def main():
model = GoogLeNet(num_classes=num_clazz,
aux_logits=True,
init_weights=True).to(device)
optimizer = optim.Adam(model.parameters(), lr=lr)
scheduler = torch.optim.lr_scheduler.ExponentialLR(optimizer, gamma=0.9)
criterion = nn.CrossEntropyLoss().to(device)
validation_acc = []
best_acc, best_epoch = 0, 0
global_step = 0
for epoch in range(epochs):
model.train() # 训练模式
total_batch_loss = 0
print('start')
# print(train_loader[:1])
for step, data in enumerate(train_loader):
x, y = data
x, y = x.to(device), y.to(device)
logits, aux_logits2, aux_logits1 = model(x)
loss0 = criterion(logits, y)
loss1 = criterion(aux_logits1, y)
loss2 = criterion(aux_logits2, y)
loss = loss0 + loss1 * 0.3 + loss2 * 0.3
total_batch_loss += loss.item()
# 梯度清零
optimizer.zero_grad()
# 计算梯度
loss.backward()
# 更新参数
optimizer.step()
if step % 200 == 0:
print('Step {}/{} \t loss: {}'.format(step, len(train_loader),
loss))
# eval模式
model.eval()
val_acc = evalute(model, val_loader)
if val_acc > best_acc:
best_epoch = epoch
best_acc = val_acc
torch.save(model.state_dict(), 'best.mdl')
scheduler.step() # 调整学习率
print("epoch: ", epoch, "epoch_loss: ", total_batch_loss, "epoch_acc:",
val_acc)
print('best acc:', best_acc, 'best epoch:', best_epoch)
model.load_state_dict(torch.load('best.mdl'))
print('loaded from ckpt!')
test_acc = evalute(model, test_loader)
print('test acc:', test_acc)
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
data_transform = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
# load image
img_path = "../tulip.jpg"
assert os.path.exists(img_path), "file: '{}' dose not exist.".format(
img_path)
img = Image.open(img_path)
plt.imshow(img)
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
# read class_indict
json_path = './class_indices.json'
assert os.path.exists(json_path), "file: '{}' dose not exist.".format(
json_path)
json_file = open(json_path, "r")
class_indict = json.load(json_file)
# create model
model = GoogLeNet(num_classes=5, aux_logits=False).to(device)
# * 初始化的时候，aux_logits=False，不需要搭建辅助分类器
# load model weights
weights_path = "./googleNet.pth"
assert os.path.exists(weights_path), "file: '{}' dose not exist.".format(
weights_path)
missing_keys, unexpected_keys = model.load_state_dict(torch.load(
weights_path, map_location=device),
strict=False)
# * strict默认是True，表示精准匹配 当前模型和需要载入的权重模型 之间的结构
# * strict=False, 因为刚刚保存模型的时候已经保存了2个辅助分类器，而此时不需要，所以设为False
model.eval()
with torch.no_grad():
# predict class
output = torch.squeeze(model(img.to(device))).cpu()
predict = torch.softmax(output, dim=0)
predict_cla = torch.argmax(predict).numpy()
print_res = "class: {} prob: {:.3}".format(
class_indict[str(predict_cla)], predict[predict_cla].numpy())
plt.title(print_res)
print(print_res)
plt.show()
def predict(self):
im_height = 224
im_width = 224
# load image
img = Image.open(fname)
# resize image to 224x224
img = img.resize((im_width, im_height))
plt.imshow(img)
