def predict(self, test_images):
self.eval()
count = test_images.shape[0]
result_np = []
for idx in range(0, count):
img = test_images[idx, :, :, :]
img = np.expand_dims(img, axis=0)
img = torch.Tensor(img).permute(0, 3, 1, 2).to(device)
pred = self(img)
pred_np = pred.cpu().detach().numpy()
for elem in pred_np:
result_np.append(elem)
return result_np
网络结构是VGG-19,参考我的源代码。
像这样的架构:
class VGG(object):
def __init__(self):
...
def train(self, train_images, valid_images):
train_dataset = torch.utils.data.Dataset(train_images)
valid_dataset = torch.utils.data.Dataset(valid_images)
trainloader = torch.utils.data.DataLoader(train_dataset)
validloader = torch.utils.data.DataLoader(valid_dataset)
self.optimizer = Adam(...)
self.criterion = CrossEntropyLoss(...)
for epoch in range(0, epochs):
...
self.evaluate(validloader, model=self, criterion=self.criterion)
...
def evaluate(self, dataloader, model, criterion):
model.eval()
for i, sample in enumerate(dataloader):
...
def predict(self, test_images):
...
if __name__ == "__main__":
network = VGG()
trainset, validset = get_dataset()
testset = get_test_dataset()
network.train(trainset, validset)
result = network.predict(testset)