Binary DenseNet 121 分类器仅以 >0.5 的概率预测阳性
Binary DenseNet 121 Classifier only predicting positive with probability >0.5
我从这个 github repo 借用代码来训练 DenseNet-121 [https://github.com/gaetandi/cheXpert/blob/master/cheXpert_final.ipynb][1]
github 代码用于 CheXpert 胸部 X-ray 数据集上的 14 class class化。我已经针对二进制 classification 对其进行了修改。
# initialize and load the model
pathModel = "/ds2/images/model_ones_2epoch_densenet.tar"#"m-epoch0-07032019-213933.pth.tar"
我初始化了 14 class 模型，这样我就可以使用预训练的权重：
model = DenseNet121(nnClassCount).cuda()
model = torch.nn.DataParallel(model).cuda()
modelCheckpoint = torch.load(pathModel)
model.load_state_dict(modelCheckpoint['state_dict'])
然后转为二进制class化：
nnClassCount = 1
model.module.densenet121.classifier = nn.Sequential(
nn.Linear(1024, nnClassCount),
nn.Sigmoid()
).cuda()
model = torch.nn.DataParallel(model).cuda()
然后通过以下方式训练：
batch, losst, losse = CheXpertTrainer.train(model, dataLoaderTrain, dataLoaderVal, nnClassCount, 100, timestampLaunch, checkpoint = None, weight_path = weight_path)
我的训练数据位于一个 2 列的 csv 中，第 headers 列（'Path' 和 'Class-Positive'），路径位置在第一列，0 或 1 在第二列第二栏。我在编译训练列表时使用了过采样，因此 csv 中的路径大约是 0 和 1 之间的 50/50 分割......随机排列。
我使用 livelossplot 来监控 training/validation 损失和准确性。我的损失图看起来符合预期，但准确度图在 0.5 左右趋于平坦（如果网络表示其 100% 为正或负，则考虑到 50/50 的数据，这是有道理的）。我假设我在做预测时做错了什么，但也许训练中的某些地方不正确。
对于预测和概率，我是 运行:
varOutput = model(varInput)
_, preds = torch.max(varOutput, 1)
print('varshape: ',varOutput.shape)
probs = torch.sigmoid(varOutput)
*我的问题：preds 都显示为 0，probs 都高于 0.5 *
这是来自 github 的初始代码：
import os
import numpy as np
import time
import sys
import csv
import cv2
import matplotlib.pyplot as plt
import torch
import torch.nn as nn
import torch.backends.cudnn as cudnn
import torchvision
import torchvision.transforms as transforms
import torch.optim as optim
import torch.nn.functional as tfunc
from torch.utils.data import Dataset
from torch.utils.data.dataset import random_split
from torch.utils.data import DataLoader
from torch.optim.lr_scheduler import ReduceLROnPlateau
from PIL import Image
import torch.nn.functional as func
from sklearn.metrics.ranking import roc_auc_score
import sklearn.metrics as metrics
import random
use_gpu = torch.cuda.is_available()
# Paths to the files with training, and validation sets.
# Each file contains pairs (path to image, output vector)
pathFileTrain = '../CheXpert-v1.0-small/train.csv'
pathFileValid = '../CheXpert-v1.0-small/valid.csv'
# Neural network parameters:
nnIsTrained = False #pre-trained using ImageNet
nnClassCount = 14 #dimension of the output
# Training settings: batch size, maximum number of epochs
trBatchSize = 64
trMaxEpoch = 3
# Parameters related to image transforms: size of the down-scaled image, cropped image
imgtransResize = (320, 320)
imgtransCrop = 224
# Class names
class_names = ['No Finding', 'Enlarged Cardiomediastinum', 'Cardiomegaly', 'Lung Opacity',
'Lung Lesion', 'Edema', 'Consolidation', 'Pneumonia', 'Atelectasis', 'Pneumothorax',
'Pleural Effusion', 'Pleural Other', 'Fracture', 'Support Devices']
class CheXpertDataSet(Dataset):
def __init__(self, image_list_file, transform=None, policy="ones"):
"""
image_list_file: path to the file containing images with corresponding labels.
transform: optional transform to be applied on a sample.
