def train(X, y, epochs=10, batch_size=16):
dataset = IrisDataset(X, y)
num_examples = len(dataset)
loader = torch.utils.data.DataLoader(dataset,
batch_size=batch_size,
shuffle=True)
print(X.shape[1])
model = IrisNet(input_dim=X.shape[1])
optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
criterion = torch.nn.CrossEntropyLoss()
for epoch in range(1, epochs + 1):
num_correct = 0
for i, (inputs, labels) in enumerate(loader):
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs, labels)
num_correct += (labels == outputs.argmax(1)).sum()
loss.backward()
optimizer.step()
print(
f"Finished: {epoch}, accuracy: {round(num_correct.float().numpy() / num_examples, 4) * 100}%"
)
return model
def _main():
dataset = IrisDataset()
plot = Plot(dataset)
for root in plot.roots:
curdoc().add_root(root)
curdoc().title = dataset.name
def test(cls):
from dataset import IrisDataset
from sklearn.model_selection import train_test_split
iris_dataset = IrisDataset()
x_train, x_test, y_train, y_test = \
train_test_split(iris_dataset.data[:100],
iris_dataset.target[:100])
svm = cls(kernel="linear", max_iteration=200)
print(svm.train(x_train, y_train))
print(svm.score(x_test, y_test))
else:
device = torch.device("cpu")
# device=torch.device("cpu") # cudnn报错，用cpu跑
model = model_dict[args.model]
model = model.to(device)
filename = args.load
if not os.path.exists(filename):
print("model path not found !!!")
exit(1)
model.load_state_dict(torch.load(filename))
model = model.to(device)
model.eval()
test_set = IrisDataset(filepath = 'Semantic_Segmentation_Dataset/',\
split = 'test',transform = transform)
testloader = DataLoader(test_set,
batch_size=args.bs,
shuffle=False,
num_workers=0)
# windows下num_workers改成0，源代码为2
counter = 0
os.makedirs('test/labels/', exist_ok=True)
os.makedirs('test/output/', exist_ok=True)
os.makedirs('test/mask/', exist_ok=True)
with torch.no_grad():
for i, batchdata in tqdm(enumerate(testloader), total=len(testloader)):
img, labels, index, x, y = batchdata
#!/usr/bin/python
# -*- encoding: utf8 -*-
from math import exp, log2
import numpy as np
from dataset import IrisDataset
IRIS_DATASET = IrisDataset()
class LogisticRegressionClassifier:
def __init__(self, learning_rate=0.01, max_iteration=200):
self._learning_rate = learning_rate
self._max_iteration = max_iteration
self.weights = None
self.classes = None
@property
def learning_rate(self):
return self._learning_rate
@learning_rate.setter
def learning_rate(self, learning_rate):
self._learning_rate = learning_rate
@property
def max_iteration(self):
return self._max_iteration
@max_iteration.setter
logger.write_summary(str(model.parameters))
except:
print("Torch summary not found !!!")
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer,
'min',
patience=5)
criterion = CrossEntropyLoss2d()
criterion_DICE = GeneralizedDiceLoss(softmax=True, reduction=True)
criterion_SL = SurfaceLoss()
Path2file = args.dataset
train = IrisDataset(filepath=Path2file,
split='train',
transform=transform,
**kwargs)
valid = IrisDataset(filepath=Path2file,
split='validation',
transform=transform,
**kwargs)
trainloader = DataLoader(train,
batch_size=args.bs,
shuffle=True,
num_workers=args.workers)
validloader = DataLoader(valid,
batch_size=args.bs,
shuffle=False,