# scaling pixel value and normalize
img = ((np.array(img) / 255.) - 0.5) / 0.5
# Add the image to a batch where it's the only member.
img = (np.expand_dims(img, 0))
# read class_indict
try:
json_file = open('./class_indices.json', 'r')
class_indict = json.load(json_file)
except Exception as e:
print(e)
exit(-1)
model = GoogLeNet(class_num=5, aux_logits=False)
model.summary()
model.load_weights("./save_weights/myGoogLenet.h5", by_name=True) # h5 format
# model.load_weights("./save_weights/myGoogLeNet.ckpt") # ckpt format
result = model.predict(img)
predict_class = np.argmax(result)
print(class_indict[str(predict_class)])
result1 = class_indict[str(predict_class)]
self.textBrowser.setPlainText(result1)
plt.show()
def _main(model_name):
# data_sets path
train_dir = '/home/lst/datasets/cifar-10-images_train/'
val_dir = '/home/lst/datasets/cifar-10-images_test/'
# model
model = GoogLeNet(input_shape=(224, 224, 3))
# parallel model
parallel_model = multi_gpu_model(model, gpus=2)
# optimizers setting
from keras import optimizers
optimizer = optimizers.adamax(lr=0.002, decay=1e-06)
parallel_model.compile(loss=[
'categorical_crossentropy', 'categorical_crossentropy',
'categorical_crossentropy'
],
loss_weights=[1, 0.3, 0.3],
optimizer=optimizer,
metrics=["accuracy"])
# load data by batch
train_generator, validation_generator, num_train, num_val = load_batch_data(
train_dir, val_dir)
# Callbacks settings
from keras.callbacks import EarlyStopping, ModelCheckpoint, TensorBoard
early_stop = EarlyStopping(monitor='val_loss',
min_delta=0.001,
patience=30,
mode='min',
verbose=1)
checkpoint = ModelCheckpoint(f'{model_name}.h5',
monitor='val_loss',
verbose=1,
save_best_only=True,
mode='min',
period=1)
tensorboard = TensorBoard(log_dir=f'./logs/{model_name}',
histogram_freq=0,
write_graph=True,
write_images=False)
# fit
parallel_model.fit_generator(
train_generator,
validation_data=validation_generator,
steps_per_epoch=math.ceil(num_train / batch_size),
validation_steps=math.ceil(num_val / batch_size),
epochs=epochs,
callbacks=[tensorboard, early_stop, checkpoint],
)
def predict(img_path, weights_path, class_indices_path):
"""
对图像进行预测分类
:param img_path: 待预测图像路径
:param weights_path: 模型权重路径
:param class_indices_path: 标签类别索引
:return: 待预测图像类别
"""
img_height = img_width = 224
# 加载待预测图像
img = Image.open(img_path)
# 重设图像大小
img = img.resize((img_width, img_height))
plt.imshow(img)
# 归一化
img = (np.array(img) / 255. - 0.5) / 0.5
# 增加batch这个维度
img = (np.expand_dims(img, 0))
# 加载标签类别索引文件
try:
json_file = open(class_indices_path, 'r')
class_indict = json.load(json_file)
except Exception as e:
print(e)
exit(-1)
# 预测
model = GoogLeNet(class_num=5, aux_logits=False)
# 由于当前创建的模型没有辅助分类器，而保存的训练模型有辅助分类器，需要by_name参数根据名字匹配相关权重参数
model.load_weights(weights_path, by_name=True)
result = np.squeeze(model.predict(img))
predict_class = np.argmax(result)
label = class_indict[str(predict_class)], result[predict_class]
plt.title(label)
plt.show()
def main():
im_height = 224
im_width = 224
# load image
img_path = "../tulip.jpg"
assert os.path.exists(img_path), "file: '{}' dose not exist.".format(
img_path)
img = Image.open(img_path)
# resize image to 224x224
img = img.resize((im_width, im_height))
plt.imshow(img)
# scaling pixel value and normalize
img = ((np.array(img) / 255.) - 0.5) / 0.5
# Add the image to a batch where it's the only member.
img = (np.expand_dims(img, 0))
# read class_indict
json_path = './class_indices.json'
assert os.path.exists(json_path), "file: '{}' dose not exist.".format(
json_path)
json_file = open(json_path, "r")
class_indict = json.load(json_file)
model = GoogLeNet(class_num=5,
aux_logits=False) # 没有辅助分类器后，参数几乎少了一半；因为辅助分类器都是全连接层
model.summary()
# model.load_weights("./save_weights/myGoogLenet.h5", by_name=True) # h5 format
# .h5格式保存的，需要加上参数 by_name=True ；会按照当前创建的模型的变量名称载入
# 因为训练的时候是有辅助分类器的，而现在预测的时候是没有辅助分类器的
weights_path = "./save_weights/myGoogLeNet.ckpt"
assert len(glob.glob(weights_path +
"*")), "cannot find {}".format(weights_path)
model.load_weights(weights_path)
result = np.squeeze(model.predict(img))
predict_class = np.argmax(result)
print_res = "class: {} prob: {:.3}".format(
class_indict[str(predict_class)], result[predict_class])
plt.title(print_res)
print(print_res)
plt.show()
def load_model():
model = GoogLeNet()
model.load_state_dict(torch.load(PRETRAINED_MODEL))
return model
def main():
data_root = os.path.abspath(os.path.join(os.getcwd(),
"../..")) # get data root path
image_path = os.path.join(data_root, "data_set",
"flower_data") # flower data set path
train_dir = os.path.join(image_path, "train")
validation_dir = os.path.join(image_path, "val")
assert os.path.exists(train_dir), "cannot find {}".format(train_dir)
assert os.path.exists(validation_dir), "cannot find {}".format(
validation_dir)
# create direction for saving weights
if not os.path.exists("save_weights"):
os.makedirs("save_weights")
im_height = 224
im_width = 224
batch_size = 32
epochs = 30
def pre_function(img):
# img = im.open('test.jpg')
# img = np.array(img).astype(np.float32)
img = img / 255.