Upolicy: name the policy with regard to the uncertain labels
"""
image_names = []
labels = []
with open(image_list_file, "r") as f:
csvReader = csv.reader(f)
next(csvReader, None)
k=0
for line in csvReader:
k+=1
image_name= line[0]
label = line[5:]
for i in range(14):
if label[i]:
a = float(label[i])
if a == 1:
label[i] = 1
elif a == -1:
if policy == "ones":
label[i] = 1
elif policy == "zeroes":
label[i] = 0
else:
label[i] = 0
else:
label[i] = 0
else:
label[i] = 0
image_names.append('../' + image_name)
labels.append(label)
self.image_names = image_names
self.labels = labels
self.transform = transform
def __getitem__(self, index):
"""Take the index of item and returns the image and its labels"""
image_name = self.image_names[index]
image = Image.open(image_name).convert('RGB')
label = self.labels[index]
if self.transform is not None:
image = self.transform(image)
return image, torch.FloatTensor(label)
def __len__(self):
return len(self.image_names)
#TRANSFORM DATA
normalize = transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
transformList = []
#transformList.append(transforms.Resize(imgtransCrop))
transformList.append(transforms.RandomResizedCrop(imgtransCrop))
transformList.append(transforms.RandomHorizontalFlip())
transformList.append(transforms.ToTensor())
transformList.append(normalize)
transformSequence=transforms.Compose(transformList)
#LOAD DATASET
dataset = CheXpertDataSet(pathFileTrain ,transformSequence, policy="ones")
datasetTest, datasetTrain = random_split(dataset, [500, len(dataset) - 500])
datasetValid = CheXpertDataSet(pathFileValid, transformSequence)
#Problèmes de l'overlapping de patients et du transform identique ?
dataLoaderTrain = DataLoader(dataset=datasetTrain, batch_size=trBatchSize, shuffle=True, num_workers=24, pin_memory=True)
dataLoaderVal = DataLoader(dataset=datasetValid, batch_size=trBatchSize, shuffle=False, num_workers=24, pin_memory=True)
dataLoaderTest = DataLoader(dataset=datasetTest, num_workers=24, pin_memory=True)
class CheXpertTrainer():
def train (model, dataLoaderTrain, dataLoaderVal, nnClassCount, trMaxEpoch, launchTimestamp, checkpoint):
#SETTINGS: OPTIMIZER & SCHEDULER
optimizer = optim.Adam (model.parameters(), lr=0.0001, betas=(0.9, 0.999), eps=1e-08, weight_decay=1e-5)
#SETTINGS: LOSS
loss = torch.nn.BCELoss(size_average = True)
#LOAD CHECKPOINT
if checkpoint != None and use_gpu:
modelCheckpoint = torch.load(checkpoint)
model.load_state_dict(modelCheckpoint['state_dict'])
optimizer.load_state_dict(modelCheckpoint['optimizer'])
#TRAIN THE NETWORK
lossMIN = 100000
for epochID in range(0, trMaxEpoch):
timestampTime = time.strftime("%H%M%S")
timestampDate = time.strftime("%d%m%Y")
timestampSTART = timestampDate + '-' + timestampTime
batchs, losst, losse = CheXpertTrainer.epochTrain(model, dataLoaderTrain, optimizer, trMaxEpoch, nnClassCount, loss)
lossVal = CheXpertTrainer.epochVal(model, dataLoaderVal, optimizer, trMaxEpoch, nnClassCount, loss)
timestampTime = time.strftime("%H%M%S")
timestampDate = time.strftime("%d%m%Y")
timestampEND = timestampDate + '-' + timestampTime
if lossVal < lossMIN:
lossMIN = lossVal
torch.save({'epoch': epochID + 1, 'state_dict': model.state_dict(), 'best_loss': lossMIN, 'optimizer' : optimizer.state_dict()}, 'm-epoch'+str(epochID)+'-' + launchTimestamp + '.pth.tar')
