SYMBOL INDEX (1180 symbols across 200 files)

FILE: ML/Kaggles/DiabeticRetinopathy/dataset.py
  class DRDataset (line 10) | class DRDataset(Dataset):
    method __init__ (line 11) | def __init__(self, images_folder, path_to_csv, train=True, transform=N...
    method __len__ (line 19) | def __len__(self):
    method __getitem__ (line 22) | def __getitem__(self, index):

FILE: ML/Kaggles/DiabeticRetinopathy/preprocess_images.py
  function trim (line 16) | def trim(im):
  function resize_maintain_aspect (line 38) | def resize_maintain_aspect(image, desired_size):
  function save_single (line 52) | def save_single(args):
  function fast_image_resize (line 60) | def fast_image_resize(input_path_folder, output_path_folder, output_size...

FILE: ML/Kaggles/DiabeticRetinopathy/train.py
  function train_one_epoch (line 20) | def train_one_epoch(loader, model, optimizer, loss_fn, scaler, device):
  function main (line 48) | def main():

FILE: ML/Kaggles/DiabeticRetinopathy/train_blend.py
  function make_prediction (line 14) | def make_prediction(model, loader, file):
  class MyDataset (line 42) | class MyDataset(Dataset):
    method __init__ (line 43) | def __init__(self, csv_file):
    method __len__ (line 46) | def __len__(self):
    method __getitem__ (line 49) | def __getitem__(self, index):
  class MyModel (line 57) | class MyModel(nn.Module):
    method __init__ (line 58) | def __init__(self):
    method forward (line 73) | def forward(self, x):

FILE: ML/Kaggles/DiabeticRetinopathy/utils.py
  function make_prediction (line 10) | def make_prediction(model, loader, output_csv="submission.csv"):
  function check_accuracy (line 35) | def check_accuracy(loader, model, device="cuda"):
  function save_checkpoint (line 73) | def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 78) | def load_checkpoint(checkpoint, model, optimizer, lr):
  function get_csv_for_blend (line 89) | def get_csv_for_blend(loader, model, output_csv_file):

FILE: ML/Kaggles/Dog vs Cat Competition/dataset.py
  class CatDog (line 8) | class CatDog(Dataset):
    method __init__ (line 9) | def __init__(self, root, transform=None):
    method __len__ (line 15) | def __len__(self):
    method __getitem__ (line 18) | def __getitem__(self, index):

FILE: ML/Kaggles/Dog vs Cat Competition/train.py
  function save_feature_vectors (line 15) | def save_feature_vectors(model, loader, output_size=(1, 1), file="trainb...
  function train_one_epoch (line 33) | def train_one_epoch(loader, model, loss_fn, optimizer, scaler):
  function main (line 51) | def main():

FILE: ML/Kaggles/Dog vs Cat Competition/utils.py
  function check_accuracy (line 14) | def check_accuracy(
  function save_checkpoint (line 54) | def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 59) | def load_checkpoint(checkpoint, model):
  function create_submission (line 64) | def create_submission(model, model_name, files_dir):
  function blending_ensemble_data (line 176) | def blending_ensemble_data():

FILE: ML/Kaggles/Facial Keypoint Detection Competition/dataset.py
  class FacialKeypointDataset (line 8) | class FacialKeypointDataset(Dataset):
    method __init__ (line 9) | def __init__(self, csv_file, train=True, transform=None):
    method __len__ (line 16) | def __len__(self):
    method __getitem__ (line 19) | def __getitem__(self, index):

FILE: ML/Kaggles/Facial Keypoint Detection Competition/extract_images_from_csv.py
  function extract_images_from_csv (line 7) | def extract_images_from_csv(csv, column, save_folder, resize=(96, 96)):

FILE: ML/Kaggles/Facial Keypoint Detection Competition/train.py
  function train_one_epoch (line 17) | def train_one_epoch(loader, model, optimizer, loss_fn, scaler, device):
  function main (line 40) | def main():

FILE: ML/Kaggles/Facial Keypoint Detection Competition/utils.py
  function get_submission (line 8) | def get_submission(loader, dataset, model_15, model_4):
  function get_rmse (line 40) | def get_rmse(loader, model, loss_fn, device):
  function save_checkpoint (line 58) | def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 63) | def load_checkpoint(checkpoint, model, optimizer, lr):

FILE: ML/Kaggles/SantanderTransaction/dataset.py
  function get_data (line 7) | def get_data():

FILE: ML/Kaggles/SantanderTransaction/train.py
  class NN (line 11) | class NN(nn.Module):
    method __init__ (line 12) | def __init__(self, input_size, hidden_dim):
    method forward (line 18) | def forward(self, x):

FILE: ML/Kaggles/SantanderTransaction/utils.py
  function get_predictions (line 5) | def get_predictions(loader, model, device):
  function get_submission (line 21) | def get_submission(model, loader, test_ids, device):

FILE: ML/Projects/DeepSort/sort_w_attention.py
  class SortArray (line 19) | class SortArray(Dataset):
    method __init__ (line 20) | def __init__(self, batch_size, min_int, max_int, min_size, max_size):
    method __len__ (line 28) | def __len__(self):
    method __getitem__ (line 31) | def __getitem__(self, index):
  class Encoder (line 47) | class Encoder(nn.Module):
    method __init__ (line 48) | def __init__(self, hidden_size, num_layers):
    method forward (line 55) | def forward(self, x):
  class Decoder (line 65) | class Decoder(nn.Module):
    method __init__ (line 66) | def __init__(self, hidden_size, num_layers, units=100):
    method forward (line 76) | def forward(self, x, encoder_states, hidden, cell):
  class Seq2Seq (line 98) | class Seq2Seq(nn.Module):
    method __init__ (line 99) | def __init__(self, encoder, decoder):
    method forward (line 104) | def forward(self, source, target, teacher_force_ratio=0.5):

FILE: ML/Projects/DeepSort/utils.py
  function ask_user (line 4) | def ask_user():
  function sort_array (line 10) | def sort_array(encoder, decoder, device, arr=None):
  function save_checkpoint (line 65) | def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 70) | def load_checkpoint(checkpoint, model, optimizer):  # , steps):

FILE: ML/Projects/Exploring_MNIST/networks/googLeNet.py
  class Inception (line 6) | class Inception(nn.Module):
    method __init__ (line 7) | def __init__(
    method forward (line 32) | def forward(self, x):
  class GoogLeNet (line 41) | class GoogLeNet(nn.Module):
    method __init__ (line 42) | def __init__(self, img_channel):
    method forward (line 66) | def forward(self, x):
  class BasicConv2d (line 90) | class BasicConv2d(nn.Module):
    method __init__ (line 91) | def __init__(self, in_channels, out_channels, **kwargs):
    method forward (line 96) | def forward(self, x):
  function test (line 102) | def test():

FILE: ML/Projects/Exploring_MNIST/networks/lenet.py
  class LeNet (line 6) | class LeNet(nn.Module):
    method __init__ (line 7) | def __init__(self, in_channels, init_weights=True, num_classes=10):
    method forward (line 21) | def forward(self, x):
    method _initialize_weights (line 36) | def _initialize_weights(self):
  function test_lenet (line 53) | def test_lenet():

FILE: ML/Projects/Exploring_MNIST/networks/resnet.py
  class residual_template (line 5) | class residual_template(nn.Module):
    method __init__ (line 8) | def __init__(self, in_channels, out_channels, stride=1, identity_downs...
    method forward (line 29) | def forward(self, x):
  class ResNet (line 52) | class ResNet(nn.Module):
    method __init__ (line 53) | def __init__(self, residual_template, layers, image_channel, num_class...
    method _make_layer (line 90) | def _make_layer(self, residual_template, num_residuals_blocks, channel...
    method forward (line 116) | def forward(self, x):
  function ResNet50 (line 133) | def ResNet50(img_channel):
  function ResNet101 (line 137) | def ResNet101(img_channel):
  function ResNet152 (line 141) | def ResNet152(img_channel):
  function test (line 145) | def test():

FILE: ML/Projects/Exploring_MNIST/networks/vgg.py
  class VGG (line 54) | class VGG(nn.Module):
    method __init__ (line 55) | def __init__(
    method forward (line 79) | def forward(self, x):
    method _initialize_weights (line 86) | def _initialize_weights(self):
    method create_architecture (line 102) | def create_architecture(self, architecture):
  function test (line 132) | def test():

FILE: ML/Projects/Exploring_MNIST/train.py
  class Train_MNIST (line 19) | class Train_MNIST(object):
    method __init__ (line 20) | def __init__(self):
    method prepare_args (line 41) | def prepare_args(self):
    method prepare_transformations (line 120) | def prepare_transformations(self):
    method prepare_data (line 139) | def prepare_data(self, shuffle=True):
    method train (line 162) | def train(self):
    method choose_network (line 219) | def choose_network(self):
    method main (line 236) | def main(self):

FILE: ML/Projects/Exploring_MNIST/utils/mnist_data.py
  class mnist_data (line 6) | class mnist_data(object):
    method __init__ (line 7) | def __init__(
    method download_data (line 27) | def download_data(self):
    method create_validationset (line 37) | def create_validationset(self, mnist_trainset):
    method main (line 66) | def main(self):

FILE: ML/Projects/Exploring_MNIST/utils/utils.py
  function save_checkpoint (line 9) | def save_checkpoint(filename, model, optimizer, train_acc, epoch):
  function check_accuracy (line 23) | def check_accuracy(loader, model):
  function load_model (line 44) | def load_model(args, model, optimizer):
  class visdom_plotting (line 66) | class visdom_plotting(object):
    method __init__ (line 67) | def __init__(self):
    method create_plot (line 97) | def create_plot(

FILE: ML/Projects/spam_classifier_naive_bayes/build_vocabulary.py
  function build_vocabulary (line 20) | def build_vocabulary(curr_email):

FILE: ML/Projects/spam_classifier_naive_bayes/naivebayes.py
  class NaiveBayes (line 20) | class NaiveBayes:
    method __init__ (line 21) | def __init__(self, X, y):
    method fit (line 26) | def fit(self, X):
    method predict (line 38) | def predict(self, X):
    method density_function (line 50) | def density_function(self, x, mean, sigma):

FILE: ML/Projects/text_generation_babynames/generating_names.py
  class RNN (line 32) | class RNN(nn.Module):
    method __init__ (line 33) | def __init__(self, input_size, hidden_size, num_layers, output_size):
    method forward (line 42) | def forward(self, x, hidden, cell):
    method init_hidden (line 48) | def init_hidden(self, batch_size):
  class Generator (line 54) | class Generator:
    method __init__ (line 55) | def __init__(self):
    method char_tensor (line 64) | def char_tensor(self, string):
    method get_random_batch (line 70) | def get_random_batch(self):
    method generate (line 83) | def generate(self, initial_str="A", predict_len=100, temperature=0.85):
    method train (line 108) | def train(self):

FILE: ML/Pytorch/Basics/Imbalanced_classes/main.py
  function get_loader (line 46) | def get_loader(root_dir, batch_size):
  function main (line 78) | def main():

FILE: ML/Pytorch/Basics/albumentations_tutorial/full_pytorch_example.py
  class ImageFolder (line 12) | class ImageFolder(Dataset):
    method __init__ (line 13) | def __init__(self, root_dir, transform=None):
    method __len__ (line 24) | def __len__(self):
    method __getitem__ (line 27) | def __getitem__(self, index):

FILE: ML/Pytorch/Basics/albumentations_tutorial/utils.py
  function visualize (line 9) | def visualize(image):
  function plot_examples (line 16) | def plot_examples(images, bboxes=None):
  function visualize_bbox (line 32) | def visualize_bbox(img, bbox, class_name, color=(255, 0, 0), thickness=5):

FILE: ML/Pytorch/Basics/custom_dataset/custom_dataset.py
  class CatsAndDogsDataset (line 27) | class CatsAndDogsDataset(Dataset):
    method __init__ (line 28) | def __init__(self, csv_file, root_dir, transform=None):
    method __len__ (line 33) | def __len__(self):
    method __getitem__ (line 36) | def __getitem__(self, index):
  function check_accuracy (line 111) | def check_accuracy(loader, model):

