VGG Pytorch это распределение вероятностей должно добавить до 1? - PullRequest
Новая
       52

VGG Pytorch это распределение вероятностей должно добавить до 1?

0 голосов
/ 10 декабря 2018

Я обучил модель vgg16 предсказывать 102 класса цветов.Однако теперь он работает, когда я пытаюсь понять одно из его предсказаний и чувствую, что оно не работает нормально.

макет модели 

# Imports here
import os
import numpy as np
import torch

import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import json
from pprint import pprint
from scipy import misc

%matplotlib inline

data_dir = 'flower_data'
train_dir = data_dir + '/train'
test_dir = data_dir + '/valid'

json_data=open('cat_to_name.json').read()
main_classes = json.loads(json_data)
main_classes = {int(k):v for k,v in classes.items()}

train_transform_2 = transforms.Compose([transforms.RandomResizedCrop(224), 
                                    transforms.RandomRotation(30),
                                    transforms.RandomHorizontalFlip(),
                                    transforms.ToTensor()])

test_transform_2= transforms.Compose([transforms.RandomResizedCrop(224), 
                                    transforms.ToTensor()])

# TODO: Load the datasets with ImageFolder
train_data = datasets.ImageFolder(train_dir, transform=train_transform_2)
test_data = datasets.ImageFolder(test_dir, transform=test_transform_2)

# define dataloader parameters
batch_size = 20
num_workers=0

# TODO: Using the image datasets and the trainforms, define the dataloaders
train_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size, 
                                        num_workers=num_workers, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size, 
                                        num_workers=num_workers, shuffle=True)

vgg16 = models.vgg16(pretrained=True)

# Freeze training for all "features" layers
for param in vgg16.features.parameters():
    param.requires_grad = False

import torch.nn as nn

n_inputs = vgg16.classifier[6].in_features

# add last linear layer (n_inputs -> 102 flower classes)
# new layers automatically have requires_grad = True
last_layer = nn.Linear(n_inputs, len(classes))

vgg16.classifier[6] = last_layer

import torch.optim as optim

# specify loss function (categorical cross-entropy)
criterion = nn.CrossEntropyLoss()

# specify optimizer (stochastic gradient descent) and learning rate = 0.001
optimizer = optim.SGD(vgg16.classifier.parameters(), lr=0.001)

pre_trained_model=torch.load("model.pt")
new=list(pre_trained_model.items())

my_model_kvpair=vgg16.state_dict()
count=0

for key,value in my_model_kvpair.items():
    layer_name, weights = new[count]      
    my_model_kvpair[key] = weights
    count+=1

# number of epochs to train the model
n_epochs = 6

# initialize tracker for minimum validation loss
valid_loss_min = np.Inf # set initial "min" to infinity

for epoch in range(1, n_epochs+1):

    # keep track of training and validation loss
    train_loss = 0.0
    valid_loss = 0.0

    ###################
    # train the model #
    ###################
    # model by default is set to train
    vgg16.train()

    for batch_i, (data, target) in enumerate(train_loader):
        # clear the gradients of all optimized variables
        optimizer.zero_grad()
        # forward pass: compute predicted outputs by passing inputs to the model
        output = vgg16(data)
        # calculate the batch loss
        loss = criterion(output, target)
        # backward pass: compute gradient of the loss with respect to model parameters
        loss.backward()
        # perform a single optimization step (parameter update)
        optimizer.step()
        # update training loss 
        train_loss += loss.item()

        if batch_i % 20 == 19:    # print training loss every specified number of mini-batches
            print('Epoch %d, Batch %d loss: %.16f' %
                (epoch, batch_i + 1, train_loss / 20))
            train_loss = 0.0

    ######################    
    # validate the model #
    ######################
    vgg16.eval() # prep model for evaluation
    for data, target in test_loader:
        # forward pass: compute predicted outputs by passing inputs to the model
        output = vgg16(data)
        # calculate the loss
        loss = criterion(output, target)
        # update running validation loss 
        valid_loss += loss.item()

    # print training/validation statistics 
    # calculate average loss over an epoch
    train_loss = train_loss/len(train_loader.dataset)
    valid_loss = valid_loss/len(test_loader.dataset)

    print('Epoch: {} \tTraining Loss: {:.6f} \tValidation Loss: {:.6f}'.format(
        epoch+1, 
        train_loss,
        valid_loss
        ))