img = (img - 0.5) * 2.0
return img
# data generator with data augmentation
train_image_generator = ImageDataGenerator(
preprocessing_function=pre_function, horizontal_flip=True)
validation_image_generator = ImageDataGenerator(
preprocessing_function=pre_function)
train_data_gen = train_image_generator.flow_from_directory(
directory=train_dir,
batch_size=batch_size,
shuffle=True,
target_size=(im_height, im_width),
class_mode='categorical')
total_train = train_data_gen.n
# get class dict
class_indices = train_data_gen.class_indices
# transform value and key of dict
inverse_dict = dict((val, key) for key, val in class_indices.items())
# write dict into json file
json_str = json.dumps(inverse_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
val_data_gen = validation_image_generator.flow_from_directory(
directory=validation_dir,
batch_size=batch_size,
shuffle=False,
target_size=(im_height, im_width),
class_mode='categorical')
total_val = val_data_gen.n
print("using {} images for training, {} images for validation.".format(
total_train, total_val))
model = GoogLeNet(im_height=im_height,
im_width=im_width,
class_num=5,
aux_logits=True)
# model.build((batch_size, 224, 224, 3)) # when using subclass model
model.summary()
# using keras low level api for training
loss_object = tf.keras.losses.CategoricalCrossentropy(from_logits=False)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.0003)
train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.CategoricalAccuracy(
name='train_accuracy')
val_loss = tf.keras.metrics.Mean(name='val_loss')
val_accuracy = tf.keras.metrics.CategoricalAccuracy(name='val_accuracy')
@tf.function
def train_step(images, labels):
with tf.GradientTape() as tape:
aux1, aux2, output = model(images, training=True)
loss1 = loss_object(labels, aux1)
loss2 = loss_object(labels, aux2)
loss3 = loss_object(labels, output)
loss = loss1 * 0.3 + loss2 * 0.3 + loss3
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
train_loss(loss)
train_accuracy(labels, output)
@tf.function
def val_step(images, labels):
_, _, output = model(images, training=False)
loss = loss_object(labels, output)
val_loss(loss)
val_accuracy(labels, output)
best_val_acc = 0.
for epoch in range(epochs):
train_loss.reset_states() # clear history info
train_accuracy.reset_states() # clear history info
val_loss.reset_states() # clear history info
val_accuracy.reset_states() # clear history info
# train
train_bar = tqdm(range(total_train // batch_size))
for step in train_bar:
images, labels = next(train_data_gen)
train_step(images, labels)
# print train process
train_bar.desc = "train epoch[{}/{}] loss:{:.3f}, acc:{:.3f}".format(
epoch + 1, epochs, train_loss.result(),
train_accuracy.result())
# validate
val_bar = tqdm(range(total_val // batch_size))
for step in val_bar:
val_images, val_labels = next(val_data_gen)
val_step(val_images, val_labels)
# print val process
val_bar.desc = "valid epoch[{}/{}] loss:{:.3f}, acc:{:.3f}".format(
epoch + 1, epochs, val_loss.result(), val_accuracy.result())
# only save best weights
if val_accuracy.result() > best_val_acc:
best_val_acc = val_accuracy.result()
model.save_weights("./save_weights/myGoogLeNet.ckpt")
# load image
img = Image.open("../tulip.jpg")
plt.imshow(img)
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
# read class_indict
try:
json_file = open('./class_indices.json', 'r')
class_indict = json.load(json_file)
except Exception as e:
print(e)
exit(-1)
# create model
model = GoogLeNet(num_classes=5, aux_logits=False)