FILE: ML/Pytorch/Basics/custom_dataset_txt/loader_customtext.py
  class Vocabulary (line 34) | class Vocabulary:
    method __init__ (line 35) | def __init__(self, freq_threshold):
    method __len__ (line 40) | def __len__(self):
    method tokenizer_eng (line 44) | def tokenizer_eng(text):
    method build_vocabulary (line 47) | def build_vocabulary(self, sentence_list):
    method numericalize (line 64) | def numericalize(self, text):
  class FlickrDataset (line 73) | class FlickrDataset(Dataset):
    method __init__ (line 74) | def __init__(self, root_dir, captions_file, transform=None, freq_thres...
    method __len__ (line 87) | def __len__(self):
    method __getitem__ (line 90) | def __getitem__(self, index):
  class MyCollate (line 105) | class MyCollate:
    method __init__ (line 106) | def __init__(self, pad_idx):
    method __call__ (line 109) | def __call__(self, batch):
  function get_loader (line 118) | def get_loader(

FILE: ML/Pytorch/Basics/lightning_simple_CNN.py
  class CNNLightning (line 37) | class CNNLightning(pl.LightningModule):
    method __init__ (line 38) | def __init__(self, lr=3e-4, in_channels=1, num_classes=10):
    method training_step (line 61) | def training_step(self, batch, batch_idx):
    method training_epoch_end (line 75) | def training_epoch_end(self, outputs):
    method test_step (line 78) | def test_step(self, batch, batch_idx):
    method validation_step (line 86) | def validation_step(self, batch, batch_idx):
    method predict_step (line 94) | def predict_step(self, batch, batch_idx):
    method _common_step (line 99) | def _common_step(self, x, batch_idx):
    method configure_optimizers (line 106) | def configure_optimizers(self):
  class MNISTDataModule (line 111) | class MNISTDataModule(pl.LightningDataModule):
    method __init__ (line 112) | def __init__(self, batch_size=512):
    method setup (line 116) | def setup(self, stage):
    method train_dataloader (line 127) | def train_dataloader(self):
    method val_dataloader (line 135) | def val_dataloader(self):
    method test_dataloader (line 140) | def test_dataloader(self):
  class MyPrintingCallback (line 146) | class MyPrintingCallback(Callback):
    method on_train_start (line 147) | def on_train_start(self, trainer, pl_module):
    method on_train_end (line 150) | def on_train_end(self, trainer, pl_module):

FILE: ML/Pytorch/Basics/pytorch_bidirectional_lstm.py
  class BRNN (line 39) | class BRNN(nn.Module):
    method __init__ (line 40) | def __init__(self, input_size, hidden_size, num_layers, num_classes):
    method forward (line 49) | def forward(self, x):
  function check_accuracy (line 98) | def check_accuracy(loader, model):

FILE: ML/Pytorch/Basics/pytorch_init_weights.py
  class CNN (line 21) | class CNN(nn.Module):
    method __init__ (line 22) | def __init__(self, in_channels, num_classes):
    method forward (line 42) | def forward(self, x):
    method initialize_weights (line 52) | def initialize_weights(self):

FILE: ML/Pytorch/Basics/pytorch_loadsave.py
  function save_checkpoint (line 30) | def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 35) | def load_checkpoint(checkpoint, model, optimizer):
  function main (line 41) | def main():

FILE: ML/Pytorch/Basics/pytorch_lr_ratescheduler.py
  function check_accuracy (line 86) | def check_accuracy(loader, model):

FILE: ML/Pytorch/Basics/pytorch_mixed_precision_example.py
  class CNN (line 26) | class CNN(nn.Module):
    method __init__ (line 27) | def __init__(self, in_channels=1, num_classes=10):
    method forward (line 46) | def forward(self, x):
  function check_accuracy (line 108) | def check_accuracy(loader, model):

FILE: ML/Pytorch/Basics/pytorch_pretrain_finetune.py
  function check_accuracy (line 85) | def check_accuracy(loader, model):

FILE: ML/Pytorch/Basics/pytorch_rnn_gru_lstm.py
  class RNN (line 36) | class RNN(nn.Module):
    method __init__ (line 37) | def __init__(self, input_size, hidden_size, num_layers, num_classes):
    method forward (line 44) | def forward(self, x):
  class RNN_GRU (line 58) | class RNN_GRU(nn.Module):
    method __init__ (line 59) | def __init__(self, input_size, hidden_size, num_layers, num_classes):
    method forward (line 66) | def forward(self, x):
  class RNN_LSTM (line 80) | class RNN_LSTM(nn.Module):
    method __init__ (line 81) | def __init__(self, input_size, hidden_size, num_layers, num_classes):
    method forward (line 88) | def forward(self, x):
  function check_accuracy (line 140) | def check_accuracy(loader, model):

FILE: ML/Pytorch/Basics/pytorch_simple_CNN.py
  class CNN (line 28) | class CNN(nn.Module):
    method __init__ (line 29) | def __init__(self, in_channels=1, num_classes=10):
    method forward (line 48) | def forward(self, x):
  function check_accuracy (line 104) | def check_accuracy(loader, model):

FILE: ML/Pytorch/Basics/pytorch_simple_fullynet.py
  class NN (line 32) | class NN(nn.Module):
    method __init__ (line 33) | def __init__(self, input_size, num_classes):
    method forward (line 49) | def forward(self, x):
  function check_accuracy (line 117) | def check_accuracy(loader, model):

FILE: ML/Pytorch/Basics/pytorch_std_mean.py
  function get_mean_std (line 24) | def get_mean_std(loader):

FILE: ML/Pytorch/Basics/pytorch_tensorboard_.py
  class CNN (line 27) | class CNN(nn.Module):
    method __init__ (line 28) | def __init__(self, in_channels=1, num_classes=10):
    method forward (line 39) | def forward(self, x):

FILE: ML/Pytorch/Basics/pytorch_transforms.py
  class CNN (line 22) | class CNN(nn.Module):
    method __init__ (line 23) | def __init__(self, in_channels, num_classes):
    method forward (line 42) | def forward(self, x):
  function check_accuracy (line 120) | def check_accuracy(loader, model):

FILE: ML/Pytorch/Basics/set_deterministic_behavior/pytorch_set_seeds.py
  function seed_everything (line 7) | def seed_everything(seed=42):

FILE: ML/Pytorch/CNN_architectures/lenet5_pytorch.py
  class LeNet (line 13) | class LeNet(nn.Module):
    method __init__ (line 14) | def __init__(self):
    method forward (line 42) | def forward(self, x):
  function test_lenet (line 56) | def test_lenet():

FILE: ML/Pytorch/CNN_architectures/pytorch_efficientnet.py
  class CNNBlock (line 38) | class CNNBlock(nn.Module):
    method __init__ (line 39) | def __init__(
    method forward (line 55) | def forward(self, x):
  class SqueezeExcitation (line 59) | class SqueezeExcitation(nn.Module):
    method __init__ (line 60) | def __init__(self, in_channels, reduced_dim):
    method forward (line 70) | def forward(self, x):
  class InvertedResidualBlock (line 74) | class InvertedResidualBlock(nn.Module):
    method __init__ (line 75) | def __init__(
    method stochastic_depth (line 116) | def stochastic_depth(self, x):
    method forward (line 125) | def forward(self, inputs):
  class EfficientNet (line 134) | class EfficientNet(nn.Module):
    method __init__ (line 135) | def __init__(self, version, num_classes):
    method calculate_factors (line 146) | def calculate_factors(self, version, alpha=1.2, beta=1.1):
    method create_features (line 152) | def create_features(self, width_factor, depth_factor, last_channels):
    method forward (line 180) | def forward(self, x):
  function test (line 185) | def test():

FILE: ML/Pytorch/CNN_architectures/pytorch_inceptionet.py
  class GoogLeNet (line 13) | class GoogLeNet(nn.Module):
    method __init__ (line 14) | def __init__(self, aux_logits=True, num_classes=1000):
    method forward (line 58) | def forward(self, x):
  class Inception_block (line 97) | class Inception_block(nn.Module):
    method __init__ (line 98) | def __init__(
    method forward (line 119) | def forward(self, x):
  class InceptionAux (line 125) | class InceptionAux(nn.Module):
    method __init__ (line 126) | def __init__(self, in_channels, num_classes):
    method forward (line 135) | def forward(self, x):
  class conv_block (line 145) | class conv_block(nn.Module):
    method __init__ (line 146) | def __init__(self, in_channels, out_channels, **kwargs):
    method forward (line 152) | def forward(self, x):

FILE: ML/Pytorch/CNN_architectures/pytorch_resnet.py
  class block (line 17) | class block(nn.Module):
    method __init__ (line 18) | def __init__(
    method forward (line 54) | def forward(self, x):
  class ResNet (line 74) | class ResNet(nn.Module):
    method __init__ (line 75) | def __init__(self, block, layers, image_channels, num_classes):
    method forward (line 102) | def forward(self, x):
    method _make_layer (line 118) | def _make_layer(self, block, num_residual_blocks, intermediate_channel...
  function ResNet50 (line 153) | def ResNet50(img_channel=3, num_classes=1000):
  function ResNet101 (line 157) | def ResNet101(img_channel=3, num_classes=1000):
  function ResNet152 (line 161) | def ResNet152(img_channel=3, num_classes=1000):
  function test (line 165) | def test():

FILE: ML/Pytorch/CNN_architectures/pytorch_vgg_implementation.py
  class VGG_net (line 62) | class VGG_net(nn.Module):
    method __init__ (line 63) | def __init__(self, in_channels=3, num_classes=1000):
    method forward (line 78) | def forward(self, x):
    method create_conv_layers (line 84) | def create_conv_layers(self, architecture):

FILE: ML/Pytorch/GANs/1. SimpleGAN/fc_gan.py
  class Discriminator (line 20) | class Discriminator(nn.Module):
    method __init__ (line 21) | def __init__(self, in_features):
    method forward (line 30) | def forward(self, x):
  class Generator (line 34) | class Generator(nn.Module):
    method __init__ (line 35) | def __init__(self, z_dim, img_dim):
    method forward (line 44) | def forward(self, x):

FILE: ML/Pytorch/GANs/2. DCGAN/model.py
  class Discriminator (line 13) | class Discriminator(nn.Module):
    method __init__ (line 14) | def __init__(self, channels_img, features_d):
    method _block (line 29) | def _block(self, in_channels, out_channels, kernel_size, stride, paddi...
    method forward (line 43) | def forward(self, x):
  class Generator (line 47) | class Generator(nn.Module):
    method __init__ (line 48) | def __init__(self, channels_noise, channels_img, features_g):
    method _block (line 63) | def _block(self, in_channels, out_channels, kernel_size, stride, paddi...
    method forward (line 77) | def forward(self, x):
  function initialize_weights (line 81) | def initialize_weights(model):
  function test (line 88) | def test():

FILE: ML/Pytorch/GANs/3. WGAN/model.py
  class Discriminator (line 15) | class Discriminator(nn.Module):
    method __init__ (line 16) | def __init__(self, channels_img, features_d):
    method _block (line 32) | def _block(self, in_channels, out_channels, kernel_size, stride, paddi...
    method forward (line 46) | def forward(self, x):
  class Generator (line 50) | class Generator(nn.Module):
    method __init__ (line 51) | def __init__(self, channels_noise, channels_img, features_g):
    method _block (line 66) | def _block(self, in_channels, out_channels, kernel_size, stride, paddi...
    method forward (line 80) | def forward(self, x):
  function initialize_weights (line 84) | def initialize_weights(model):
  function test (line 91) | def test():

