_STOPPING = True
EARLY_STOPPING_NUM_OF_EPOCHS = 100
USE_DROPOUT = True
USE_TRANSFER_LEARNING = True
FREEZE_CNN_PARAMETERS = True
pets_training = PetsDataset(dir, Subset.TRAINING)
pets_validation = PetsDataset(dir, Subset.VALIDATION)
class CatDogNet(nn.Module):
def __init__(self):
super(CatDogNet, self).__init__()
# First Layer 2xConv and Max pool out_Shape = (16x16x32)
self.conv1_layer1 = nn.Conv2d(in_channels=3,
out_channels=32,
kernel_size=3,
stride=1,
padding=1)
self.batch_norm1_layer1 = nn.BatchNorm2d(num_features=32)
self.relu1_layer1 = nn.ReLU()
import cv2
import torch
import torch.nn as nn
from dlvc.datasets.pets import PetsDataset
from dlvc.models.pytorch import CnnClassifier
from dlvc.batches import BatchGenerator
from dlvc.test import Accuracy
from dlvc.dataset import Subset
import dlvc.ops as ops
np.random.seed(0)
pets_train = PetsDataset("../cifar-10-batches-py/", Subset.TRAINING)
op = ops.chain([
ops.type_cast(np.float32),
ops.add(-127.5),
ops.mul(1 / 127.5),
ops.hflip(),
ops.rcrop(32, 4, 'constant'),
ops.add_noise(),
ops.hwc2chw()
])
reverse_op = ops.chain([
ops.chw2hwc(),
ops.mul(127.5),
ops.add(127.5),
