权值初始化和与损失函数

权值初始化和与损失函数

一 权值的初始化

二 损失函数

一 grad_vanish_explod.py

# @brief      : 梯度消失与爆炸实验

import os
import torch
import random
import numpy as np
import torch.nn as nn
from tools.common_tools import set_seed

set_seed(1)  # 设置随机种子


class MLP(nn.Module):
    def __init__(self, neural_num, layers):
        super(MLP, self).__init__()
        self.linears = nn.ModuleList([nn.Linear(neural_num, neural_num, bias=False) for i in range(layers)])
        self.neural_num = neural_num

    def forward(self, x):
        for (i, linear) in enumerate(self.linears):
            x = linear(x)
            x = torch.relu(x)

            print("layer:{}, std:{}".format(i, x.std()))
            if torch.isnan(x.std()):
                print("output is nan in {} layers".format(i))
                break

        return x

    def initialize(self):
        for m in self.modules():
            if isinstance(m, nn.Linear):
                # nn.init.normal_(m.weight.data, std=np.sqrt(1/self.neural_num))    # normal: mean=0, std=1

                # a = np.sqrt(6 / (self.neural_num + self.neural_num))
                #
                # tanh_gain = nn.init.calculate_gain('tanh')
                # a *= tanh_gain
                #
                # nn.init.uniform_(m.weight.data, -a, a)

                # nn.init.xavier_uniform_(m.weight.data, gain=tanh_gain)

                # nn.init.normal_(m.weight.data, std=np.sqrt(2 / self.neural_num))
                nn.init.kaiming_normal_(m.weight.data)

flag = 0
# flag = 1

if flag:
    layer_nums = 100
    neural_nums = 256
    batch_size = 16

    net = MLP(neural_nums, layer_nums)
    net.initialize()

    inputs = torch.randn((batch_size, neural_nums))  # normal: mean=0, std=1

    output = net(inputs)
    print(output)

# ======================================= calculate gain =======================================

# flag = 0
flag = 1

if flag:

    x = torch.randn(10000)
    out = torch.tanh(x)

    gain = x.std() / out.std()
    print('gain:{}'.format(gain))

    tanh_gain = nn.init.calculate_gain('tanh')
    print('tanh_gain in PyTorch:', tanh_gain)

二 损失函数

一 ce_loss.py

import os
import random
import numpy as np
import torch
import torch.nn as nn
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
import torch.optim as optim
from PIL import Image
from matplotlib import pyplot as plt
from model.lenet import LeNet
from tools.my_dataset import RMBDataset
from tools.common_tools import transform_invert, set_seed

set_seed(1)  # 设置随机种子
rmb_label = {"1": 0, "100": 1}

# 参数设置
MAX_EPOCH = 10
BATCH_SIZE = 16
LR = 0.01
log_interval = 10
val_interval = 1

# ============================ step 1/5 数据 ============================

split_dir = os.path.join("..", "..", "data", "rmb_split")
train_dir = os.path.join(split_dir, "train")
valid_dir = os.path.join(split_dir, "valid")

norm_mean = [0.485, 0.456, 0.406]
norm_std = [0.229, 0.224, 0.225]

train_transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.RandomCrop(32, padding=4),
    transforms.RandomGrayscale(p=0.8),
    transforms.ToTensor(),
    transforms.Normalize(norm_mean, norm_std),
])

valid_transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.ToTensor(),
    transforms.Normalize(norm_mean, norm_std),
])

# 构建MyDataset实例
train_data = RMBDataset(data_dir=train_dir, transform=train_transform)
valid_data = RMBDataset(data_dir=valid_dir, transform=valid_transform)

# 构建DataLoder
train_loader = DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
valid_loader = DataLoader(dataset=valid_data, batch_size=BATCH_SIZE)

# ============================ step 2/5 模型 ============================

net = LeNet(classes=2)
net.initialize_weights()

# ============================ step 3/5 损失函数 ============================
loss_functoin = nn.CrossEntropyLoss()                                                   # 选择损失函数

# ============================ step 4/5 优化器 ============================
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9)                        # 选择优化器
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=10, gamma=0.1)     # 设置学习率下降策略

# ============================ step 5/5 训练 ============================
train_curve = list()
valid_curve = list()

for epoch in range(MAX_EPOCH):

    loss_mean = 0.
    correct = 0.
    total = 0.