FILE: ML/Pytorch/GANs/4. WGAN-GP/model.py
  class Discriminator (line 13) | class Discriminator(nn.Module):
    method __init__ (line 14) | def __init__(self, channels_img, features_d):
    method _block (line 28) | def _block(self, in_channels, out_channels, kernel_size, stride, paddi...
    method forward (line 42) | def forward(self, x):
  class Generator (line 46) | class Generator(nn.Module):
    method __init__ (line 47) | def __init__(self, channels_noise, channels_img, features_g):
    method _block (line 62) | def _block(self, in_channels, out_channels, kernel_size, stride, paddi...
    method forward (line 76) | def forward(self, x):
  function initialize_weights (line 80) | def initialize_weights(model):
  function test (line 87) | def test():

FILE: ML/Pytorch/GANs/4. WGAN-GP/utils.py
  function gradient_penalty (line 5) | def gradient_penalty(critic, real, fake, device="cpu"):
  function save_checkpoint (line 27) | def save_checkpoint(state, filename="celeba_wgan_gp.pth.tar"):
  function load_checkpoint (line 32) | def load_checkpoint(checkpoint, gen, disc):

FILE: ML/Pytorch/GANs/CycleGAN/dataset.py
  class HorseZebraDataset (line 6) | class HorseZebraDataset(Dataset):
    method __init__ (line 7) | def __init__(self, root_zebra, root_horse, transform=None):
    method __len__ (line 18) | def __len__(self):
    method __getitem__ (line 21) | def __getitem__(self, index):

FILE: ML/Pytorch/GANs/CycleGAN/discriminator_model.py
  class Block (line 13) | class Block(nn.Module):
    method __init__ (line 14) | def __init__(self, in_channels, out_channels, stride):
    method forward (line 30) | def forward(self, x):
  class Discriminator (line 34) | class Discriminator(nn.Module):
    method __init__ (line 35) | def __init__(self, in_channels=3, features=[64, 128, 256, 512]):
    method forward (line 68) | def forward(self, x):
  function test (line 73) | def test():

FILE: ML/Pytorch/GANs/CycleGAN/generator_model.py
  class ConvBlock (line 13) | class ConvBlock(nn.Module):
    method __init__ (line 14) | def __init__(self, in_channels, out_channels, down=True, use_act=True,...
    method forward (line 24) | def forward(self, x):
  class ResidualBlock (line 28) | class ResidualBlock(nn.Module):
    method __init__ (line 29) | def __init__(self, channels):
    method forward (line 36) | def forward(self, x):
  class Generator (line 40) | class Generator(nn.Module):
    method __init__ (line 41) | def __init__(self, img_channels, num_features=64, num_residuals=9):
    method forward (line 104) | def forward(self, x):
  function test (line 114) | def test():

FILE: ML/Pytorch/GANs/CycleGAN/train.py
  function train_fn (line 23) | def train_fn(
  function main (line 102) | def main():

FILE: ML/Pytorch/GANs/CycleGAN/utils.py
  function save_checkpoint (line 6) | def save_checkpoint(model, optimizer, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 15) | def load_checkpoint(checkpoint_file, model, optimizer, lr):
  function seed_everything (line 27) | def seed_everything(seed=42):

FILE: ML/Pytorch/GANs/ESRGAN/dataset.py
  class MyImageFolder (line 13) | class MyImageFolder(Dataset):
    method __init__ (line 14) | def __init__(self, root_dir):
    method __len__ (line 24) | def __len__(self):
    method __getitem__ (line 27) | def __getitem__(self, index):
  function test (line 39) | def test():

FILE: ML/Pytorch/GANs/ESRGAN/loss.py
  class VGGLoss (line 6) | class VGGLoss(nn.Module):
    method __init__ (line 7) | def __init__(self):
    method forward (line 16) | def forward(self, input, target):

FILE: ML/Pytorch/GANs/ESRGAN/model.py
  class ConvBlock (line 5) | class ConvBlock(nn.Module):
    method __init__ (line 6) | def __init__(self, in_channels, out_channels, use_act, **kwargs):
    method forward (line 16) | def forward(self, x):
  class UpsampleBlock (line 20) | class UpsampleBlock(nn.Module):
    method __init__ (line 21) | def __init__(self, in_c, scale_factor=2):
    method forward (line 27) | def forward(self, x):
  class DenseResidualBlock (line 31) | class DenseResidualBlock(nn.Module):
    method __init__ (line 32) | def __init__(self, in_channels, channels=32, residual_beta=0.2):
    method forward (line 49) | def forward(self, x):
  class RRDB (line 57) | class RRDB(nn.Module):
    method __init__ (line 58) | def __init__(self, in_channels, residual_beta=0.2):
    method forward (line 63) | def forward(self, x):
  class Generator (line 67) | class Generator(nn.Module):
    method __init__ (line 68) | def __init__(self, in_channels=3, num_channels=64, num_blocks=23):
    method forward (line 89) | def forward(self, x):
  class Discriminator (line 96) | class Discriminator(nn.Module):
    method __init__ (line 97) | def __init__(self, in_channels=3, features=[64, 64, 128, 128, 256, 256...
    method forward (line 122) | def forward(self, x):
  function initialize_weights (line 126) | def initialize_weights(model, scale=0.1):
  function test (line 137) | def test():

FILE: ML/Pytorch/GANs/ESRGAN/train.py
  function train_fn (line 15) | def train_fn(
  function main (line 78) | def main():

FILE: ML/Pytorch/GANs/ESRGAN/utils.py
  function gradient_penalty (line 9) | def gradient_penalty(critic, real, fake, device):
  function save_checkpoint (line 32) | def save_checkpoint(model, optimizer, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 41) | def load_checkpoint(checkpoint_file, model, optimizer, lr):
  function plot_examples (line 54) | def plot_examples(low_res_folder, gen):

FILE: ML/Pytorch/GANs/Pix2Pix/dataset.py
  class MapDataset (line 9) | class MapDataset(Dataset):
    method __init__ (line 10) | def __init__(self, root_dir):
    method __len__ (line 14) | def __len__(self):
    method __getitem__ (line 17) | def __getitem__(self, index):

FILE: ML/Pytorch/GANs/Pix2Pix/discriminator_model.py
  class CNNBlock (line 5) | class CNNBlock(nn.Module):
    method __init__ (line 6) | def __init__(self, in_channels, out_channels, stride):
    method forward (line 16) | def forward(self, x):
  class Discriminator (line 20) | class Discriminator(nn.Module):
    method __init__ (line 21) | def __init__(self, in_channels=3, features=[64, 128, 256, 512]):
    method forward (line 51) | def forward(self, x, y):
  function test (line 58) | def test():

FILE: ML/Pytorch/GANs/Pix2Pix/generator_model.py
  class Block (line 5) | class Block(nn.Module):
    method __init__ (line 6) | def __init__(self, in_channels, out_channels, down=True, act="relu", u...
    method forward (line 20) | def forward(self, x):
  class Generator (line 25) | class Generator(nn.Module):
    method __init__ (line 26) | def __init__(self, in_channels=3, features=64):
    method forward (line 74) | def forward(self, x):
  function test (line 93) | def test():

FILE: ML/Pytorch/GANs/Pix2Pix/train.py
  function train_fn (line 16) | def train_fn(
  function main (line 58) | def main():

FILE: ML/Pytorch/GANs/Pix2Pix/utils.py
  function save_some_examples (line 5) | def save_some_examples(gen, val_loader, epoch, folder):
  function save_checkpoint (line 19) | def save_checkpoint(model, optimizer, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 28) | def load_checkpoint(checkpoint_file, model, optimizer, lr):

FILE: ML/Pytorch/GANs/ProGAN/model.py
  class WSConv2d (line 28) | class WSConv2d(nn.Module):
    method __init__ (line 38) | def __init__(
    method forward (line 51) | def forward(self, x):
  class PixelNorm (line 55) | class PixelNorm(nn.Module):
    method __init__ (line 56) | def __init__(self):
    method forward (line 60) | def forward(self, x):
  class ConvBlock (line 64) | class ConvBlock(nn.Module):
    method __init__ (line 65) | def __init__(self, in_channels, out_channels, use_pixelnorm=True):
    method forward (line 73) | def forward(self, x):
  class Generator (line 81) | class Generator(nn.Module):
    method __init__ (line 82) | def __init__(self, z_dim, in_channels, img_channels=3):
    method fade_in (line 113) | def fade_in(self, alpha, upscaled, generated):
    method forward (line 117) | def forward(self, x, alpha, steps):
  class Discriminator (line 136) | class Discriminator(nn.Module):
    method __init__ (line 137) | def __init__(self, z_dim, in_channels, img_channels=3):
    method fade_in (line 175) | def fade_in(self, alpha, downscaled, out):
    method minibatch_std (line 180) | def minibatch_std(self, x):
    method forward (line 189) | def forward(self, x, alpha, steps):

FILE: ML/Pytorch/GANs/ProGAN/train.py
  function get_loader (line 24) | def get_loader(image_size):
  function train_fn (line 48) | def train_fn(
  function main (line 124) | def main():

FILE: ML/Pytorch/GANs/ProGAN/utils.py
  function plot_to_tensorboard (line 12) | def plot_to_tensorboard(
  function gradient_penalty (line 25) | def gradient_penalty(critic, real, fake, alpha, train_step, device="cpu"):
  function save_checkpoint (line 48) | def save_checkpoint(model, optimizer, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 57) | def load_checkpoint(checkpoint_file, model, optimizer, lr):
  function seed_everything (line 68) | def seed_everything(seed=42):
  function generate_examples (line 78) | def generate_examples(gen, steps, truncation=0.7, n=100):

FILE: ML/Pytorch/GANs/SRGAN/dataset.py
  class MyImageFolder (line 8) | class MyImageFolder(Dataset):
    method __init__ (line 9) | def __init__(self, root_dir):
    method __len__ (line 19) | def __len__(self):
    method __getitem__ (line 22) | def __getitem__(self, index):
  function test (line 33) | def test():

FILE: ML/Pytorch/GANs/SRGAN/loss.py
  class VGGLoss (line 7) | class VGGLoss(nn.Module):
    method __init__ (line 8) | def __init__(self):
    method forward (line 16) | def forward(self, input, target):

FILE: ML/Pytorch/GANs/SRGAN/model.py
  class ConvBlock (line 5) | class ConvBlock(nn.Module):
    method __init__ (line 6) | def __init__(
    method forward (line 25) | def forward(self, x):
  class UpsampleBlock (line 29) | class UpsampleBlock(nn.Module):
    method __init__ (line 30) | def __init__(self, in_c, scale_factor):
    method forward (line 36) | def forward(self, x):
  class ResidualBlock (line 40) | class ResidualBlock(nn.Module):
    method __init__ (line 41) | def __init__(self, in_channels):
    method forward (line 59) | def forward(self, x):
  class Generator (line 65) | class Generator(nn.Module):
    method __init__ (line 66) | def __init__(self, in_channels=3, num_channels=64, num_blocks=16):
    method forward (line 74) | def forward(self, x):
  class Discriminator (line 82) | class Discriminator(nn.Module):
    method __init__ (line 83) | def __init__(self, in_channels=3, features=[64, 64, 128, 128, 256, 256...
    method forward (line 110) | def forward(self, x):
  function test (line 114) | def test():

FILE: ML/Pytorch/GANs/SRGAN/train.py
  function train_fn (line 15) | def train_fn(loader, disc, gen, opt_gen, opt_disc, mse, bce, vgg_loss):
  function main (line 51) | def main():

FILE: ML/Pytorch/GANs/SRGAN/utils.py
  function gradient_penalty (line 9) | def gradient_penalty(critic, real, fake, device):
  function save_checkpoint (line 32) | def save_checkpoint(model, optimizer, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 41) | def load_checkpoint(checkpoint_file, model, optimizer, lr):
  function plot_examples (line 53) | def plot_examples(low_res_folder, gen):