# load model weights
model_weight_path = "./googleNet.pth"
missing_keys, unexpected_keys = model.load_state_dict(torch.load(model_weight_path), strict=False)
model.eval()
with torch.no_grad():
# predict class
output = torch.squeeze(model(img))
predict = torch.softmax(output, dim=0)
predict_cla = torch.argmax(predict).numpy()
print(predict.numpy()[predict_cla])
print(class_indict[str(predict_cla)])
plt.show()
def run():
# 准备数据
train_image_generator = ImageDataGenerator(
preprocessing_function=pre_function, horizontal_flip=True)
validation_image_generator = ImageDataGenerator(
preprocessing_function=pre_function)
train_data_gen = train_image_generator.flow_from_directory(
directory=train_dir,
batch_size=batch_size,
shuffle=True,
target_size=(img_height, img_width),
class_mode='categorical')
val_data_gen = validation_image_generator.flow_from_directory(
directory=validation_dir,
batch_size=batch_size,
shuffle=False,
target_size=(img_height, img_width),
class_mode='categorical')
total_train, total_val = train_data_gen.n, val_data_gen.n
# get class dict
class_indices = train_data_gen.class_indices
# transform value and key of dict
inverse_dict = dict((val, key) for key, val in class_indices.items())
# write dict into json file
json_str = json.dumps(inverse_dict, indent=4)
with open('../class_indices.json', 'w') as json_file:
json_file.write(json_str)
# 构建GoogLeNet模型
model = GoogLeNet(img_height=img_height,
img_width=img_width,
class_num=5,
aux_logits=True)
# model.build((batch_size, 224, 224, 3)) # when using subclass model
# model.load_weights("pretrain_weights.ckpt")
model.summary()
# 使用keras低层API自定义训练过程
loss_object = tf.keras.losses.CategoricalCrossentropy(from_logits=False)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.0005)
train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.CategoricalAccuracy(
name='train_accuracy')
test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.CategoricalAccuracy(name='test_accuracy')
@tf.function
def train_step(images, labels):
with tf.GradientTape() as tape:
aux1, aux2, output = model(images, training=True)
loss1 = loss_object(labels, aux1)
loss2 = loss_object(labels, aux2)
loss3 = loss_object(labels, output)
loss = loss1 * 0.3 + loss2 * 0.3 + loss3
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
train_loss(loss)
train_accuracy(labels, output)
@tf.function
def test_step(images, labels):
_, _, output = model(images, training=False)
t_loss = loss_object(labels, output)
test_loss(t_loss)
test_accuracy(labels, output)
best_test_loss = float('inf')
for epoch in range(1, epochs + 1):
train_loss.reset_states() # clear history info
train_accuracy.reset_states() # clear history info
test_loss.reset_states() # clear history info
test_accuracy.reset_states() # clear history info
for step in range(total_train // batch_size):
images, labels = next(train_data_gen)
train_step(images, labels)
for step in range(total_val // batch_size):
test_images, test_labels = next(val_data_gen)
test_step(test_images, test_labels)
template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
print(
template.format(epoch, train_loss.result(),
train_accuracy.result() * 100, test_loss.result(),
test_accuracy.result() * 100))
if test_loss.result() < best_test_loss:
best_test_loss = test_loss.result()
model.save_weights("../save_weights/GoogLeNet.h5")
import matplotlib.pyplot as plt
im_height = 224
im_width = 224
# 读入图片
img = Image.open(
"E:/DeepLearning/GoogLeNet/daisy_test.jpg") # 这是我的路径，要根据自己的根目录来改
# resize成224x224的格式
img = img.resize((im_width, im_height))
plt.imshow(img)