    net.train()
    for i, data in enumerate(train_loader):

        # forward
        inputs, labels = data
        outputs = net(inputs)

        # backward
        optimizer.zero_grad()
        loss = loss_functoin(outputs, labels)
        loss.backward()

        # update weights
        optimizer.step()

        # 统计分类情况
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).squeeze().sum().numpy()

        # 打印训练信息
        loss_mean += loss.item()
        train_curve.append(loss.item())
        if (i+1) % log_interval == 0:
            loss_mean = loss_mean / log_interval
            print("Training:Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
                epoch, MAX_EPOCH, i+1, len(train_loader), loss_mean, correct / total))
            loss_mean = 0.

    scheduler.step()  # 更新学习率

    # validate the model
    if (epoch+1) % val_interval == 0:

        correct_val = 0.
        total_val = 0.
        loss_val = 0.
        net.eval()
        with torch.no_grad():
            for j, data in enumerate(valid_loader):
                inputs, labels = data
                outputs = net(inputs)
                loss = loss_functoin(outputs, labels)

                _, predicted = torch.max(outputs.data, 1)
                total_val += labels.size(0)
                correct_val += (predicted == labels).squeeze().sum().numpy()

                loss_val += loss.item()

            valid_curve.append(loss_val)
            print("Valid:\t Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
                epoch, MAX_EPOCH, j+1, len(valid_loader), loss_val, correct / total))


train_x = range(len(train_curve))
train_y = train_curve

train_iters = len(train_loader)
valid_x = np.arange(1, len(valid_curve)+1) * train_iters*val_interval # 由于valid中记录的是epochloss，需要对记录点进行转换到iterations
valid_y = valid_curve

plt.plot(train_x, train_y, label='Train')
plt.plot(valid_x, valid_y, label='Valid')

plt.legend(loc='upper right')
plt.ylabel('loss value')
plt.xlabel('Iteration')
plt.show()

# ============================ inference ============================

BASE_DIR = os.path.dirname(os.path.abspath(__file__))
test_dir = os.path.join(BASE_DIR, "test_data")

test_data = RMBDataset(data_dir=test_dir, transform=valid_transform)
valid_loader = DataLoader(dataset=test_data, batch_size=1)

for i, data in enumerate(valid_loader):
    # forward
    inputs, labels = data
    outputs = net(inputs)
    _, predicted = torch.max(outputs.data, 1)

    rmb = 1 if predicted.numpy()[0] == 0 else 100

    img_tensor = inputs[0, ...]  # C H W
    img = transform_invert(img_tensor, train_transform)
    plt.imshow(img)
    plt.title("LeNet got {} Yuan".format(rmb))
    plt.show()
    plt.pause(0.5)
    plt.close()

二 loss_function_1.py

"""
# @brief      : 1. nn.CrossEntropyLoss
                2. nn.NLLLoss
                3. BCELoss
                4. BCEWithLogitsLoss
"""

import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np

# fake data
inputs = torch.tensor([[1, 2], [1, 3], [1, 3]], dtype=torch.float)
target = torch.tensor([0, 1, 1], dtype=torch.long)

# ----------------------------------- CrossEntropy loss: reduction -----------------------------------
flag = 0
# flag = 1
if flag:
    # def loss function
    loss_f_none = nn.CrossEntropyLoss(weight=None, reduction='none')
    loss_f_sum = nn.CrossEntropyLoss(weight=None, reduction='sum')
    loss_f_mean = nn.CrossEntropyLoss(weight=None, reduction='mean')

    # forward
    loss_none = loss_f_none(inputs, target)
    loss_sum = loss_f_sum(inputs, target)
    loss_mean = loss_f_mean(inputs, target)

    # view
    print("Cross Entropy Loss:\n ", loss_none, loss_sum, loss_mean)

# --------------------------------- compute by hand
flag = 0
# flag = 1
if flag:

    idx = 0

    input_1 = inputs.detach().numpy()[idx]      # [1, 2]
    target_1 = target.numpy()[idx]              # [0]

    # 第一项
    x_class = input_1[target_1]

    # 第二项
    sigma_exp_x = np.sum(list(map(np.exp, input_1)))
    log_sigma_exp_x = np.log(sigma_exp_x)

    # 输出loss
    loss_1 = -x_class + log_sigma_exp_x

    print("第一个样本loss为: ", loss_1)