FILE: ML/Pytorch/GANs/StyleGAN/model.py
  class PixelNorm (line 8) | class PixelNorm(nn.Module):
    method __init__ (line 9) | def __init__(self):
    method forward (line 13) | def forward(self, x):
  class MappingNetwork (line 17) | class MappingNetwork(nn.Module):
    method __init__ (line 18) | def __init__(self, z_dim, w_dim):
    method forward (line 39) | def forward(self, x):
  class InjectNoise (line 43) | class InjectNoise(nn.Module):
    method __init__ (line 44) | def __init__(self, channels):
    method forward (line 48) | def forward(self, x):
  class AdaIN (line 52) | class AdaIN(nn.Module):
    method __init__ (line 53) | def __init__(self, channels, w_dim):
    method forward (line 59) | def forward(self, x, w):
  class WSConv2d (line 66) | class WSConv2d(nn.Module):
    method __init__ (line 67) | def __init__(
    method forward (line 80) | def forward(self, x):
  class WSLinear (line 84) | class WSLinear(nn.Module):
    method __init__ (line 85) | def __init__(
    method forward (line 98) | def forward(self, x):
  class GenBlock (line 102) | class GenBlock(nn.Module):
    method __init__ (line 103) | def __init__(self, in_channels, out_channels, w_dim):
    method forward (line 113) | def forward(self, x, w):
  class ConvBlock (line 118) | class ConvBlock(nn.Module):
    method __init__ (line 119) | def __init__(self, in_channels, out_channels):
    method forward (line 125) | def forward(self, x):
  class Generator (line 131) | class Generator(nn.Module):
    method __init__ (line 132) | def __init__(self, z_dim, w_dim, in_channels, img_channels=3):
    method fade_in (line 159) | def fade_in(self, alpha, upscaled, generated):
    method forward (line 163) | def forward(self, noise, alpha, steps):
  class Discriminator (line 185) | class Discriminator(nn.Module):
    method __init__ (line 186) | def __init__(self, in_channels, img_channels=3):
    method fade_in (line 224) | def fade_in(self, alpha, downscaled, out):
    method minibatch_std (line 229) | def minibatch_std(self, x):
    method forward (line 238) | def forward(self, x, alpha, steps):

FILE: ML/Pytorch/GANs/StyleGAN/prepare_data.py
  function resize (line 8) | def resize(file, size, folder_to_save):

FILE: ML/Pytorch/GANs/StyleGAN/train.py
  function get_loader (line 24) | def get_loader(image_size):
  function train_fn (line 48) | def train_fn(
  function main (line 132) | def main():

FILE: ML/Pytorch/GANs/StyleGAN/utils.py
  function plot_to_tensorboard (line 10) | def plot_to_tensorboard(
  function gradient_penalty (line 23) | def gradient_penalty(critic, real, fake, alpha, train_step, device="cpu"):
  function save_checkpoint (line 46) | def save_checkpoint(model, optimizer, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 55) | def load_checkpoint(checkpoint_file, model, optimizer, lr):
  function seed_everything (line 67) | def seed_everything(seed=42):
  class EMA (line 78) | class EMA:
    method __init__ (line 81) | def __init__(self, gamma=0.99, save=True, save_frequency=100, save_fil...
    method register_weights (line 99) | def register_weights(self, model):
    method __call__ (line 108) | def __call__(self, model):
    method copy_weights_to (line 118) | def copy_weights_to(self, model):
    method save_ema_weights (line 123) | def save_ema_weights(self):

FILE: ML/Pytorch/huggingface/dataset.py
  class cnn_dailymail (line 7) | class cnn_dailymail(Dataset):
    method __init__ (line 8) | def __init__(self, csv_file, tokenizer, max_length=512):
    method __len__ (line 18) | def __len__(self):
    method __getitem__ (line 21) | def __getitem__(self, idx):
  class MyDataModule (line 47) | class MyDataModule(pl.LightningDataModule):
    method __init__ (line 48) | def __init__(
    method setup (line 59) | def setup(self, stage=None):
    method train_dataloader (line 72) | def train_dataloader(self):
    method val_dataloader (line 81) | def val_dataloader(self):
    method test_dataloader (line 86) | def test_dataloader(self):

FILE: ML/Pytorch/huggingface/learninghugg.py
  function tokenize_function (line 10) | def tokenize_function(example):
  function compute_metrics (line 24) | def compute_metrics(eval_preds):

FILE: ML/Pytorch/huggingface/model.py
  class MyLightningModule (line 16) | class MyLightningModule(pl.LightningModule):
    method __init__ (line 17) | def __init__(self, model_name, learning_rate, weight_decay):
    method forward (line 40) | def forward(self, input_ids, attention_mask, labels=None):
    method training_step (line 48) | def training_step(self, batch, batch_idx):
    method validation_step (line 56) | def validation_step(self, batch, batch_idx):
    method on_validation_epoch_end (line 69) | def on_validation_epoch_end(self):
    method predict (line 95) | def predict(self, article: str, max_input_length: int = 512, max_outpu...
    method configure_optimizers (line 124) | def configure_optimizers(self):

FILE: ML/Pytorch/image_segmentation/semantic_segmentation_unet/dataset.py
  class CarvanaDataset (line 6) | class CarvanaDataset(Dataset):
    method __init__ (line 7) | def __init__(self, image_dir, mask_dir, transform=None):
    method __len__ (line 13) | def __len__(self):
    method __getitem__ (line 16) | def __getitem__(self, index):

FILE: ML/Pytorch/image_segmentation/semantic_segmentation_unet/model.py
  class DoubleConv (line 5) | class DoubleConv(nn.Module):
    method __init__ (line 6) | def __init__(self, in_channels, out_channels):
    method forward (line 17) | def forward(self, x):
  class UNET (line 20) | class UNET(nn.Module):
    method __init__ (line 21) | def __init__(
    method forward (line 46) | def forward(self, x):
  function test (line 69) | def test():

FILE: ML/Pytorch/image_segmentation/semantic_segmentation_unet/train.py
  function train_fn (line 31) | def train_fn(loader, model, optimizer, loss_fn, scaler):
  function main (line 53) | def main():

FILE: ML/Pytorch/image_segmentation/semantic_segmentation_unet/utils.py
  function save_checkpoint (line 6) | def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 10) | def load_checkpoint(checkpoint, model):
  function get_loaders (line 14) | def get_loaders(
  function check_accuracy (line 55) | def check_accuracy(loader, model, device="cuda"):
  function save_predictions_as_imgs (line 79) | def save_predictions_as_imgs(

FILE: ML/Pytorch/more_advanced/Seq2Seq/seq2seq.py
  function tokenize_ger (line 16) | def tokenize_ger(text):
  function tokenize_eng (line 20) | def tokenize_eng(text):
  class Encoder (line 38) | class Encoder(nn.Module):
    method __init__ (line 39) | def __init__(self, input_size, embedding_size, hidden_size, num_layers...
    method forward (line 48) | def forward(self, x):
  class Decoder (line 60) | class Decoder(nn.Module):
    method __init__ (line 61) | def __init__(
    method forward (line 73) | def forward(self, x, hidden, cell):
  class Seq2Seq (line 94) | class Seq2Seq(nn.Module):
    method __init__ (line 95) | def __init__(self, encoder, decoder):
    method forward (line 100) | def forward(self, source, target, teacher_force_ratio=0.5):

FILE: ML/Pytorch/more_advanced/Seq2Seq/utils.py
  function translate_sentence (line 7) | def translate_sentence(model, sentence, german, english, device, max_len...
  function bleu (line 59) | def bleu(data, model, german, english, device):
  function save_checkpoint (line 76) | def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 81) | def load_checkpoint(checkpoint, model, optimizer):

FILE: ML/Pytorch/more_advanced/Seq2Seq_attention/seq2seq_attention.py
  function tokenize_ger (line 21) | def tokenize_ger(text):
  function tokenize_eng (line 25) | def tokenize_eng(text):
  class Encoder (line 43) | class Encoder(nn.Module):
    method __init__ (line 44) | def __init__(self, input_size, embedding_size, hidden_size, num_layers...
    method forward (line 56) | def forward(self, x):
  class Decoder (line 74) | class Decoder(nn.Module):
    method __init__ (line 75) | def __init__(
    method forward (line 91) | def forward(self, x, encoder_states, hidden, cell):
  class Seq2Seq (line 125) | class Seq2Seq(nn.Module):
    method __init__ (line 126) | def __init__(self, encoder, decoder):
    method forward (line 131) | def forward(self, source, target, teacher_force_ratio=0.5):

FILE: ML/Pytorch/more_advanced/Seq2Seq_attention/utils.py
  function translate_sentence (line 7) | def translate_sentence(model, sentence, german, english, device, max_len...
  function bleu (line 54) | def bleu(data, model, german, english, device):
  function save_checkpoint (line 71) | def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 76) | def load_checkpoint(checkpoint, model, optimizer):

FILE: ML/Pytorch/more_advanced/VAE/lightning_vae/dataset.py
  class MNISTDataModule (line 9) | class MNISTDataModule(pl.LightningDataModule):
    method __init__ (line 10) | def __init__(self, batch_size, num_workers):
    method setup (line 15) | def setup(self, stage):
    method train_dataloader (line 26) | def train_dataloader(self):
    method val_dataloader (line 35) | def val_dataloader(self):
    method test_dataloader (line 44) | def test_dataloader(self):

FILE: ML/Pytorch/more_advanced/VAE/lightning_vae/model.py
  class VAEpl (line 7) | class VAEpl(pl.LightningModule):
    method __init__ (line 8) | def __init__(self, lr, input_dim=784, h_dim=200, z_dim=20):
    method encode (line 25) | def encode(self, x):
    method decode (line 30) | def decode(self, z):
    method forward (line 34) | def forward(self, x):
    method training_step (line 41) | def training_step(self, batch, batch_idx):
    method validation_step (line 62) | def validation_step(self, batch, batch_idx):
    method test_step (line 72) | def test_step(self, batch, batch_idx):
    method configure_optimizers (line 82) | def configure_optimizers(self):

FILE: ML/Pytorch/more_advanced/VAE/lightning_vae/utils.py
  function inference (line 8) | def inference(model, dataset, digit, num_examples=1):

FILE: ML/Pytorch/more_advanced/VAE/model.py
  class VariationalAutoEncoder (line 5) | class VariationalAutoEncoder(nn.Module):
    method __init__ (line 6) | def __init__(self, input_dim, h_dim=200, z_dim=20):
    method encode (line 19) | def encode(self, x):
    method decode (line 24) | def decode(self, z):
    method forward (line 28) | def forward(self, x):

FILE: ML/Pytorch/more_advanced/VAE/train.py
  function inference (line 27) | def inference(digit, num_examples=1):

FILE: ML/Pytorch/more_advanced/finetuning_whisper/dataset.py
  class CommonVoice (line 16) | class CommonVoice(Dataset):
    method __init__ (line 17) | def __init__(self, data_dir, whisper_model="tiny"):
    method __len__ (line 31) | def __len__(self):
    method __getitem__ (line 34) | def __getitem__(self, idx):
  class DataCollatorSpeechSeq2SeqWithPadding (line 59) | class DataCollatorSpeechSeq2SeqWithPadding:
    method __init__ (line 60) | def __init__(self, feature_extractor, tokenizer):
    method __call__ (line 64) | def __call__(self, batch):
  class WhisperDataset (line 89) | class WhisperDataset(pl.LightningDataModule):
    method __init__ (line 90) | def __init__(self, data_dir, batch_size=32, num_workers=0, whisper_mod...
    method setup (line 98) | def setup(self, stage=None):
    method train_dataloader (line 104) | def train_dataloader(self):

FILE: ML/Pytorch/more_advanced/finetuning_whisper/model.py
  class WhisperFinetuning (line 9) | class WhisperFinetuning(pl.LightningModule):
    method __init__ (line 10) | def __init__(self, lr, whisper_model="tiny"):
    method training_step (line 17) | def training_step(self, batch, batch_idx):
    method configure_optimizers (line 28) | def configure_optimizers(self):

FILE: ML/Pytorch/more_advanced/finetuning_whisper/whisper.py
  function prepare_dataset (line 69) | def prepare_dataset(example):
  class DataCollatorSpeechSeq2SeqWithPadding (line 87) | class DataCollatorSpeechSeq2SeqWithPadding:
    method __call__ (line 90) | def __call__(
  function compute_metrics (line 126) | def compute_metrics(pred):