# 对原图标准化处理
img = ((np.array(img) / 255.) - 0.5) / 0.5
# Add the image to a batch where it's the only member.
img = (np.expand_dims(img, 0))
# 读class_indict文件
try:
json_file = open('./class_indices.json', 'r')
class_indict = json.load(json_file)
except Exception as e:
print(e)
exit(-1)
model = GoogLeNet(class_num=5, aux_logits=False) # 重新构建网络
model.summary()
model.load_weights("./save_weights/myGoogLenet.h5", by_name=True) # 加载模型参数
# model.load_weights("./save_weights/myGoogLeNet.ckpt") # ckpt format
result = model.predict(img)
predict_class = np.argmax(result)
print('预测出的类别是：', class_indict[str(predict_class)]) # 打印显示出预测类别
plt.show()
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
data_transform = transforms.Compose(
[transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
# load image
img_path = "./a.jpg"
assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
img = Image.open(img_path)
plt.imshow(img)
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
# read class_indict
json_path = './class_indices.json'
assert os.path.exists(json_path), "file: '{}' dose not exist.".format(json_path)
json_file = open(json_path, "r")
class_indict = json.load(json_file)
# create model
model = GoogLeNet(num_classes=5, aux_logits=False).to(device)
# load model weights
weights_path = "./weights/googlenet.pth"
assert os.path.exists(weights_path), "file: '{}' dose not exist.".format(weights_path)
missing_keys, unexpected_keys = model.load_state_dict(torch.load(weights_path, map_location=device),
strict=False)
model.eval()
print('=================================')
dummy_input = torch.randn(1, 3, 224, 224).to(device)
torch.onnx.export(
model,
dummy_input,
'googlenet.onnx',
dynamic_axes={'image': {0: 'B'}, 'outputs': {0: 'B'}},
input_names=['image'],
output_names=['outputs'],
opset_version=12
)
print('=================================')
print('---------------------------------')
traced_script_module = torch.jit.trace(model, dummy_input)
traced_script_module.save("googlenet.pt")
with torch.no_grad():
# predict class
output = torch.squeeze(model(img.to(device))).cpu()
predict = torch.softmax(output, dim=0)
predict_cla = torch.argmax(predict).numpy()
print_res = "class: {} prob: {:.3}".format(class_indict[str(predict_cla)],
predict[predict_cla].numpy())
plt.title(print_res)
print(print_res)
plt.show()
shuffle=False,
num_workers=0)
# test_data_iter = iter(validate_loader)
# test_image, test_label = test_data_iter.next()
# net = torchvision.models.googlenet(num_classes=5)
# model_dict = net.state_dict()
# pretrain_model = torch.load("googlenet.pth")
# del_list = ["aux1.fc2.weight", "aux1.fc2.bias",
# "aux2.fc2.weight", "aux2.fc2.bias",
# "fc.weight", "fc.bias"]
# pretrain_dict = {k: v for k, v in pretrain_model.items() if k not in del_list}
# model_dict.update(pretrain_dict)
# net.load_state_dict(model_dict)
net = GoogLeNet(num_classes=5, aux_logits=True, init_weights=True)
net.to(device)
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.0003)
best_acc = 0.0
save_path = './googleNet.pth'
for epoch in range(30):
# train
net.train()
running_loss = 0.0
for step, data in enumerate(train_loader, start=0):
images, labels = data
optimizer.zero_grad()
logits, aux_logits2, aux_logits1 = net(images.to(device))
loss0 = loss_function(logits, labels.to(device))
json_str = json.dumps(inverse_dict,
indent=4) #将转换后的字典写入文件class_indices.json
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
# 使用图像生成器从验证集validation_dir中读取样本
val_data_gen = train_image_generator.flow_from_directory(
directory=validation_dir,
batch_size=batch_size,
shuffle=True,
target_size=(im_height, im_width),
class_mode='categorical')
# 验证集的数量
total_val = val_data_gen.n
model = GoogLeNet(im_height=im_height,
im_width=im_width,
class_num=5,
aux_logits=True) #实例化模型
# model.build((batch_size, 224, 224, 3)) # when using subclass model
model.summary()
#使用keras底层api进行网络训练
loss_object = tf.keras.losses.CategoricalCrossentropy(
from_logits=False) # 定义损失函数（这种方式需要one-hot编码）
optimizer = tf.keras.optimizers.Adam(lr=0.0001) #定义优化器
train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.CategoricalAccuracy(
name='train_acuracy') #定义平均准确率
test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.CategoricalAccuracy(
inverse_dict = dict((val, key) for key, val in class_indices.items())
# write dict into json file
json_str = json.dumps(inverse_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
val_data_gen = train_image_generator.flow_from_directory(