# ----------------------------------- weight -----------------------------------
flag = 0
# flag = 1
if flag:
    # def loss function
    weights = torch.tensor([1, 2], dtype=torch.float)
    # weights = torch.tensor([0.7, 0.3], dtype=torch.float)

    loss_f_none_w = nn.CrossEntropyLoss(weight=weights, reduction='none')
    loss_f_sum = nn.CrossEntropyLoss(weight=weights, reduction='sum')
    loss_f_mean = nn.CrossEntropyLoss(weight=weights, reduction='mean')

    # forward
    loss_none_w = loss_f_none_w(inputs, target)
    loss_sum = loss_f_sum(inputs, target)
    loss_mean = loss_f_mean(inputs, target)

    # view
    print("\nweights: ", weights)
    print(loss_none_w, loss_sum, loss_mean)


# --------------------------------- compute by hand
flag = 0
# flag = 1
if flag:
    weights = torch.tensor([1, 2], dtype=torch.float)
    weights_all = np.sum(list(map(lambda x: weights.numpy()[x], target.numpy())))  # [0, 1, 1]  # [1 2 2]

    mean = 0
    loss_sep = loss_none.detach().numpy()
    for i in range(target.shape[0]):

        x_class = target.numpy()[i]
        tmp = loss_sep[i] * (weights.numpy()[x_class] / weights_all)
        mean += tmp

    print(mean)


# ----------------------------------- 2 NLLLoss -----------------------------------
flag = 0
# flag = 1
if flag:

    weights = torch.tensor([1, 1], dtype=torch.float)

    loss_f_none_w = nn.NLLLoss(weight=weights, reduction='none')
    loss_f_sum = nn.NLLLoss(weight=weights, reduction='sum')
    loss_f_mean = nn.NLLLoss(weight=weights, reduction='mean')

    # forward
    loss_none_w = loss_f_none_w(inputs, target)
    loss_sum = loss_f_sum(inputs, target)
    loss_mean = loss_f_mean(inputs, target)

    # view
    print("\nweights: ", weights)
    print("NLL Loss", loss_none_w, loss_sum, loss_mean)


# ----------------------------------- 3 BCE Loss -----------------------------------
flag = 0
# flag = 1
if flag:
    inputs = torch.tensor([[1, 2], [2, 2], [3, 4], [4, 5]], dtype=torch.float)
    target = torch.tensor([[1, 0], [1, 0], [0, 1], [0, 1]], dtype=torch.float)

    target_bce = target

    # itarget
    inputs = torch.sigmoid(inputs)

    weights = torch.tensor([1, 1], dtype=torch.float)

    loss_f_none_w = nn.BCELoss(weight=weights, reduction='none')
    loss_f_sum = nn.BCELoss(weight=weights, reduction='sum')
    loss_f_mean = nn.BCELoss(weight=weights, reduction='mean')

    # forward
    loss_none_w = loss_f_none_w(inputs, target_bce)
    loss_sum = loss_f_sum(inputs, target_bce)
    loss_mean = loss_f_mean(inputs, target_bce)

    # view
    print("\nweights: ", weights)
    print("BCE Loss", loss_none_w, loss_sum, loss_mean)


# --------------------------------- compute by hand
flag = 0
# flag = 1
if flag:

    idx = 0

    x_i = inputs.detach().numpy()[idx, idx]
    y_i = target.numpy()[idx, idx]              #

    # loss
    # l_i = -[ y_i * np.log(x_i) + (1-y_i) * np.log(1-y_i) ]      # np.log(0) = nan
    l_i = -y_i * np.log(x_i) if y_i else -(1-y_i) * np.log(1-x_i)

    # 输出loss
    print("BCE inputs: ", inputs)
    print("第一个loss为: ", l_i)


# ----------------------------------- 4 BCE with Logis Loss -----------------------------------
# flag = 0
flag = 1
if flag:
    inputs = torch.tensor([[1, 2], [2, 2], [3, 4], [4, 5]], dtype=torch.float)
    target = torch.tensor([[1, 0], [1, 0], [0, 1], [0, 1]], dtype=torch.float)

    target_bce = target

    # inputs = torch.sigmoid(inputs)

    weights = torch.tensor([1, 1], dtype=torch.float)

    loss_f_none_w = nn.BCEWithLogitsLoss(weight=weights, reduction='none')
    loss_f_sum = nn.BCEWithLogitsLoss(weight=weights, reduction='sum')
    loss_f_mean = nn.BCEWithLogitsLoss(weight=weights, reduction='mean')