FILE: ML/Pytorch/more_advanced/image_captioning/get_loader.py
  class Vocabulary (line 22) | class Vocabulary:
    method __init__ (line 23) | def __init__(self, freq_threshold):
    method __len__ (line 28) | def __len__(self):
    method tokenizer_eng (line 32) | def tokenizer_eng(text):
    method build_vocabulary (line 35) | def build_vocabulary(self, sentence_list):
    method numericalize (line 52) | def numericalize(self, text):
  class FlickrDataset (line 61) | class FlickrDataset(Dataset):
    method __init__ (line 62) | def __init__(self, root_dir, captions_file, transform=None, freq_thres...
    method __len__ (line 75) | def __len__(self):
    method __getitem__ (line 78) | def __getitem__(self, index):
  class MyCollate (line 93) | class MyCollate:
    method __init__ (line 94) | def __init__(self, pad_idx):
    method __call__ (line 97) | def __call__(self, batch):
  function get_loader (line 106) | def get_loader(

FILE: ML/Pytorch/more_advanced/image_captioning/model.py
  class EncoderCNN (line 7) | class EncoderCNN(nn.Module):
    method __init__ (line 8) | def __init__(self, embed_size, train_CNN=False):
    method forward (line 17) | def forward(self, images):
  class DecoderRNN (line 22) | class DecoderRNN(nn.Module):
    method __init__ (line 23) | def __init__(self, embed_size, hidden_size, vocab_size, num_layers):
    method forward (line 30) | def forward(self, features, captions):
  class CNNtoRNN (line 38) | class CNNtoRNN(nn.Module):
    method __init__ (line 39) | def __init__(self, embed_size, hidden_size, vocab_size, num_layers):
    method forward (line 44) | def forward(self, images, captions):
    method caption_image (line 49) | def caption_image(self, image, vocabulary, max_length=50):

FILE: ML/Pytorch/more_advanced/image_captioning/train.py
  function train (line 12) | def train():

FILE: ML/Pytorch/more_advanced/image_captioning/utils.py
  function print_examples (line 6) | def print_examples(model, device, dataset):
  function save_checkpoint (line 59) | def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 64) | def load_checkpoint(checkpoint, model, optimizer):

FILE: ML/Pytorch/more_advanced/neuralstyle/nst.py
  class VGG (line 10) | class VGG(nn.Module):
    method __init__ (line 11) | def __init__(self):
    method forward (line 24) | def forward(self, x):
  function load_image (line 40) | def load_image(image_name):

FILE: ML/Pytorch/more_advanced/seq2seq_transformer/seq2seq_transformer.py
  function tokenize_ger (line 31) | def tokenize_ger(text):
  function tokenize_eng (line 35) | def tokenize_eng(text):
  class Transformer (line 53) | class Transformer(nn.Module):
    method __init__ (line 54) | def __init__(
    method make_src_mask (line 87) | def make_src_mask(self, src):
    method forward (line 93) | def forward(self, src, trg):

FILE: ML/Pytorch/more_advanced/seq2seq_transformer/utils.py
  function translate_sentence (line 7) | def translate_sentence(model, sentence, german, english, device, max_len...
  function bleu (line 45) | def bleu(data, model, german, english, device):
  function save_checkpoint (line 62) | def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 67) | def load_checkpoint(checkpoint, model, optimizer):

FILE: ML/Pytorch/more_advanced/torchtext/torchtext_tutorial1.py
  function tokenize (line 20) | def tokenize(text):
  class RNN_LSTM (line 54) | class RNN_LSTM(nn.Module):
    method __init__ (line 55) | def __init__(self, input_size, embed_size, hidden_size, num_layers):
    method forward (line 64) | def forward(self, x):

FILE: ML/Pytorch/more_advanced/torchtext/torchtext_tutorial2.py
  function tokenize_eng (line 15) | def tokenize_eng(text):
  function tokenize_ger (line 19) | def tokenize_ger(text):

FILE: ML/Pytorch/more_advanced/torchtext/torchtext_tutorial3.py
  function tokenize_eng (line 39) | def tokenize_eng(text):
  function tokenize_ger (line 43) | def tokenize_ger(text):

FILE: ML/Pytorch/more_advanced/transformer_from_scratch/transformer_from_scratch.py
  class SelfAttention (line 15) | class SelfAttention(nn.Module):
    method __init__ (line 16) | def __init__(self, embed_size, heads):
    method forward (line 31) | def forward(self, values, keys, query, mask):
  class TransformerBlock (line 80) | class TransformerBlock(nn.Module):
    method __init__ (line 81) | def __init__(self, embed_size, heads, dropout, forward_expansion):
    method forward (line 95) | def forward(self, value, key, query, mask):
  class Encoder (line 105) | class Encoder(nn.Module):
    method __init__ (line 106) | def __init__(
    method forward (line 138) | def forward(self, x, mask):
  class DecoderBlock (line 153) | class DecoderBlock(nn.Module):
    method __init__ (line 154) | def __init__(self, embed_size, heads, forward_expansion, dropout, devi...
    method forward (line 163) | def forward(self, x, value, key, src_mask, trg_mask):
  class Decoder (line 170) | class Decoder(nn.Module):
    method __init__ (line 171) | def __init__(
    method forward (line 196) | def forward(self, x, enc_out, src_mask, trg_mask):
  class Transformer (line 209) | class Transformer(nn.Module):
    method __init__ (line 210) | def __init__(
    method make_src_mask (line 253) | def make_src_mask(self, src):
    method make_trg_mask (line 258) | def make_trg_mask(self, trg):
    method forward (line 266) | def forward(self, src, trg):

FILE: ML/Pytorch/object_detection/YOLO/dataset.py
  class VOCDataset (line 11) | class VOCDataset(torch.utils.data.Dataset):
    method __init__ (line 12) | def __init__(
    method __len__ (line 23) | def __len__(self):
    method __getitem__ (line 26) | def __getitem__(self, index):

FILE: ML/Pytorch/object_detection/YOLO/loss.py
  class YoloLoss (line 11) | class YoloLoss(nn.Module):
    method __init__ (line 16) | def __init__(self, S=7, B=2, C=20):
    method forward (line 34) | def forward(self, predictions, target):

FILE: ML/Pytorch/object_detection/YOLO/model.py
  class CNNBlock (line 38) | class CNNBlock(nn.Module):
    method __init__ (line 39) | def __init__(self, in_channels, out_channels, **kwargs):
    method forward (line 45) | def forward(self, x):
  class Yolov1 (line 49) | class Yolov1(nn.Module):
    method __init__ (line 50) | def __init__(self, in_channels=3, **kwargs):
    method forward (line 57) | def forward(self, x):
    method _create_conv_layers (line 61) | def _create_conv_layers(self, architecture):
    method _create_fcs (line 105) | def _create_fcs(self, split_size, num_boxes, num_classes):

FILE: ML/Pytorch/object_detection/YOLO/train.py
  class Compose (line 43) | class Compose(object):
    method __init__ (line 44) | def __init__(self, transforms):
    method __call__ (line 47) | def __call__(self, img, bboxes):
  function train_fn (line 57) | def train_fn(train_loader, model, optimizer, loss_fn):
  function main (line 76) | def main():

FILE: ML/Pytorch/object_detection/YOLO/utils.py
  function intersection_over_union (line 7) | def intersection_over_union(boxes_preds, boxes_labels, box_format="midpo...
  function non_max_suppression (line 54) | def non_max_suppression(bboxes, iou_threshold, threshold, box_format="co...
  function mean_average_precision (line 95) | def mean_average_precision(
  function plot_image (line 203) | def plot_image(image, boxes):
  function get_bboxes (line 235) | def get_bboxes(
  function convert_cellboxes (line 290) | def convert_cellboxes(predictions, S=7):
  function cellboxes_to_boxes (line 327) | def cellboxes_to_boxes(out, S=7):
  function save_checkpoint (line 341) | def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 346) | def load_checkpoint(checkpoint, model, optimizer):

FILE: ML/Pytorch/object_detection/YOLOv3/dataset.py
  class YOLODataset (line 22) | class YOLODataset(Dataset):
    method __init__ (line 23) | def __init__(
    method __len__ (line 46) | def __len__(self):
    method __getitem__ (line 49) | def __getitem__(self, index):
  function test (line 93) | def test():

FILE: ML/Pytorch/object_detection/YOLOv3/loss.py
  class YoloLoss (line 13) | class YoloLoss(nn.Module):
    method __init__ (line 14) | def __init__(self):
    method forward (line 27) | def forward(self, predictions, target, anchors):

FILE: ML/Pytorch/object_detection/YOLOv3/model.py
  class CNNBlock (line 44) | class CNNBlock(nn.Module):
    method __init__ (line 45) | def __init__(self, in_channels, out_channels, bn_act=True, **kwargs):
    method forward (line 52) | def forward(self, x):
  class ResidualBlock (line 59) | class ResidualBlock(nn.Module):
    method __init__ (line 60) | def __init__(self, channels, use_residual=True, num_repeats=1):
    method forward (line 74) | def forward(self, x):
  class ScalePrediction (line 84) | class ScalePrediction(nn.Module):
    method __init__ (line 85) | def __init__(self, in_channels, num_classes):
    method forward (line 95) | def forward(self, x):
  class YOLOv3 (line 103) | class YOLOv3(nn.Module):
    method __init__ (line 104) | def __init__(self, in_channels=3, num_classes=80):
    method forward (line 110) | def forward(self, x):
    method _create_conv_layers (line 129) | def _create_conv_layers(self):

FILE: ML/Pytorch/object_detection/YOLOv3/train.py
  function train_fn (line 28) | def train_fn(train_loader, model, optimizer, loss_fn, scaler, scaled_anc...
  function main (line 59) | def main():

FILE: ML/Pytorch/object_detection/YOLOv3/utils.py
  function iou_width_height (line 14) | def iou_width_height(boxes1, boxes2):
  function intersection_over_union (line 31) | def intersection_over_union(boxes_preds, boxes_labels, box_format="midpo...
  function non_max_suppression (line 80) | def non_max_suppression(bboxes, iou_threshold, threshold, box_format="co...
  function mean_average_precision (line 124) | def mean_average_precision(
  function plot_image (line 235) | def plot_image(image, boxes):
  function get_evaluation_bboxes (line 280) | def get_evaluation_bboxes(
  function cells_to_bboxes (line 337) | def cells_to_bboxes(predictions, anchors, S, is_preds=True):
  function check_class_accuracy (line 376) | def check_class_accuracy(model, loader, threshold):
  function get_mean_std (line 409) | def get_mean_std(loader):
  function save_checkpoint (line 424) | def save_checkpoint(model, optimizer, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 433) | def load_checkpoint(checkpoint_file, model, optimizer, lr):
  function get_loaders (line 445) | def get_loaders(train_csv_path, test_csv_path):
  function plot_couple_examples (line 501) | def plot_couple_examples(model, loader, thresh, iou_thresh, anchors):
  function seed_everything (line 527) | def seed_everything(seed=42):

FILE: ML/Pytorch/object_detection/metrics/iou.py
  function intersection_over_union (line 4) | def intersection_over_union(boxes_preds, boxes_labels, box_format="midpo...