    # save model if validation loss has decreased
    if valid_loss <= valid_loss_min:
        print('Validation loss decreased ({:.6f} --> {:.6f}).  Saving model ...'.format(
        valid_loss_min,
        valid_loss))
        torch.save(vgg16.state_dict(), 'model.pt')
        valid_loss_min = valid_loss

тестирование на одном изображении 

tensor = torch.from_numpy(test_image)
reshaped = tensor.permute(2, 0, 1).unsqueeze(0)
floatified = reshaped.to(torch.float32) / 255
vgg16(floatified)
>>>
tensor([[ 2.5686, -1.1964, -0.0872, -1.7010, -1.6669, -1.0638,  0.4515,  0.1124,
          0.0166,  0.3156,  1.1699,  1.5374,  1.8720,  2.5184,  2.9046, -0.8241,
         -1.1949, -0.5700,  0.8692, -1.0485,  0.0390, -1.3783, -3.4632, -0.0143,
          1.0986,  0.2667, -1.1127, -0.8515,  0.7759, -0.7528,  1.6366, -0.1170,
         -0.4983, -2.6970,  0.7545,  0.0188,  0.1094,  0.5002,  0.8838, -0.0006,
         -1.7993, -1.3706,  0.4964, -0.3251, -1.7313,  1.8731,  2.4963,  1.1713,
         -1.5726,  1.5476,  3.9576,  0.7388,  0.0228,  0.3947, -1.7237, -1.8350,
         -2.0297,  1.4088, -1.3469,  1.6128, -1.0851,  2.0257,  0.5881,  0.7498,
          0.0738,  2.0592,  1.8034, -0.5468,  1.9512,  0.4534,  0.7746, -1.0465,
         -0.7254,  0.3333, -1.6506, -0.4242,  1.9529, -0.4542,  0.2396, -1.6804,
         -2.7987, -0.6367, -0.3599,  1.0102,  2.6319,  0.8305, -1.4333,  3.3043,
         -0.4021, -0.4877,  0.9125,  0.0607, -1.0326,  1.3186, -2.5861,  0.1211,
         -2.3177, -1.5040,  1.0416,  1.4008,  1.4225, -2.7291]],
       grad_fn=<ThAddmmBackward>)

sum([ 2.5686, -1.1964, -0.0872, -1.7010, -1.6669, -1.0638,  0.4515,  0.1124,
          0.0166,  0.3156,  1.1699,  1.5374,  1.8720,  2.5184,  2.9046, -0.8241,
         -1.1949, -0.5700,  0.8692, -1.0485,  0.0390, -1.3783, -3.4632, -0.0143,
          1.0986,  0.2667, -1.1127, -0.8515,  0.7759, -0.7528,  1.6366, -0.1170,
         -0.4983, -2.6970,  0.7545,  0.0188,  0.1094,  0.5002,  0.8838, -0.0006,
         -1.7993, -1.3706,  0.4964, -0.3251, -1.7313,  1.8731,  2.4963,  1.1713,
         -1.5726,  1.5476,  3.9576,  0.7388,  0.0228,  0.3947, -1.7237, -1.8350,
         -2.0297,  1.4088, -1.3469,  1.6128, -1.0851,  2.0257,  0.5881,  0.7498,
          0.0738,  2.0592,  1.8034, -0.5468,  1.9512,  0.4534,  0.7746, -1.0465,
         -0.7254,  0.3333, -1.6506, -0.4242,  1.9529, -0.4542,  0.2396, -1.6804,
         -2.7987, -0.6367, -0.3599,  1.0102,  2.6319,  0.8305, -1.4333,  3.3043,
         -0.4021, -0.4877,  0.9125,  0.0607, -1.0326,  1.3186, -2.5861,  0.1211,
         -2.3177, -1.5040,  1.0416,  1.4008,  1.4225, -2.7291])
>>>
5.325799999999998

с учетом того, как я тестирую его на одном изображении (а модель, как обычно, обучается и тестируется партиями, она возвращает матрицу прогнозирования, которая, по-видимому, не нормирована или не равна 1.

Это нормально?

1 Ответ

0 голосов
/ 10 декабря 2018

Я не могу с уверенностью сказать, не увидев ваш обучающий код, но, скорее всего, ваша модель была обучена с кросс-энтропийной потерей и, как таковая, выдает logits , а не вероятности класса.Вы можете превратить их в правильные вероятности, применив функцию softmax .

...