print ('Epoch [' + str(epochID + 1) + '] [save] [' + timestampEND + '] loss= ' + str(lossVal))
else:
print ('Epoch [' + str(epochID + 1) + '] [----] [' + timestampEND + '] loss= ' + str(lossVal))
return batchs, losst, losse
#--------------------------------------------------------------------------------
def epochTrain(model, dataLoader, optimizer, epochMax, classCount, loss):
batch = []
losstrain = []
losseval = []
model.train()
for batchID, (varInput, target) in enumerate(dataLoaderTrain):
varTarget = target.cuda(non_blocking = True)
#varTarget = target.cuda()
varOutput = model(varInput)
lossvalue = loss(varOutput, varTarget)
optimizer.zero_grad()
lossvalue.backward()
optimizer.step()
l = lossvalue.item()
losstrain.append(l)
if batchID%35==0:
print(batchID//35, "% batches computed")
#Fill three arrays to see the evolution of the loss
batch.append(batchID)
le = CheXpertTrainer.epochVal(model, dataLoaderVal, optimizer, trMaxEpoch, nnClassCount, loss).item()
losseval.append(le)
print(batchID)
print(l)
print(le)
return batch, losstrain, losseval
#--------------------------------------------------------------------------------
def epochVal(model, dataLoader, optimizer, epochMax, classCount, loss):
model.eval()
lossVal = 0
lossValNorm = 0
with torch.no_grad():
for i, (varInput, target) in enumerate(dataLoaderVal):
target = target.cuda(non_blocking = True)
varOutput = model(varInput)
losstensor = loss(varOutput, target)
lossVal += losstensor
lossValNorm += 1
outLoss = lossVal / lossValNorm
return outLoss
#--------------------------------------------------------------------------------
#---- Computes area under ROC curve
#---- dataGT - ground truth data
#---- dataPRED - predicted data
#---- classCount - number of classes
def computeAUROC (dataGT, dataPRED, classCount):
outAUROC = []
datanpGT = dataGT.cpu().numpy()
datanpPRED = dataPRED.cpu().numpy()
for i in range(classCount):
try:
outAUROC.append(roc_auc_score(datanpGT[:, i], datanpPRED[:, i]))
except ValueError:
pass
return outAUROC
#--------------------------------------------------------------------------------
def test(model, dataLoaderTest, nnClassCount, checkpoint, class_names):
cudnn.benchmark = True
if checkpoint != None and use_gpu:
modelCheckpoint = torch.load(checkpoint)
model.load_state_dict(modelCheckpoint['state_dict'])
if use_gpu:
outGT = torch.FloatTensor().cuda()
outPRED = torch.FloatTensor().cuda()
else:
outGT = torch.FloatTensor()
outPRED = torch.FloatTensor()
model.eval()
with torch.no_grad():
for i, (input, target) in enumerate(dataLoaderTest):
target = target.cuda()
outGT = torch.cat((outGT, target), 0).cuda()
bs, c, h, w = input.size()
varInput = input.view(-1, c, h, w)
out = model(varInput)
outPRED = torch.cat((outPRED, out), 0)
aurocIndividual = CheXpertTrainer.computeAUROC(outGT, outPRED, nnClassCount)
aurocMean = np.array(aurocIndividual).mean()
print ('AUROC mean ', aurocMean)
for i in range (0, len(aurocIndividual)):
print (class_names[i], ' ', aurocIndividual[i])
return outGT, outPRED
class DenseNet121(nn.Module):
"""Model modified.
The architecture of our model is the same as standard DenseNet121
except the classifier layer which has an additional sigmoid function.