FILE: ML/Pytorch/object_detection/metrics/mean_avg_precision.py
  function mean_average_precision (line 6) | def mean_average_precision(

FILE: ML/Pytorch/object_detection/metrics/nms.py
  function nms (line 4) | def nms(bboxes, iou_threshold, threshold, box_format="corners"):

FILE: ML/Pytorch/others/default_setups/CV - Image Classification/augmentations.py
  function ShearX (line 7) | def ShearX(img, v):  # [-0.3, 0.3]
  function ShearY (line 14) | def ShearY(img, v):  # [-0.3, 0.3]
  function TranslateX (line 21) | def TranslateX(img, v):  # [-150, 150] => percentage: [-0.45, 0.45]
  function TranslateXabs (line 29) | def TranslateXabs(img, v):  # [-150, 150] => percentage: [-0.45, 0.45]
  function TranslateY (line 36) | def TranslateY(img, v):  # [-150, 150] => percentage: [-0.45, 0.45]
  function TranslateYabs (line 44) | def TranslateYabs(img, v):  # [-150, 150] => percentage: [-0.45, 0.45]
  function Rotate (line 51) | def Rotate(img, v):  # [-30, 30]
  function AutoContrast (line 58) | def AutoContrast(img, _):
  function Invert (line 62) | def Invert(img, _):
  function Equalize (line 66) | def Equalize(img, _):
  function Flip (line 70) | def Flip(img, _):  # not from the paper
  function Solarize (line 74) | def Solarize(img, v):  # [0, 256]
  function SolarizeAdd (line 79) | def SolarizeAdd(img, addition=0, threshold=128):
  function Posterize (line 88) | def Posterize(img, v):  # [4, 8]
  function Contrast (line 94) | def Contrast(img, v):  # [0.1,1.9]
  function Color (line 99) | def Color(img, v):  # [0.1,1.9]
  function Brightness (line 104) | def Brightness(img, v):  # [0.1,1.9]
  function Sharpness (line 109) | def Sharpness(img, v):  # [0.1,1.9]
  function Cutout (line 114) | def Cutout(img, v):  # [0, 60] => percentage: [0, 0.2]
  function CutoutAbs (line 123) | def CutoutAbs(img, v):  # [0, 60] => percentage: [0, 0.2]
  function SamplePairing (line 144) | def SamplePairing(imgs):  # [0, 0.4]
  function Identity (line 152) | def Identity(img, v):
  function augment_list (line 155) | def augment_list():
  class RandAugment (line 177) | class RandAugment:
    method __init__ (line 178) | def __init__(self, n, m):
    method __call__ (line 183) | def __call__(self, img):

FILE: ML/Pytorch/others/default_setups/CV - Image Classification/dataset.py
  class MyImageFolder (line 9) | class MyImageFolder(Dataset):
    method __init__ (line 10) | def __init__(self, root_dir, transform=None):
    method __len__ (line 21) | def __len__(self):
    method __getitem__ (line 24) | def __getitem__(self, index):

FILE: ML/Pytorch/others/default_setups/CV - Image Classification/model.py
  class Net (line 4) | class Net(nn.Module):
    method __init__ (line 5) | def __init__(self, net_version, num_classes):
    method forward (line 12) | def forward(self, x):

FILE: ML/Pytorch/others/default_setups/CV - Image Classification/train.py
  function train_fn (line 12) | def train_fn(loader, model, optimizer, loss_fn, scaler, device):
  function main (line 30) | def main():

FILE: ML/Pytorch/others/default_setups/CV - Image Classification/utils.py
  function check_accuracy (line 9) | def check_accuracy(loader, model, device="cuda"):
  function save_checkpoint (line 29) | def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
  function load_checkpoint (line 34) | def load_checkpoint(checkpoint, model, optimizer):
  function make_prediction (line 39) | def make_prediction(model, transform, rootdir, device):

FILE: ML/Pytorch/pytorch_lightning/1. start code/simple_fc.py
  class NN (line 11) | class NN(nn.Module):
    method __init__ (line 12) | def __init__(self, input_size, num_classes):
    method forward (line 17) | def forward(self, x):
  function check_accuracy (line 75) | def check_accuracy(loader, model):

FILE: ML/Pytorch/pytorch_lightning/10. Multi-GPU/callbacks.py
  class MyPrintingCallback (line 3) | class MyPrintingCallback(Callback):
    method __init__ (line 4) | def __init__(self):
    method on_train_start (line 7) | def on_train_start(self, trainer, pl_module):
    method on_train_end (line 10) | def on_train_end(self, trainer, pl_module):

FILE: ML/Pytorch/pytorch_lightning/10. Multi-GPU/dataset.py
  class MnistDataModule (line 12) | class MnistDataModule(pl.LightningDataModule):
    method __init__ (line 13) | def __init__(self, data_dir, batch_size, num_workers):
    method prepare_data (line 19) | def prepare_data(self):
    method setup (line 23) | def setup(self, stage):
    method train_dataloader (line 42) | def train_dataloader(self):
    method val_dataloader (line 50) | def val_dataloader(self):
    method test_dataloader (line 58) | def test_dataloader(self):

FILE: ML/Pytorch/pytorch_lightning/10. Multi-GPU/model.py
  class NN (line 14) | class NN(pl.LightningModule):
    method __init__ (line 15) | def __init__(self, input_size, learning_rate, num_classes):
    method forward (line 26) | def forward(self, x):
    method training_step (line 31) | def training_step(self, batch, batch_idx):
    method training_epoch_end (line 51) | def training_epoch_end(self, outputs):
    method validation_step (line 64) | def validation_step(self, batch, batch_idx):
    method test_step (line 69) | def test_step(self, batch, batch_idx):
    method _common_step (line 74) | def _common_step(self, batch, batch_idx):
    method predict_step (line 81) | def predict_step(self, batch, batch_idx):
    method configure_optimizers (line 88) | def configure_optimizers(self):

FILE: ML/Pytorch/pytorch_lightning/2. LightningModule/simple_fc.py
  class NN (line 11) | class NN(nn.Module):
    method __init__ (line 12) | def __init__(self, input_size, num_classes):
    method forward (line 17) | def forward(self, x):
    method __init__ (line 23) | def __init__(self, input_size, num_classes):
    method forward (line 29) | def forward(self, x):
    method training_step (line 34) | def training_step(self, batch, batch_idx):
    method validation_step (line 39) | def validation_step(self, batch, batch_idx):
    method test_step (line 44) | def test_step(self, batch, batch_idx):
    method _common_step (line 49) | def _common_step(self, batch, batch_idx):
    method predict_step (line 56) | def predict_step(self, batch, batch_idx):
    method configure_optimizers (line 63) | def configure_optimizers(self):
  class NN (line 22) | class NN(pl.LightningModule):
    method __init__ (line 12) | def __init__(self, input_size, num_classes):
    method forward (line 17) | def forward(self, x):
    method __init__ (line 23) | def __init__(self, input_size, num_classes):
    method forward (line 29) | def forward(self, x):
    method training_step (line 34) | def training_step(self, batch, batch_idx):
    method validation_step (line 39) | def validation_step(self, batch, batch_idx):
    method test_step (line 44) | def test_step(self, batch, batch_idx):
    method _common_step (line 49) | def _common_step(self, batch, batch_idx):
    method predict_step (line 56) | def predict_step(self, batch, batch_idx):
    method configure_optimizers (line 63) | def configure_optimizers(self):
  function check_accuracy (line 119) | def check_accuracy(loader, model):

FILE: ML/Pytorch/pytorch_lightning/3. Lightning Trainer/simple_fc.py
  class NN (line 12) | class NN(pl.LightningModule):
    method __init__ (line 13) | def __init__(self, input_size, num_classes):
    method forward (line 19) | def forward(self, x):
    method training_step (line 24) | def training_step(self, batch, batch_idx):
    method validation_step (line 29) | def validation_step(self, batch, batch_idx):
    method test_step (line 34) | def test_step(self, batch, batch_idx):
    method _common_step (line 39) | def _common_step(self, batch, batch_idx):
    method predict_step (line 46) | def predict_step(self, batch, batch_idx):
    method configure_optimizers (line 53) | def configure_optimizers(self):
  function check_accuracy (line 98) | def check_accuracy(loader, model):

FILE: ML/Pytorch/pytorch_lightning/4. Metrics/simple_fc.py
  class MyAccuracy (line 14) | class MyAccuracy(Metric):
    method __init__ (line 15) | def __init__(self):
    method update (line 20) | def update(self, preds, target):
    method compute (line 26) | def compute(self):
  class NN (line 30) | class NN(pl.LightningModule):
    method __init__ (line 31) | def __init__(self, input_size, num_classes):
    method forward (line 40) | def forward(self, x):
    method training_step (line 45) | def training_step(self, batch, batch_idx):
    method validation_step (line 53) | def validation_step(self, batch, batch_idx):
    method test_step (line 58) | def test_step(self, batch, batch_idx):
    method _common_step (line 63) | def _common_step(self, batch, batch_idx):
    method predict_step (line 70) | def predict_step(self, batch, batch_idx):
    method configure_optimizers (line 77) | def configure_optimizers(self):
  function check_accuracy (line 115) | def check_accuracy(loader, model):

FILE: ML/Pytorch/pytorch_lightning/5. DataModule/simple_fc.py
  class MyAccuracy (line 14) | class MyAccuracy(Metric):
    method __init__ (line 15) | def __init__(self):
    method update (line 20) | def update(self, preds, target):
    method compute (line 26) | def compute(self):
  class NN (line 30) | class NN(pl.LightningModule):
    method __init__ (line 31) | def __init__(self, input_size, num_classes):
    method forward (line 40) | def forward(self, x):
    method training_step (line 45) | def training_step(self, batch, batch_idx):
    method validation_step (line 53) | def validation_step(self, batch, batch_idx):
    method test_step (line 58) | def test_step(self, batch, batch_idx):
    method _common_step (line 63) | def _common_step(self, batch, batch_idx):
    method predict_step (line 70) | def predict_step(self, batch, batch_idx):
    method configure_optimizers (line 77) | def configure_optimizers(self):
  class MnistDataModule (line 81) | class MnistDataModule(pl.LightningDataModule):
    method __init__ (line 82) | def __init__(self, data_dir, batch_size, num_workers):
    method prepare_data (line 88) | def prepare_data(self):
    method setup (line 92) | def setup(self, stage):
    method train_dataloader (line 107) | def train_dataloader(self):
    method val_dataloader (line 115) | def val_dataloader(self):
    method test_dataloader (line 123) | def test_dataloader(self):

FILE: ML/Pytorch/pytorch_lightning/6. Restructuring/dataset.py
  class MnistDataModule (line 11) | class MnistDataModule(pl.LightningDataModule):
    method __init__ (line 12) | def __init__(self, data_dir, batch_size, num_workers):
    method prepare_data (line 18) | def prepare_data(self):
    method setup (line 22) | def setup(self, stage):
    method train_dataloader (line 37) | def train_dataloader(self):
    method val_dataloader (line 45) | def val_dataloader(self):
    method test_dataloader (line 53) | def test_dataloader(self):

FILE: ML/Pytorch/pytorch_lightning/6. Restructuring/model.py
  class NN (line 13) | class NN(pl.LightningModule):
    method __init__ (line 14) | def __init__(self, input_size, learning_rate, num_classes):
    method forward (line 25) | def forward(self, x):
    method training_step (line 30) | def training_step(self, batch, batch_idx):
    method validation_step (line 46) | def validation_step(self, batch, batch_idx):
    method test_step (line 51) | def test_step(self, batch, batch_idx):
    method _common_step (line 56) | def _common_step(self, batch, batch_idx):
    method predict_step (line 63) | def predict_step(self, batch, batch_idx):
    method configure_optimizers (line 70) | def configure_optimizers(self):

FILE: ML/Pytorch/pytorch_lightning/7. Callbacks/callbacks.py
  class MyPrintingCallback (line 3) | class MyPrintingCallback(Callback):
    method __init__ (line 4) | def __init__(self):
    method on_train_start (line 7) | def on_train_start(self, trainer, pl_module):
    method on_train_end (line 10) | def on_train_end(self, trainer, pl_module):

FILE: ML/Pytorch/pytorch_lightning/7. Callbacks/dataset.py
  class MnistDataModule (line 11) | class MnistDataModule(pl.LightningDataModule):
    method __init__ (line 12) | def __init__(self, data_dir, batch_size, num_workers):
    method prepare_data (line 18) | def prepare_data(self):
    method setup (line 22) | def setup(self, stage):
    method train_dataloader (line 37) | def train_dataloader(self):
    method val_dataloader (line 45) | def val_dataloader(self):
    method test_dataloader (line 53) | def test_dataloader(self):