directory=validation_dir,
batch_size=batch_size,
shuffle=True,
target_size=(im_height, im_width),
class_mode='categorical')
total_val = val_data_gen.n
model = GoogLeNet(im_height=im_height,
im_width=im_width,
class_num=5,
aux_logits=True)
# model.build((batch_size, 224, 224, 3)) # when using subclass model
model.summary()
# using keras low level api for training
loss_object = tf.keras.losses.CategoricalCrossentropy(from_logits=False)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.0003)
train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.CategoricalAccuracy(name='train_accuracy')
test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.CategoricalAccuracy(name='test_accuracy')
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
data_transform = {
"train": transforms.Compose([transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]),
"val": transforms.Compose([transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])}
data_root = os.path.abspath(os.path.join(os.getcwd(), "../..")) # get data root path
image_path = data_root + "/data_set/flower_data/" # flower data set path
train_dataset = datasets.ImageFolder(root=image_path + "train",
transform=data_transform["train"])
train_num = len(train_dataset)
# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx
cla_dict = dict((val, key) for key, val in flower_list.items())
# write dict into json file
json_str = json.dumps(cla_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
batch_size = 32
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size, shuffle=True,
num_workers=0)
validate_dataset = datasets.ImageFolder(root=image_path + "val",
transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(validate_dataset,
batch_size=batch_size, shuffle=False,
num_workers=0)
# test_data_iter = iter(validate_loader)
# test_image, test_label = test_data_iter.next()
# net = torchvision.models.googlenet(num_classes=5)
# model_dict = net.state_dict()
# pretrain_model = torch.load("googlenet.pth")
# del_list = ["aux1.fc2.weight", "aux1.fc2.bias",
# "aux2.fc2.weight", "aux2.fc2.bias",
# "fc.weight", "fc.bias"]
# pretrain_dict = {k: v for k, v in pretrain_model.items() if k not in del_list}
# model_dict.update(pretrain_dict)
# net.load_state_dict(model_dict)
net = GoogLeNet(num_classes=5, aux_logits=True, init_weights=True)
net.to(device)
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.0003)
best_acc = 0.0
save_path = './googleNet.pth'
for epoch in range(30):
# train
net.train()
running_loss = 0.0
for step, data in enumerate(train_loader, start=0):
images, labels = data
optimizer.zero_grad()
logits, aux_logits2, aux_logits1 = net(images.to(device))
loss0 = loss_function(logits, labels.to(device))
loss1 = loss_function(aux_logits1, labels.to(device))
loss2 = loss_function(aux_logits2, labels.to(device))
loss = loss0 + loss1 * 0.3 + loss2 * 0.3
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
# print train process
rate = (step + 1) / len(train_loader)
a = "*" * int(rate * 50)
b = "." * int((1 - rate) * 50)
print("\rtrain loss: {:^3.0f}%[{}->{}]{:.3f}".format(int(rate * 100), a, b, loss), end="")
print()
# validate
net.eval()
acc = 0.0 # accumulate accurate number / epoch
with torch.no_grad():
for val_data in validate_loader:
val_images, val_labels = val_data
outputs = net(val_images.to(device)) # eval model only have last output layer
predict_y = torch.max(outputs, dim=1)[1]
acc += (predict_y == val_labels.to(device)).sum().item()
val_accurate = acc / val_num
if val_accurate > best_acc:
best_acc = val_accurate
torch.save(net.state_dict(), save_path)
print('[epoch %d] train_loss: %.3f test_accuracy: %.3f' %
(epoch + 1, running_loss / step, val_accurate))
print('Finished Training')
def main():
gpus = tf.config.experimental.list_physical_devices("GPU")
if gpus:
try:
for gpu in gpus:
tf.config.experimental.set_memory_growth(gpu, True)
except RuntimeError as e:
print(e)
exit(-1)
data_root = os.path.abspath(os.path.join(os.getcwd(),
"../..")) # get data root path
image_path = os.path.join(data_root, "data_set",
"flower_data") # flower data set path
train_dir = os.path.join(image_path, "train")
validation_dir = os.path.join(image_path, "val")
assert os.path.exists(train_dir), "cannot find {}".format(train_dir)
assert os.path.exists(validation_dir), "cannot find {}".format(
validation_dir)
# create direction for saving weights
if not os.path.exists("save_weights"):
os.makedirs("save_weights")