"""
def __init__(self, out_size):
super(DenseNet121, self).__init__()
self.densenet121 = torchvision.models.densenet121(pretrained=True)
num_ftrs = self.densenet121.classifier.in_features
self.densenet121.classifier = nn.Sequential(
nn.Linear(num_ftrs, out_size),
nn.Sigmoid()
)
def forward(self, x):
x = self.densenet121(x)
return x
# initialize and load the model
model = DenseNet121(nnClassCount).cuda()
model = torch.nn.DataParallel(model).cuda()
timestampTime = time.strftime("%H%M%S")
timestampDate = time.strftime("%d%m%Y")
timestampLaunch = timestampDate + '-' + timestampTime
batch, losst, losse = CheXpertTrainer.train(model, dataLoaderTrain, dataLoaderVal, nnClassCount, trMaxEpoch, timestampLaunch, checkpoint = None)
print("Model trained")
看起来您已经针对二进制 class 化正确调整了训练，但预测并非如此，因为您仍在尝试它，就好像它是一个多 class 预测一样.
您的模型 (varOutput) 的输出大小为 (batch_size, 1)，因为只有一个 class .该维度的最大值将始终为 0，因为这是唯一可用的 class，没有单独的 class 表示 1.
这个 class 代表两种情况（0 和 1），因此您可以认为它是正数 (1) 的概率。要获得 0 或 1 的不同值，您只需使用 0.5 的阈值，因此低于该值的所有内容都会收到 class 0 和高于该 1 的内容。这可以通过 torch.round.[= 轻松完成。 16=]
但是您还有另一个问题，您连续两次应用 sigmoid 函数，一次在 classifier nn.Sigmoid() 中，然后再次 torch.sigmoid(varOutput)。这是有问题的，因为 sigmoid(0) = 0.5，因此你所有的概率都超过 0.5.
你模型的输出已经是概率，剩下的就是四舍五入了：
probs = model(varInput)
# The .squeeze(1) is to get rid of the singular class dimension
preds = torch.round(probs).squeeze(1)
我从这个 github repo 借用代码来训练 DenseNet-121 [https://github.com/gaetandi/cheXpert/blob/master/cheXpert_final.ipynb][1]
github 代码用于 CheXpert 胸部 X-ray 数据集上的 14 class class化。我已经针对二进制 classification 对其进行了修改。
# initialize and load the model
pathModel = "/ds2/images/model_ones_2epoch_densenet.tar"#"m-epoch0-07032019-213933.pth.tar"
我初始化了 14 class 模型，这样我就可以使用预训练的权重：
model = DenseNet121(nnClassCount).cuda()
model = torch.nn.DataParallel(model).cuda()
modelCheckpoint = torch.load(pathModel)
model.load_state_dict(modelCheckpoint['state_dict'])
然后转为二进制class化：
nnClassCount = 1
model.module.densenet121.classifier = nn.Sequential(
nn.Linear(1024, nnClassCount),
nn.Sigmoid()
).cuda()
model = torch.nn.DataParallel(model).cuda()
然后通过以下方式训练：
batch, losst, losse = CheXpertTrainer.train(model, dataLoaderTrain, dataLoaderVal, nnClassCount, 100, timestampLaunch, checkpoint = None, weight_path = weight_path)
我的训练数据位于一个 2 列的 csv 中，第 headers 列（'Path' 和 'Class-Positive'），路径位置在第一列，0 或 1 在第二列第二栏。我在编译训练列表时使用了过采样，因此 csv 中的路径大约是 0 和 1 之间的 50/50 分割......随机排列。
我使用 livelossplot 来监控 training/validation 损失和准确性。我的损失图看起来符合预期，但准确度图在 0.5 左右趋于平坦（如果网络表示其 100% 为正或负，则考虑到 50/50 的数据，这是有道理的）。我假设我在做预测时做错了什么，但也许训练中的某些地方不正确。
对于预测和概率，我是 运行:
varOutput = model(varInput)
_, preds = torch.max(varOutput, 1)
print('varshape: ',varOutput.shape)
probs = torch.sigmoid(varOutput)
*我的问题：preds 都显示为 0，probs 都高于 0.5 *
这是来自 github 的初始代码：
import os
import numpy as np
import time
import sys
import csv
import cv2
import matplotlib.pyplot as plt
import torch
import torch.nn as nn
import torch.backends.cudnn as cudnn
import torchvision
import torchvision.transforms as transforms
import torch.optim as optim
import torch.nn.functional as tfunc
from torch.utils.data import Dataset
from torch.utils.data.dataset import random_split
from torch.utils.data import DataLoader
from torch.optim.lr_scheduler import ReduceLROnPlateau
from PIL import Image
import torch.nn.functional as func
from sklearn.metrics.ranking import roc_auc_score
import sklearn.metrics as metrics
import random
use_gpu = torch.cuda.is_available()