FILE: ML/Pytorch/pytorch_lightning/7. Callbacks/model.py
  class NN (line 13) | class NN(pl.LightningModule):
    method __init__ (line 14) | def __init__(self, input_size, learning_rate, num_classes):
    method forward (line 25) | def forward(self, x):
    method training_step (line 30) | def training_step(self, batch, batch_idx):
    method validation_step (line 46) | def validation_step(self, batch, batch_idx):
    method test_step (line 51) | def test_step(self, batch, batch_idx):
    method _common_step (line 56) | def _common_step(self, batch, batch_idx):
    method predict_step (line 63) | def predict_step(self, batch, batch_idx):
    method configure_optimizers (line 70) | def configure_optimizers(self):

FILE: ML/Pytorch/pytorch_lightning/8. Logging Tensorboard/callbacks.py
  class MyPrintingCallback (line 3) | class MyPrintingCallback(Callback):
    method __init__ (line 4) | def __init__(self):
    method on_train_start (line 7) | def on_train_start(self, trainer, pl_module):
    method on_train_end (line 10) | def on_train_end(self, trainer, pl_module):

FILE: ML/Pytorch/pytorch_lightning/8. Logging Tensorboard/dataset.py
  class MnistDataModule (line 12) | class MnistDataModule(pl.LightningDataModule):
    method __init__ (line 13) | def __init__(self, data_dir, batch_size, num_workers):
    method prepare_data (line 19) | def prepare_data(self):
    method setup (line 23) | def setup(self, stage):
    method train_dataloader (line 42) | def train_dataloader(self):
    method val_dataloader (line 50) | def val_dataloader(self):
    method test_dataloader (line 58) | def test_dataloader(self):

FILE: ML/Pytorch/pytorch_lightning/8. Logging Tensorboard/model.py
  class NN (line 14) | class NN(pl.LightningModule):
    method __init__ (line 15) | def __init__(self, input_size, learning_rate, num_classes):
    method forward (line 26) | def forward(self, x):
    method training_step (line 31) | def training_step(self, batch, batch_idx):
    method validation_step (line 54) | def validation_step(self, batch, batch_idx):
    method test_step (line 59) | def test_step(self, batch, batch_idx):
    method _common_step (line 64) | def _common_step(self, batch, batch_idx):
    method predict_step (line 71) | def predict_step(self, batch, batch_idx):
    method configure_optimizers (line 78) | def configure_optimizers(self):

FILE: ML/Pytorch/pytorch_lightning/9. Profiler/callbacks.py
  class MyPrintingCallback (line 3) | class MyPrintingCallback(Callback):
    method __init__ (line 4) | def __init__(self):
    method on_train_start (line 7) | def on_train_start(self, trainer, pl_module):
    method on_train_end (line 10) | def on_train_end(self, trainer, pl_module):

FILE: ML/Pytorch/pytorch_lightning/9. Profiler/dataset.py
  class MnistDataModule (line 12) | class MnistDataModule(pl.LightningDataModule):
    method __init__ (line 13) | def __init__(self, data_dir, batch_size, num_workers):
    method prepare_data (line 19) | def prepare_data(self):
    method setup (line 23) | def setup(self, stage):
    method train_dataloader (line 42) | def train_dataloader(self):
    method val_dataloader (line 50) | def val_dataloader(self):
    method test_dataloader (line 58) | def test_dataloader(self):

FILE: ML/Pytorch/pytorch_lightning/9. Profiler/model.py
  class NN (line 14) | class NN(pl.LightningModule):
    method __init__ (line 15) | def __init__(self, input_size, learning_rate, num_classes):
    method forward (line 26) | def forward(self, x):
    method training_step (line 31) | def training_step(self, batch, batch_idx):
    method training_epoch_end (line 51) | def training_epoch_end(self, outputs):
    method validation_step (line 64) | def validation_step(self, batch, batch_idx):
    method test_step (line 69) | def test_step(self, batch, batch_idx):
    method _common_step (line 74) | def _common_step(self, batch, batch_idx):
    method predict_step (line 81) | def predict_step(self, batch, batch_idx):
    method configure_optimizers (line 88) | def configure_optimizers(self):

FILE: ML/Pytorch/recommender_systems/neural_collaborative_filtering/main.py
  class MovieLens (line 18) | class MovieLens(Dataset):
    method __init__ (line 19) | def __init__(self, df_ratings):
    method __len__ (line 22) | def __len__(self):
    method __getitem__ (line 25) | def __getitem__(self, idx):
  class LightningData (line 33) | class LightningData(pl.LightningDataModule):
    method __init__ (line 34) | def __init__(self, batch_size):
    method prepare_data (line 38) | def prepare_data(self):
    method setup (line 53) | def setup(self, stage=None):
    method train_dataloader (line 57) | def train_dataloader(self):
    method val_dataloader (line 60) | def val_dataloader(self):
  class Net (line 63) | class Net(nn.Module):
    method __init__ (line 64) | def __init__(self, n_users, n_movies, n_factors=50):
    method forward (line 70) | def forward(self, user, movie):
  class NetLightning (line 77) | class NetLightning(pl.LightningModule):
    method __init__ (line 78) | def __init__(self, n_users, n_movies, n_factors=50, lr=3e-4):
    method forward (line 87) | def forward(self, user, movie):
    method training_step (line 90) | def training_step(self, batch, batch_idx):
    method validation_step (line 98) | def validation_step(self, batch, batch_idx):
    method predict_step (line 105) | def predict_step(self, user_id):
    method configure_optimizers (line 109) | def configure_optimizers(self):

FILE: ML/TensorFlow/Basics/tutorial10-save-model.py
  class MyModel (line 34) | class MyModel(keras.Model):
    method __init__ (line 35) | def __init__(self):
    method call (line 40) | def call(self, input_tensor):

FILE: ML/TensorFlow/Basics/tutorial12-tensorflowdatasets.py
  function normalize_img (line 25) | def normalize_img(image, label):
  function build_vocabulary (line 75) | def build_vocabulary():
  function my_enc (line 89) | def my_enc(text_tensor, label):
  function encode_map_fn (line 94) | def encode_map_fn(text, label):

FILE: ML/TensorFlow/Basics/tutorial13-data-augmentation.py
  function normalize_img (line 18) | def normalize_img(image, label):
  function augment (line 27) | def augment(image, label):

FILE: ML/TensorFlow/Basics/tutorial14-callbacks.py
  function normalize_img (line 22) | def normalize_img(image, label):
  class OurOwnCallback (line 55) | class OurOwnCallback(keras.callbacks.Callback):
    method on_epoch_end (line 56) | def on_epoch_end(self, epoch, logs=None):

FILE: ML/TensorFlow/Basics/tutorial15-customizing-modelfit.py
  class CustomFit (line 28) | class CustomFit(keras.Model):
    method __init__ (line 29) | def __init__(self, model):
    method compile (line 33) | def compile(self, optimizer, loss):
    method train_step (line 38) | def train_step(self, data):
    method test_step (line 58) | def test_step(self, data):

FILE: ML/TensorFlow/Basics/tutorial16-customloops.py
  function normalize_img (line 23) | def normalize_img(image, label):

FILE: ML/TensorFlow/Basics/tutorial17-tensorboard/1_tb_callback.py
  function normalize_img (line 27) | def normalize_img(image, label):
  function augment (line 32) | def augment(image, label):
  function get_model (line 72) | def get_model():

FILE: ML/TensorFlow/Basics/tutorial17-tensorboard/2_tb_scalars.py
  function normalize_img (line 27) | def normalize_img(image, label):
  function augment (line 36) | def augment(image, label):
  function get_model (line 73) | def get_model():

FILE: ML/TensorFlow/Basics/tutorial17-tensorboard/3_tb_images.py
  function normalize_img (line 29) | def normalize_img(image, label):
  function augment (line 38) | def augment(image, label):
  function get_model (line 78) | def get_model():

FILE: ML/TensorFlow/Basics/tutorial17-tensorboard/4_tb_confusion.py
  function normalize_img (line 29) | def normalize_img(image, label):
  function augment (line 38) | def augment(image, label):
  function get_model (line 75) | def get_model():

FILE: ML/TensorFlow/Basics/tutorial17-tensorboard/5_tb_graph.py
  function my_func (line 22) | def my_func(x, y):

FILE: ML/TensorFlow/Basics/tutorial17-tensorboard/6_tb_hparams.py
  function normalize_img (line 28) | def normalize_img(image, label):
  function augment (line 37) | def augment(image, label):
  function train_model_one_epoch (line 74) | def train_model_one_epoch(hparams):

FILE: ML/TensorFlow/Basics/tutorial17-tensorboard/7_tb_projector.py
  function normalize_img (line 29) | def normalize_img(image, label):
  function augment (line 38) | def augment(image, label):

FILE: ML/TensorFlow/Basics/tutorial17-tensorboard/utils.py
  function plot_to_image (line 14) | def plot_to_image(figure):
  function image_grid (line 35) | def image_grid(data, labels, class_names):
  function get_confusion_matrix (line 59) | def get_confusion_matrix(y_labels, logits, class_names):
  function plot_confusion_matrix (line 68) | def plot_confusion_matrix(cm, class_names):
  function create_sprite (line 99) | def create_sprite(data):
  function plot_to_projector (line 122) | def plot_to_projector(

FILE: ML/TensorFlow/Basics/tutorial18-customdata-images/1_in_subfolders.py
  function augment (line 58) | def augment(x, y):
  function training (line 109) | def training():

FILE: ML/TensorFlow/Basics/tutorial18-customdata-images/2_csv_file.py
  function read_image (line 17) | def read_image(image_file, label):
  function augment (line 23) | def augment(image, label):

FILE: ML/TensorFlow/Basics/tutorial18-customdata-images/3_single_folder.py
  function process_path (line 18) | def process_path(file_path):

FILE: ML/TensorFlow/Basics/tutorial19-customdata-text/tutorial19-customdata-text.py
  function filter_train (line 51) | def filter_train(line):
  function filter_test (line 63) | def filter_test(line):
  function build_vocabulary (line 85) | def build_vocabulary(ds_train, threshold=200):
  function my_encoder (line 125) | def my_encoder(text_tensor, label):
  function encode_map_fn (line 130) | def encode_map_fn(line):

FILE: ML/TensorFlow/Basics/tutorial20-classify-cancer-beginner-project-example/train_isic.py
  function plot_roc (line 96) | def plot_roc(labels, data):

FILE: ML/TensorFlow/Basics/tutorial4-convnet.py
  function my_model (line 32) | def my_model():

FILE: ML/TensorFlow/Basics/tutorial5-regularization.py
  function my_model (line 18) | def my_model():

FILE: ML/TensorFlow/Basics/tutorial7-indepth-functional.py
  function read_image (line 30) | def read_image(image_path, label):

FILE: ML/TensorFlow/Basics/tutorial8_keras_subclassing.py
  class CNNBlock (line 20) | class CNNBlock(layers.Layer):
    method __init__ (line 21) | def __init__(self, out_channels, kernel_size=3):
    method call (line 26) | def call(self, input_tensor, training=False):
  class ResBlock (line 38) | class ResBlock(layers.Layer):
    method __init__ (line 39) | def __init__(self, channels):
    method call (line 48) | def call(self, input_tensor, training=False):
  class ResNet_Like (line 56) | class ResNet_Like(keras.Model):
    method __init__ (line 57) | def __init__(self, num_classes=10):
    method call (line 65) | def call(self, input_tensor, training=False):
    method model (line 73) | def model(self):

FILE: ML/TensorFlow/Basics/tutorial9-custom-layers.py
  class Dense (line 18) | class Dense(layers.Layer):
    method __init__ (line 19) | def __init__(self, units, input_dim):
    method call (line 31) | def call(self, inputs):
    method __init__ (line 36) | def __init__(self, units):
    method build (line 40) | def build(self, input_shape):
    method call (line 51) | def call(self, inputs):
  class Dense (line 35) | class Dense(layers.Layer):
    method __init__ (line 19) | def __init__(self, units, input_dim):
    method call (line 31) | def call(self, inputs):
    method __init__ (line 36) | def __init__(self, units):
    method build (line 40) | def build(self, input_shape):
    method call (line 51) | def call(self, inputs):
  class MyReLU (line 55) | class MyReLU(layers.Layer):
    method __init__ (line 56) | def __init__(self):
    method call (line 59) | def call(self, x):
  class MyModel (line 63) | class MyModel(Model):  # model.fit, model.evalute, model.predict
    method __init__ (line 64) | def __init__(self, num_classes=10):
    method call (line 73) | def call(self, x):

FILE: ML/TensorFlow/CNN_architectures/AlexNet/alexnet.py
  function AlexNet (line 23) | def AlexNet(input_shape: typing.Tuple[int], classes: int = 1000) -> Model:

FILE: ML/TensorFlow/CNN_architectures/GoogLeNet/block.py
  function convolution_block (line 22) | def convolution_block(
  function inception_block (line 55) | def inception_block(
  function auxiliary_block (line 131) | def auxiliary_block(

FILE: ML/TensorFlow/CNN_architectures/GoogLeNet/googlenet.py
  function GoogLeNet (line 27) | def GoogLeNet(input_shape: typing.Tuple[int] = (224, 224, 3), classes: i...