im_height = 224
im_width = 224
batch_size = 32
epochs = 30
# class dict
data_class = [
cla for cla in os.listdir(train_dir)
if os.path.isdir(os.path.join(train_dir, cla))
]
class_num = len(data_class)
class_dict = dict((value, index) for index, value in enumerate(data_class))
# reverse value and key of dict
inverse_dict = dict((val, key) for key, val in class_dict.items())
# write dict into json file
json_str = json.dumps(inverse_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
# load train images list
train_image_list = glob.glob(train_dir + "/*/*.jpg")
random.shuffle(train_image_list)
train_num = len(train_image_list)
assert train_num > 0, "cannot find any .jpg file in {}".format(train_dir)
train_label_list = [
class_dict[path.split(os.path.sep)[-2]] for path in train_image_list
]
# load validation images list
val_image_list = glob.glob(validation_dir + "/*/*.jpg")
random.shuffle(val_image_list)
val_num = len(val_image_list)
assert val_num > 0, "cannot find any .jpg file in {}".format(
validation_dir)
val_label_list = [
class_dict[path.split(os.path.sep)[-2]] for path in val_image_list
]
print("using {} images for training, {} images for validation.".format(
train_num, val_num))
def process_train_img(img_path, label):
label = tf.one_hot(label, depth=class_num)
image = tf.io.read_file(img_path)
image = tf.image.decode_jpeg(image)
image = tf.image.convert_image_dtype(image, tf.float32)
image = tf.image.resize(image, [im_height, im_width])
image = tf.image.random_flip_left_right(image)
image = (image - 0.5) / 0.5
return image, label
def process_val_img(img_path, label):
label = tf.one_hot(label, depth=class_num)
image = tf.io.read_file(img_path)
image = tf.image.decode_jpeg(image)
image = tf.image.convert_image_dtype(image, tf.float32)
image = tf.image.resize(image, [im_height, im_width])
image = (image - 0.5) / 0.5
return image, label
AUTOTUNE = tf.data.experimental.AUTOTUNE
# load train dataset
train_dataset = tf.data.Dataset.from_tensor_slices(
(train_image_list, train_label_list))
train_dataset = train_dataset.shuffle(buffer_size=train_num)\
.map(process_train_img, num_parallel_calls=AUTOTUNE)\
.repeat().batch(batch_size).prefetch(AUTOTUNE)
# load train dataset
val_dataset = tf.data.Dataset.from_tensor_slices(
(val_image_list, val_label_list))
val_dataset = val_dataset.map(process_val_img, num_parallel_calls=tf.data.experimental.AUTOTUNE)\
.repeat().batch(batch_size)
# 实例化模型
model = GoogLeNet(im_height=224,
im_width=224,
class_num=5,
aux_logits=True)
model.summary()
# using keras low level api for training
loss_object = tf.keras.losses.CategoricalCrossentropy(from_logits=False)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.0003)
train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.CategoricalAccuracy(
name='train_accuracy')
test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.CategoricalAccuracy(name='test_accuracy')
@tf.function
def train_step(images, labels):
with tf.GradientTape() as tape:
aux1, aux2, output = model(images, training=True)
loss1 = loss_object(labels, aux1)
loss2 = loss_object(labels, aux2)
loss3 = loss_object(labels, output)
loss = loss1 * 0.3 + loss2 * 0.3 + loss3
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
train_loss(loss)
train_accuracy(labels, output)
@tf.function
def test_step(images, labels):
_, _, output = model(images, training=False)
t_loss = loss_object(labels, output)
test_loss(t_loss)
test_accuracy(labels, output)
best_test_loss = float('inf')
train_step_num = train_num // batch_size
val_step_num = val_num // batch_size
for epoch in range(1, epochs + 1):
train_loss.reset_states() # clear history info
train_accuracy.reset_states() # clear history info
test_loss.reset_states() # clear history info
test_accuracy.reset_states() # clear history info
t1 = time.perf_counter()
for index, (images, labels) in enumerate(train_dataset):
train_step(images, labels)
if index + 1 == train_step_num:
break
print(time.perf_counter() - t1)
for index, (images, labels) in enumerate(val_dataset):
test_step(images, labels)
if index + 1 == val_step_num:
break
template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
print(
template.format(epoch, train_loss.result(),
train_accuracy.result() * 100, test_loss.result(),
test_accuracy.result() * 100))
if test_loss.result() < best_test_loss:
model.save_weights("./save_weights/myGoogLeNet.ckpt".format(epoch),
save_format='tf')
img = img.resize((im_width, im_height))
plt.imshow(img)