# Paths to the files with training, and validation sets.
# Each file contains pairs (path to image, output vector)
pathFileTrain = '../CheXpert-v1.0-small/train.csv'
pathFileValid = '../CheXpert-v1.0-small/valid.csv'
# Neural network parameters:
nnIsTrained = False #pre-trained using ImageNet
nnClassCount = 14 #dimension of the output
# Training settings: batch size, maximum number of epochs
trBatchSize = 64
trMaxEpoch = 3
# Parameters related to image transforms: size of the down-scaled image, cropped image
imgtransResize = (320, 320)
imgtransCrop = 224
# Class names
class_names = ['No Finding', 'Enlarged Cardiomediastinum', 'Cardiomegaly', 'Lung Opacity',
'Lung Lesion', 'Edema', 'Consolidation', 'Pneumonia', 'Atelectasis', 'Pneumothorax',
'Pleural Effusion', 'Pleural Other', 'Fracture', 'Support Devices']
class CheXpertDataSet(Dataset):
def __init__(self, image_list_file, transform=None, policy="ones"):
"""
image_list_file: path to the file containing images with corresponding labels.
transform: optional transform to be applied on a sample.
Upolicy: name the policy with regard to the uncertain labels
"""
image_names = []
labels = []
with open(image_list_file, "r") as f:
csvReader = csv.reader(f)
next(csvReader, None)
k=0
for line in csvReader:
k+=1
image_name= line[0]
label = line[5:]
for i in range(14):
if label[i]:
a = float(label[i])
if a == 1:
label[i] = 1
elif a == -1:
if policy == "ones":
label[i] = 1
elif policy == "zeroes":
label[i] = 0
else:
label[i] = 0
else:
label[i] = 0
else:
label[i] = 0
image_names.append('../' + image_name)
labels.append(label)
self.image_names = image_names
self.labels = labels
self.transform = transform
def __getitem__(self, index):
"""Take the index of item and returns the image and its labels"""
image_name = self.image_names[index]
image = Image.open(image_name).convert('RGB')
label = self.labels[index]
if self.transform is not None:
image = self.transform(image)
return image, torch.FloatTensor(label)
def __len__(self):
return len(self.image_names)
#TRANSFORM DATA
normalize = transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
transformList = []
#transformList.append(transforms.Resize(imgtransCrop))
transformList.append(transforms.RandomResizedCrop(imgtransCrop))
transformList.append(transforms.RandomHorizontalFlip())
transformList.append(transforms.ToTensor())
transformList.append(normalize)
transformSequence=transforms.Compose(transformList)
#LOAD DATASET
dataset = CheXpertDataSet(pathFileTrain ,transformSequence, policy="ones")
datasetTest, datasetTrain = random_split(dataset, [500, len(dataset) - 500])
datasetValid = CheXpertDataSet(pathFileValid, transformSequence)
#Problèmes de l'overlapping de patients et du transform identique ?