FILE: ML/TensorFlow/CNN_architectures/LeNet5/lenet5.py
  function LeNet5 (line 21) | def LeNet5(input_shape: typing.Tuple[int], classes: int = 1000) -> Model:

FILE: ML/TensorFlow/CNN_architectures/ResNet/block.py
  function block (line 17) | def block(

FILE: ML/TensorFlow/CNN_architectures/ResNet/resnet.py
  function ResNet (line 27) | def ResNet(name: str, layers: typing.List[int], input_shape: typing.Tupl...
  function make_layer (line 118) | def make_layer(X: tf.Tensor, layers: int, kernel_size: int, filters: typ...

FILE: ML/TensorFlow/CNN_architectures/VGGNet/vggnet.py
  function VGGNet (line 24) | def VGGNet(
  function make_conv_layer (line 60) | def make_conv_layer(
  function make_dense_layer (line 107) | def make_dense_layer(X: tf.Tensor, output_units: int, dropout = 0.5, act...

FILE: ML/algorithms/decisiontree/decision_tree.py
  class DecisionTree (line 26) | class DecisionTree:
    method __init__ (line 27) | def __init__(self, max_depth, min_node_size):
    method calculate_gini (line 44) | def calculate_gini(self, child_nodes):
    method apply_split (line 84) | def apply_split(self, feature_index, threshold, data):
    method find_best_split (line 107) | def find_best_split(self, data):
    method calc_class (line 138) | def calc_class(self, node):
    method recursive_split (line 157) | def recursive_split(self, node, depth):
    method train (line 200) | def train(self, X):
    method print_dt (line 215) | def print_dt(self, tree, depth=0):
    method predict_single (line 240) | def predict_single(self, tree, instance):
    method predict (line 260) | def predict(self, X):

FILE: ML/algorithms/kmeans/kmeansclustering.py
  class KMeansClustering (line 16) | class KMeansClustering:
    method __init__ (line 17) | def __init__(self, X, num_clusters):
    method initialize_random_centroids (line 24) | def initialize_random_centroids(self, X):
    method create_clusters (line 33) | def create_clusters(self, X, centroids):
    method calculate_new_centroids (line 46) | def calculate_new_centroids(self, clusters, X):
    method predict_cluster (line 54) | def predict_cluster(self, clusters, X):
    method plot_fig (line 63) | def plot_fig(self, X, y):
    method fit (line 67) | def fit(self, X):

FILE: ML/algorithms/knn/knn.py
  class KNearestNeighbor (line 13) | class KNearestNeighbor:
    method __init__ (line 14) | def __init__(self, k):
    method train (line 18) | def train(self, X, y):
    method predict (line 22) | def predict(self, X_test, num_loops=0):
    method compute_distance_two_loops (line 34) | def compute_distance_two_loops(self, X_test):
    method compute_distance_one_loop (line 53) | def compute_distance_one_loop(self, X_test):
    method compute_distance_vectorized (line 70) | def compute_distance_vectorized(self, X_test):
    method predict_labels (line 88) | def predict_labels(self, distances):

FILE: ML/algorithms/linearregression/linear_regression_gradient_descent.py
  class LinearRegression (line 16) | class LinearRegression:
    method __init__ (line 17) | def __init__(self, print_cost=False):
    method y_hat (line 22) | def y_hat(self, X, w):
    method cost (line 25) | def cost(self, yhat, y):
    method gradient_descent (line 30) | def gradient_descent(self, w, X, y, yhat):
    method main (line 36) | def main(self, X, y):

FILE: ML/algorithms/linearregression/linear_regression_normal_equation.py
  function linear_regression_normal_equation (line 16) | def linear_regression_normal_equation(X, y):

FILE: ML/algorithms/logisticregression/logistic_regression.py
  class LogisticRegression (line 13) | class LogisticRegression:
    method __init__ (line 14) | def __init__(self, X, learning_rate=0.1, num_iters=10000):
    method train (line 21) | def train(self, X, y):
    method predict (line 51) | def predict(self, X):
    method sigmoid (line 57) | def sigmoid(self, z):

FILE: ML/algorithms/naivebayes/naivebayes.py
  class NaiveBayes (line 20) | class NaiveBayes:
    method __init__ (line 21) | def __init__(self, X, y):
    method fit (line 26) | def fit(self, X):
    method predict (line 38) | def predict(self, X):
    method density_function (line 50) | def density_function(self, x, mean, sigma):

FILE: ML/algorithms/neuralnetwork/NN.py
  class NeuralNetwork (line 13) | class NeuralNetwork:
    method __init__ (line 14) | def __init__(self, X, y):
    method init_kaiming_weights (line 26) | def init_kaiming_weights(self, l0, l1):
    method forward_prop (line 33) | def forward_prop(self, X, parameters):
    method compute_cost (line 57) | def compute_cost(self, y, probs, parameters):
    method back_prop (line 72) | def back_prop(self, cache, parameters, y):
    method update_parameters (line 104) | def update_parameters(self, parameters, grads):
    method main (line 128) | def main(self, X, y, num_iter=10000):

FILE: ML/algorithms/neuralnetwork/utils.py
  function create_dataset (line 11) | def create_dataset(N, K=2):
  function plot_contour (line 30) | def plot_contour(X, y, model, parameters):

FILE: ML/algorithms/randomforest/random_forest.py
  class RandomForest (line 39) | class RandomForest:
    method __init__ (line 40) | def __init__(self,n_trees,fold_size):
    method cross_validation_split (line 59) | def cross_validation_split(self,dataset, n_folds, p):
    method randomize_features (line 82) | def randomize_features(self,splits):
    method print_trees (line 102) | def print_trees(self):
    method train (line 117) | def train(self,X):
    method predict (line 133) | def predict(self,X):

FILE: ML/algorithms/svm/svm.py
  function linear (line 23) | def linear(x, z):
  function polynomial (line 27) | def polynomial(x, z, p=5):
  function gaussian (line 31) | def gaussian(x, z, sigma=0.1):
  class SVM (line 35) | class SVM:
    method __init__ (line 36) | def __init__(self, kernel=gaussian, C=1):
    method fit (line 40) | def fit(self, X, y):
    method predict (line 62) | def predict(self, X):
    method get_parameters (line 75) | def get_parameters(self, alphas):

FILE: ML/algorithms/svm/utils.py
  function create_dataset (line 11) | def create_dataset(N, D=2, K=2):
  function plot_contour (line 31) | def plot_contour(X, y, svm):

FILE: ML/ml_metrics/metrics.py
  function true_positives (line 7) | def true_positives(y_true, y_pred):
  function true_negatives (line 15) | def true_negatives(y_true, y_pred):
  function false_positives (line 23) | def false_positives(y_true, y_pred):
  function false_negatives (line 31) | def false_negatives(y_true, y_pred):
  function binary_accuracy (line 39) | def binary_accuracy(y_true, y_pred):
  function precision (line 47) | def precision(y_true, y_pred):
  function recall (line 58) | def recall(y_true, y_pred):
  function multiclass_accuracy (line 69) | def multiclass_accuracy(y_true, y_pred):
  function confusion_matrix (line 77) | def confusion_matrix(y_true, y_pred):
  function accuracy_cm (line 90) | def accuracy_cm(cm):
  function balanced_accuracy_cm (line 94) | def balanced_accuracy_cm(cm):
  function precision_cm (line 104) | def precision_cm(cm, average="specific", class_label=1, eps=1e-12):
  function recall_cm (line 132) | def recall_cm(cm, average="specific", class_label=1, eps=1e-12):
  function f1score_cm (line 154) | def f1score_cm(cm, average="specific", class_label=1):
  function roc_curve (line 170) | def roc_curve(y_true, y_preds, plot_graph=True, calculate_AUC=True, thre...
  function precision_recall_curve (line 195) | def precision_recall_curve(y_true, y_preds, plot_graph=True, calculate_A...

FILE: ML_tests/LinearRegression_tests/LinearRegression_GD.py
  class TestLinearRegression_GradientDescent (line 15) | class TestLinearRegression_GradientDescent(unittest.TestCase):
    method setUp (line 16) | def setUp(self):
    method test_perfectpositiveslope (line 40) | def test_perfectpositiveslope(self):
    method test_perfectnegativeslope (line 45) | def test_perfectnegativeslope(self):
    method test_multipledimension (line 50) | def test_multipledimension(self):
    method test_zeros (line 55) | def test_zeros(self):
    method test_noisydata (line 60) | def test_noisydata(self):

FILE: ML_tests/LinearRegression_tests/LinearRegression_normal.py
  class TestLinearRegression_NormalEq (line 16) | class TestLinearRegression_NormalEq(unittest.TestCase):
    method setUp (line 17) | def setUp(self):
    method test_perfectpositiveslope (line 39) | def test_perfectpositiveslope(self):
    method test_perfectnegativeslope (line 46) | def test_perfectnegativeslope(self):
    method test_multipledimension (line 51) | def test_multipledimension(self):
    method test_zeros (line 58) | def test_zeros(self):
    method test_noisydata (line 63) | def test_noisydata(self):

FILE: ML_tests/Object_detection_tests/iou_test.py
  class TestIntersectionOverUnion (line 9) | class TestIntersectionOverUnion(unittest.TestCase):
    method setUp (line 10) | def setUp(self):
    method test_both_inside_cell_shares_area (line 82) | def test_both_inside_cell_shares_area(self):
    method test_partially_outside_cell_shares_area (line 86) | def test_partially_outside_cell_shares_area(self):
    method test_both_inside_cell_shares_no_area (line 90) | def test_both_inside_cell_shares_no_area(self):
    method test_midpoint_outside_cell_shares_area (line 94) | def test_midpoint_outside_cell_shares_area(self):
    method test_both_inside_cell_shares_entire_area (line 98) | def test_both_inside_cell_shares_entire_area(self):
    method test_box_format_x1_y1_x2_y2 (line 102) | def test_box_format_x1_y1_x2_y2(self):
    method test_additional_and_batch (line 106) | def test_additional_and_batch(self):

FILE: ML_tests/Object_detection_tests/map_test.py
  class TestMeanAveragePrecision (line 8) | class TestMeanAveragePrecision(unittest.TestCase):
    method setUp (line 9) | def setUp(self):
    method test_all_correct_one_class (line 62) | def test_all_correct_one_class(self):
    method test_all_correct_batch (line 72) | def test_all_correct_batch(self):
    method test_all_wrong_class (line 82) | def test_all_wrong_class(self):
    method test_one_inaccurate_box (line 92) | def test_one_inaccurate_box(self):
    method test_all_wrong_class (line 102) | def test_all_wrong_class(self):

FILE: ML_tests/Object_detection_tests/nms_test.py
  class TestNonMaxSuppression (line 9) | class TestNonMaxSuppression(unittest.TestCase):
    method setUp (line 10) | def setUp(self):
    method test_remove_on_iou (line 56) | def test_remove_on_iou(self):
    method test_keep_on_class (line 65) | def test_keep_on_class(self):
    method test_remove_on_iou_and_class (line 74) | def test_remove_on_iou_and_class(self):
    method test_keep_on_iou (line 83) | def test_keep_on_iou(self):