print()
time_elapsed = time.time() - since
print('Training complete in {:.0f}m {:.0f}s'.format(
time_elapsed // 60, time_elapsed % 60))
print('Best val Acc: {:4f}'.format(best_acc))
# load best model weights
model.load_state_dict(best_model_wts)
return model
from torchsample.callbacks import ReduceLROnPlateau
model_ft = resnet3.resnet182(pretrained=True)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 2)
model_ft.avgpool = nn.AdaptiveAvgPool2d(1)
ct = 0
for child in model_ft.children():
ct += 1
if ct < 0:
for param in child.parameters():
param.requires_grad = False
if use_gpu:
model_ft = model_ft.cuda()
criterion = nn.CrossEntropyLoss()
import cv2, torch
import io
from PIL import Image
from torchvision import models, transforms
from torch.autograd import Variable
from torch.nn import functional as F
import numpy as np
import resnet3
import torch.nn.functional as F
import torch.nn as nn
import os
net = resnet3.resnet182(pretrained=True)
num_ftrs = net.fc.in_features
net.fc = nn.Linear(num_ftrs, 2)
net.avgpool = nn.AdaptiveAvgPool2d(1)
net.eval()
resume = 'GD1.pth.tar'
if resume:
if os.path.isfile(resume):
print("=> loading checkpoint '{}'".format(resume))
checkpoint = torch.load(resume)
start_epoch = checkpoint['epoch']
best_prec1 = checkpoint['best_prec1']
net.load_state_dict(checkpoint['state_dict'])
print("=> loaded checkpoint '{}' (epoch {})".format(
resume, checkpoint['epoch']))
finalconv_name = 'layer4'