dataLoaderTrain = DataLoader(dataset=datasetTrain, batch_size=trBatchSize, shuffle=True, num_workers=24, pin_memory=True)
dataLoaderVal = DataLoader(dataset=datasetValid, batch_size=trBatchSize, shuffle=False, num_workers=24, pin_memory=True)
dataLoaderTest = DataLoader(dataset=datasetTest, num_workers=24, pin_memory=True)
class CheXpertTrainer():
def train (model, dataLoaderTrain, dataLoaderVal, nnClassCount, trMaxEpoch, launchTimestamp, checkpoint):
#SETTINGS: OPTIMIZER & SCHEDULER
optimizer = optim.Adam (model.parameters(), lr=0.0001, betas=(0.9, 0.999), eps=1e-08, weight_decay=1e-5)
#SETTINGS: LOSS
loss = torch.nn.BCELoss(size_average = True)
#LOAD CHECKPOINT
if checkpoint != None and use_gpu:
modelCheckpoint = torch.load(checkpoint)
model.load_state_dict(modelCheckpoint['state_dict'])
optimizer.load_state_dict(modelCheckpoint['optimizer'])
#TRAIN THE NETWORK
lossMIN = 100000
for epochID in range(0, trMaxEpoch):
timestampTime = time.strftime("%H%M%S")
timestampDate = time.strftime("%d%m%Y")
timestampSTART = timestampDate + '-' + timestampTime
batchs, losst, losse = CheXpertTrainer.epochTrain(model, dataLoaderTrain, optimizer, trMaxEpoch, nnClassCount, loss)
lossVal = CheXpertTrainer.epochVal(model, dataLoaderVal, optimizer, trMaxEpoch, nnClassCount, loss)
timestampTime = time.strftime("%H%M%S")
timestampDate = time.strftime("%d%m%Y")
timestampEND = timestampDate + '-' + timestampTime
if lossVal < lossMIN:
lossMIN = lossVal
torch.save({'epoch': epochID + 1, 'state_dict': model.state_dict(), 'best_loss': lossMIN, 'optimizer' : optimizer.state_dict()}, 'm-epoch'+str(epochID)+'-' + launchTimestamp + '.pth.tar')
print ('Epoch [' + str(epochID + 1) + '] [save] [' + timestampEND + '] loss= ' + str(lossVal))
else:
print ('Epoch [' + str(epochID + 1) + '] [----] [' + timestampEND + '] loss= ' + str(lossVal))
return batchs, losst, losse
#--------------------------------------------------------------------------------
def epochTrain(model, dataLoader, optimizer, epochMax, classCount, loss):
batch = []
losstrain = []
losseval = []
model.train()
for batchID, (varInput, target) in enumerate(dataLoaderTrain):
varTarget = target.cuda(non_blocking = True)
#varTarget = target.cuda()
varOutput = model(varInput)
lossvalue = loss(varOutput, varTarget)
optimizer.zero_grad()
lossvalue.backward()
optimizer.step()
l = lossvalue.item()
losstrain.append(l)
if batchID%35==0:
print(batchID//35, "% batches computed")
#Fill three arrays to see the evolution of the loss
batch.append(batchID)
le = CheXpertTrainer.epochVal(model, dataLoaderVal, optimizer, trMaxEpoch, nnClassCount, loss).item()
losseval.append(le)
print(batchID)
print(l)
print(le)
return batch, losstrain, losseval
#--------------------------------------------------------------------------------
def epochVal(model, dataLoader, optimizer, epochMax, classCount, loss):
model.eval()
lossVal = 0
lossValNorm = 0
with torch.no_grad():
for i, (varInput, target) in enumerate(dataLoaderVal):
target = target.cuda(non_blocking = True)
varOutput = model(varInput)
losstensor = loss(varOutput, target)
lossVal += losstensor