    # forward
    loss_none_w = loss_f_none_w(inputs, target_bce)
    loss_sum = loss_f_sum(inputs, target_bce)
    loss_mean = loss_f_mean(inputs, target_bce)

    # view
    print("\nweights: ", weights)
    print(loss_none_w, loss_sum, loss_mean)


# --------------------------------- pos weight

# flag = 0
flag = 1
if flag:
    inputs = torch.tensor([[1, 2], [2, 2], [3, 4], [4, 5]], dtype=torch.float)
    target = torch.tensor([[1, 0], [1, 0], [0, 1], [0, 1]], dtype=torch.float)

    target_bce = target

    # itarget
    # inputs = torch.sigmoid(inputs)

    weights = torch.tensor([1], dtype=torch.float)
    pos_w = torch.tensor([3], dtype=torch.float)        # 3

    loss_f_none_w = nn.BCEWithLogitsLoss(weight=weights, reduction='none', pos_weight=pos_w)
    loss_f_sum = nn.BCEWithLogitsLoss(weight=weights, reduction='sum', pos_weight=pos_w)
    loss_f_mean = nn.BCEWithLogitsLoss(weight=weights, reduction='mean', pos_weight=pos_w)

    # forward
    loss_none_w = loss_f_none_w(inputs, target_bce)
    loss_sum = loss_f_sum(inputs, target_bce)
    loss_mean = loss_f_mean(inputs, target_bce)

    # view
    print("\npos_weights: ", pos_w)
    print(loss_none_w, loss_sum, loss_mean)

三 loss_function_2.py

"""

# @brief      :
                5. nn.L1Loss
                6. nn.MSELoss
                7. nn.SmoothL1Loss
                8. nn.PoissonNLLLoss
                9. nn.KLDivLoss
                10. nn.MarginRankingLoss
                11. nn.MultiLabelMarginLoss
                12. nn.SoftMarginLoss
                13. nn.MultiLabelSoftMarginLoss
                14. nn.MultiMarginLoss
                15. nn.TripletMarginLoss
                16. nn.HingeEmbeddingLoss
                17. nn.CosineEmbeddingLoss
                18. nn.CTCLoss
"""

import torch
import torch.nn as nn
import torch.nn.functional as F
import matplotlib.pyplot as plt
import numpy as np
from tools.common_tools import set_seed

set_seed(1)  # 设置随机种子

# ------------------------------------------------- 5 L1 loss ----------------------------------------------
flag = 0
# flag = 1
if flag:

    inputs = torch.ones((2, 2))
    target = torch.ones((2, 2)) * 3

    loss_f = nn.L1Loss(reduction='none')
    loss = loss_f(inputs, target)

    print("input:{}\ntarget:{}\nL1 loss:{}".format(inputs, target, loss))

# ------------------------------------------------- 6 MSE loss ----------------------------------------------

    loss_f_mse = nn.MSELoss(reduction='none')
    loss_mse = loss_f_mse(inputs, target)

    print("MSE loss:{}".format(loss_mse))

# ------------------------------------------------- 7 Smooth L1 loss ----------------------------------------------
flag = 0
# flag = 1
if flag:
    inputs = torch.linspace(-3, 3, steps=500)
    target = torch.zeros_like(inputs)

    loss_f = nn.SmoothL1Loss(reduction='none')

    loss_smooth = loss_f(inputs, target)

    loss_l1 = np.abs(inputs.numpy())

    plt.plot(inputs.numpy(), loss_smooth.numpy(), label='Smooth L1 Loss')
    plt.plot(inputs.numpy(), loss_l1, label='L1 loss')
    plt.xlabel('x_i - y_i')
    plt.ylabel('loss value')
    plt.legend()
    plt.grid()
    plt.show()


# ------------------------------------------------- 8 Poisson NLL Loss ----------------------------------------------
flag = 0
# flag = 1
if flag:

    inputs = torch.randn((2, 2))
    target = torch.randn((2, 2))

    loss_f = nn.PoissonNLLLoss(log_input=True, full=False, reduction='none')
    loss = loss_f(inputs, target)
    print("input:{}\ntarget:{}\nPoisson NLL loss:{}".format(inputs, target, loss))

