from models import ResNet34
from PIL import Image
import torch as t
from torch.autograd import Variable
import matplotlib.pyplot as plt
model = ResNet34.ResNet()
model.load_state_dict(t.load('params99.pth'))
# print('-----model=',model)
model.eval()
img_data = Image.open('/home/cat_and_dog/data/test_imgs/s0009_cat.jpg')
img_data.save('test.png')
print('--img_data=', img_data)
import matplotlib
im = matplotlib.image.imread('/home/cat_and_dog/data/test_imgs/s0009_cat.jpg')
print('---img=', im)
from models import ResNet34
from config import DefaultConfig
from data.dataset import DogCat
from torch.utils.data import Dataset, DataLoader
import torch as t
from torch.autograd import Variable
import matplotlib.pyplot as plt
#from .models.ResNet34 import DogCat
opt = DefaultConfig()
print('----opt=', opt)
lr = opt.lr
print('---opt.train_data_root=', opt.train_data_root)
# step1: models
net = ResNet34.ResNet()
# print('----net=',net)
train_dataset = DogCat(opt.train_data_root, train=True)
val_dataset = DogCat(opt.train_data_root, train=False)
# step2: data set
train_dataloader = DataLoader(train_dataset,
opt.batch_size,
shuffle=True,
num_workers=opt.num_workers)
val_dataloader = DataLoader(val_dataset,
4,
shuffle=True,
num_workers=opt.num_workers)
# step3: target function and optimizer