lossValNorm += 1
outLoss = lossVal / lossValNorm
return outLoss
#--------------------------------------------------------------------------------
#---- Computes area under ROC curve
#---- dataGT - ground truth data
#---- dataPRED - predicted data
#---- classCount - number of classes
def computeAUROC (dataGT, dataPRED, classCount):
outAUROC = []
datanpGT = dataGT.cpu().numpy()
datanpPRED = dataPRED.cpu().numpy()
for i in range(classCount):
try:
outAUROC.append(roc_auc_score(datanpGT[:, i], datanpPRED[:, i]))
except ValueError:
pass
return outAUROC
#--------------------------------------------------------------------------------
def test(model, dataLoaderTest, nnClassCount, checkpoint, class_names):
cudnn.benchmark = True
if checkpoint != None and use_gpu:
modelCheckpoint = torch.load(checkpoint)
model.load_state_dict(modelCheckpoint['state_dict'])
if use_gpu:
outGT = torch.FloatTensor().cuda()
outPRED = torch.FloatTensor().cuda()
else:
outGT = torch.FloatTensor()
outPRED = torch.FloatTensor()
model.eval()
with torch.no_grad():
for i, (input, target) in enumerate(dataLoaderTest):
target = target.cuda()
outGT = torch.cat((outGT, target), 0).cuda()
bs, c, h, w = input.size()
varInput = input.view(-1, c, h, w)
out = model(varInput)
outPRED = torch.cat((outPRED, out), 0)
aurocIndividual = CheXpertTrainer.computeAUROC(outGT, outPRED, nnClassCount)
aurocMean = np.array(aurocIndividual).mean()
print ('AUROC mean ', aurocMean)
for i in range (0, len(aurocIndividual)):
print (class_names[i], ' ', aurocIndividual[i])
return outGT, outPRED
class DenseNet121(nn.Module):
"""Model modified.
The architecture of our model is the same as standard DenseNet121
except the classifier layer which has an additional sigmoid function.
"""
def __init__(self, out_size):
super(DenseNet121, self).__init__()
self.densenet121 = torchvision.models.densenet121(pretrained=True)
num_ftrs = self.densenet121.classifier.in_features
self.densenet121.classifier = nn.Sequential(
nn.Linear(num_ftrs, out_size),
nn.Sigmoid()
)
def forward(self, x):
x = self.densenet121(x)
return x
# initialize and load the model
model = DenseNet121(nnClassCount).cuda()
model = torch.nn.DataParallel(model).cuda()
timestampTime = time.strftime("%H%M%S")
timestampDate = time.strftime("%d%m%Y")
timestampLaunch = timestampDate + '-' + timestampTime
batch, losst, losse = CheXpertTrainer.train(model, dataLoaderTrain, dataLoaderVal, nnClassCount, trMaxEpoch, timestampLaunch, checkpoint = None)
print("Model trained")
看起来您已经针对二进制 class 化正确调整了训练，但预测并非如此，因为您仍在尝试它，就好像它是一个多 class 预测一样.
您的模型 (varOutput) 的输出大小为 (batch_size, 1)，因为只有一个 class .该维度的最大值将始终为 0，因为这是唯一可用的 class，没有单独的 class 表示 1.
这个 class 代表两种情况（0 和 1），因此您可以认为它是正数 (1) 的概率。要获得 0 或 1 的不同值，您只需使用 0.5 的阈值，因此低于该值的所有内容都会收到 class 0 和高于该 1 的内容。这可以通过 torch.round.[= 轻松完成。 16=]
但是您还有另一个问题，您连续两次应用 sigmoid 函数，一次在 classifier nn.Sigmoid() 中，然后再次 torch.sigmoid(varOutput)。这是有问题的，因为 sigmoid(0) = 0.5，因此你所有的概率都超过 0.5.
你模型的输出已经是概率，剩下的就是四舍五入了：
probs = model(varInput)
# The .squeeze(1) is to get rid of the singular class dimension
preds = torch.round(probs).squeeze(1)