# --------------------------------- compute by hand
flag = 0
# flag = 1
if flag:

    idx = 0

    loss_1 = torch.exp(inputs[idx, idx]) - target[idx, idx]*inputs[idx, idx]

    print("第一个元素loss:", loss_1)


# ------------------------------------------------- 9 KL Divergence Loss ----------------------------------------------
flag = 0
# flag = 1
if flag:

    inputs = torch.tensor([[0.5, 0.3, 0.2], [0.2, 0.3, 0.5]])
    inputs_log = torch.log(inputs)
    target = torch.tensor([[0.9, 0.05, 0.05], [0.1, 0.7, 0.2]], dtype=torch.float)

    loss_f_none = nn.KLDivLoss(reduction='none')
    loss_f_mean = nn.KLDivLoss(reduction='mean')
    loss_f_bs_mean = nn.KLDivLoss(reduction='batchmean')

    loss_none = loss_f_none(inputs, target)
    loss_mean = loss_f_mean(inputs, target)
    loss_bs_mean = loss_f_bs_mean(inputs, target)

    print("loss_none:\n{}\nloss_mean:\n{}\nloss_bs_mean:\n{}".format(loss_none, loss_mean, loss_bs_mean))

# --------------------------------- compute by hand
flag = 0
# flag = 1
if flag:

    idx = 0

    loss_1 = target[idx, idx] * (torch.log(target[idx, idx]) - inputs[idx, idx])

    print("第一个元素loss:", loss_1)


# ---------------------------------------------- 10 Margin Ranking Loss --------------------------------------------
flag = 0
# flag = 1
if flag:

    x1 = torch.tensor([[1], [2], [3]], dtype=torch.float)
    x2 = torch.tensor([[2], [2], [2]], dtype=torch.float)

    target = torch.tensor([1, 1, -1], dtype=torch.float)

    loss_f_none = nn.MarginRankingLoss(margin=0, reduction='none')

    loss = loss_f_none(x1, x2, target)

    print(loss)

# ---------------------------------------------- 11 Multi Label Margin Loss -----------------------------------------
flag = 0
# flag = 1
if flag:

    x = torch.tensor([[0.1, 0.2, 0.4, 0.8]])
    y = torch.tensor([[0, 3, -1, -1]], dtype=torch.long)

    loss_f = nn.MultiLabelMarginLoss(reduction='none')

    loss = loss_f(x, y)

    print(loss)

# --------------------------------- compute by hand
flag = 0
# flag = 1
if flag:

    x = x[0]
    item_1 = (1-(x[0] - x[1])) + (1 - (x[0] - x[2]))    # [0]
    item_2 = (1-(x[3] - x[1])) + (1 - (x[3] - x[2]))    # [3]

    loss_h = (item_1 + item_2) / x.shape[0]

    print(loss_h)

# ---------------------------------------------- 12 SoftMargin Loss -----------------------------------------
flag = 0
# flag = 1
if flag:

    inputs = torch.tensor([[0.3, 0.7], [0.5, 0.5]])
    target = torch.tensor([[-1, 1], [1, -1]], dtype=torch.float)

    loss_f = nn.SoftMarginLoss(reduction='none')

    loss = loss_f(inputs, target)

    print("SoftMargin: ", loss)

# --------------------------------- compute by hand
flag = 0
# flag = 1
if flag:

    idx = 0

    inputs_i = inputs[idx, idx]
    target_i = target[idx, idx]

    loss_h = np.log(1 + np.exp(-target_i * inputs_i))

    print(loss_h)


# ---------------------------------------------- 13 MultiLabel SoftMargin Loss -----------------------------------------
flag = 0
# flag = 1
if flag:

    inputs = torch.tensor([[0.3, 0.7, 0.8]])
    target = torch.tensor([[0, 1, 1]], dtype=torch.float)

    loss_f = nn.MultiLabelSoftMarginLoss(reduction='none')

    loss = loss_f(inputs, target)

    print("MultiLabel SoftMargin: ", loss)

# --------------------------------- compute by hand
flag = 0
# flag = 1
if flag:

    i_0 = torch.log(torch.exp(-inputs[0, 0]) / (1 + torch.exp(-inputs[0, 0])))

    i_1 = torch.log(1 / (1 + torch.exp(-inputs[0, 1])))
    i_2 = torch.log(1 / (1 + torch.exp(-inputs[0, 2])))

    loss_h = (i_0 + i_1 + i_2) / -3

    print(loss_h)

# ---------------------------------------------- 14 Multi Margin Loss -----------------------------------------
flag = 0
# flag = 1
if flag:

    x = torch.tensor([[0.1, 0.2, 0.7], [0.2, 0.5, 0.3]])
    y = torch.tensor([1, 2], dtype=torch.long)

    loss_f = nn.MultiMarginLoss(reduction='none')

    loss = loss_f(x, y)

    print("Multi Margin Loss: ", loss)

# --------------------------------- compute by hand
flag = 0
# flag = 1
if flag:

    x = x[0]
    margin = 1

    i_0 = margin - (x[1] - x[0])
    # i_1 = margin - (x[1] - x[1])
    i_2 = margin - (x[1] - x[2])

    loss_h = (i_0 + i_2) / x.shape[0]

    print(loss_h)

# ---------------------------------------------- 15 Triplet Margin Loss -----------------------------------------
flag = 0
# flag = 1
if flag:

    anchor = torch.tensor([[1.]])
    pos = torch.tensor([[2.]])
    neg = torch.tensor([[0.5]])

    loss_f = nn.TripletMarginLoss(margin=1.0, p=1)

    loss = loss_f(anchor, pos, neg)

    print("Triplet Margin Loss", loss)

# --------------------------------- compute by hand
flag = 0
# flag = 1
if flag:

    margin = 1
    a, p, n = anchor[0], pos[0], neg[0]

    d_ap = torch.abs(a-p)
    d_an = torch.abs(a-n)

    loss = d_ap - d_an + margin

    print(loss)

# ---------------------------------------------- 16 Hinge Embedding Loss -----------------------------------------
flag = 0
# flag = 1
if flag:

    inputs = torch.tensor([[1., 0.8, 0.5]])
    target = torch.tensor([[1, 1, -1]])

    loss_f = nn.HingeEmbeddingLoss(margin=1, reduction='none')

    loss = loss_f(inputs, target)

    print("Hinge Embedding Loss", loss)

# --------------------------------- compute by hand
flag = 0
# flag = 1
if flag:
    margin = 1.
    loss = max(0, margin - inputs.numpy()[0, 2])

    print(loss)


# ---------------------------------------------- 17 Cosine Embedding Loss -----------------------------------------
flag = 0
# flag = 1
if flag:

    x1 = torch.tensor([[0.3, 0.5, 0.7], [0.3, 0.5, 0.7]])
    x2 = torch.tensor([[0.1, 0.3, 0.5], [0.1, 0.3, 0.5]])

    target = torch.tensor([[1, -1]], dtype=torch.float)

    loss_f = nn.CosineEmbeddingLoss(margin=0., reduction='none')

    loss = loss_f(x1, x2, target)

    print("Cosine Embedding Loss", loss)

# --------------------------------- compute by hand
flag = 0
# flag = 1
if flag:
    margin = 0.

    def cosine(a, b):
        numerator = torch.dot(a, b)
        denominator = torch.norm(a, 2) * torch.norm(b, 2)
        return float(numerator/denominator)

    l_1 = 1 - (cosine(x1[0], x2[0]))

    l_2 = max(0, cosine(x1[0], x2[0]))

    print(l_1, l_2)


# ---------------------------------------------- 18 CTC Loss -----------------------------------------
# flag = 0
flag = 1
if flag:
    T = 50      # Input sequence length
    C = 20      # Number of classes (including blank)
    N = 16      # Batch size
    S = 30      # Target sequence length of longest target in batch
    S_min = 10  # Minimum target length, for demonstration purposes

    # Initialize random batch of input vectors, for *size = (T,N,C)
    inputs = torch.randn(T, N, C).log_softmax(2).detach().requires_grad_()

    # Initialize random batch of targets (0 = blank, 1:C = classes)
    target = torch.randint(low=1, high=C, size=(N, S), dtype=torch.long)

    input_lengths = torch.full(size=(N,), fill_value=T, dtype=torch.long)
    target_lengths = torch.randint(low=S_min, high=S, size=(N,), dtype=torch.long)

    ctc_loss = nn.CTCLoss()
    loss = ctc_loss(inputs, target, input_lengths, target_lengths)

    print("CTC loss: ", loss)