# scaling pixel value and normalize
img = ((np.array(img) / 255.) - 0.5) / 0.5
# Add the image to a batch where it's the only member.
img = (np.expand_dims(img, 0))
# read class_indict
try:
json_file = open('./class_indices.json', 'r')
class_indict = json.load(json_file)
except Exception as e:
print(e)
exit(-1)
model = GoogLeNet(class_num=5, aux_logits=False)
# 在训练过程中，用了sequential和functional方式构建模型，所以模型是一个static graph，当做validation的时候，不能动态控制附加输出的分支，但是做inference的时候构建的模型不含附加输出的分支
model.summary()
# 模型载入参数的两种方式，对于h5格式，需要指定按照卷积层的名称载入参数；对于ckpt格式，则不需要指定，会自动按照名称给参数赋值
# model.load_weights("./save_weights/myGoogLenet.h5", by_name=True) # h5 format
model.load_weights("./save_weights/myGoogLeNet.ckpt") # ckpt format
result = model.predict(img)
# 预测结果应该是：
# result = np.squeeze(model.predict(img))
predict_class = np.argmax(result)
print(class_indict[str(predict_class)])
plt.show()
# 我们这次仍然使用前面项目介绍过的ResNet模型，简单数据增广、MixUp都用上，看看使用SMOTE方法改善训练数据分布不平衡的效果。
#
# In[1]:
# 模型训练
from model import GoogLeNet
from train import train
if __name__ == '__main__':
# 在分布不平衡的数据集上训练
# model = GoogLeNet("GoogLeNet", num_classes=3)
# train(model, augment='userDef') # 使用自定义数据増广的训练
# model = GoogLeNet("GoogLeNet", num_classes=3)
# train(model, augment='samplePairing') # 使用samplePairing
model = GoogLeNet("GoogLeNet", num_classes=3)
train(model, augment='mixup') # 使用mixup
# 在分布平衡的数据集上训练
# model = GoogLeNet("GoogLeNet", num_classes=3)
# train(model, augment='userDef', bal='balance') # 使用自定义数据増广的训练
# model = GoogLeNet("GoogLeNet", num_classes=3)
# train(model, augment='samplePairing', bal='balance') # 使用samplePairing
model = GoogLeNet("GoogLeNet", num_classes=3)
train(model, augment='mixup', bal='balance') # 使用mixup
# In[32]:
#查看训练结果(loss)
import numpy as np
import matplotlib.pyplot as plt
im_width = 224
#读入图片
img = Image.open('daisy_test.jpg')
img = img.resize((im_height, im_width))
plt.imshow(img)
plt.show()
#对原图像进行处理
img = (np.array(img) / 255. - 0.5) / 0.5
# 当图像只有一张时，需要增加一维度
img = np.expand_dims(img, 0)
# 读取标签说明文件
try:
json_file = open('class_indices.json', 'r')
class_indict = json.load(json_file)
except Exception as e:
print(e)
exit(-1)
#构造网络
# saved model use following method
# model = tf.keras.models.load_model('./saved_model/')
#save wieight model use following method
model = GoogLeNet(class_num=5,
im_height=im_height,
im_width=im_width,
aux_logits=False)
model.load_weights('save_weights/myGoogLeNet.h5', by_name=True) #加载模型参数
model.summary()
result = model.predict(img)
predict_class = np.argmax(result)
print('预测出来的类别为{0}'.format(class_indict[str(predict_class)]))
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print("using {} device.".format(device))
data_transform = {
"train": transforms.Compose([transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]),
"val": transforms.Compose([transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])}
data_root = os.path.abspath(os.path.join(os.getcwd(), "../..")) # get data root path
image_path = os.path.join(data_root, "data_set", "flower_data") # flower data set path
assert os.path.exists(image_path), "{} path does not exist.".format(image_path)
train_dataset = datasets.ImageFolder(root=os.path.join(image_path, "train"),
transform=data_transform["train"])
train_num = len(train_dataset)
# {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
flower_list = train_dataset.class_to_idx
cla_dict = dict((val, key) for key, val in flower_list.items())
# write dict into json file
json_str = json.dumps(cla_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
batch_size = 32
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8]) # number of workers
print('Using {} dataloader workers every process'.format(nw))
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size, shuffle=True,
num_workers=nw)
validate_dataset = datasets.ImageFolder(root=os.path.join(image_path, "val"),
transform=data_transform["val"])
val_num = len(validate_dataset)
validate_loader = torch.utils.data.DataLoader(validate_dataset,
batch_size=batch_size, shuffle=False,
num_workers=nw)
print("using {} images for training, {} images fot validation.".format(train_num,
val_num))
# test_data_iter = iter(validate_loader)
# test_image, test_label = test_data_iter.next()
# net = torchvision.models.googlenet(num_classes=5)
# model_dict = net.state_dict()
# pretrain_model = torch.load("googlenet.pth")
# del_list = ["aux1.fc2.weight", "aux1.fc2.bias",
# "aux2.fc2.weight", "aux2.fc2.bias",
# "fc.weight", "fc.bias"]
# pretrain_dict = {k: v for k, v in pretrain_model.items() if k not in del_list}
# model_dict.update(pretrain_dict)
# net.load_state_dict(model_dict)
net = GoogLeNet(num_classes=5, aux_logits=True, init_weights=True)
net.to(device)
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.0003)
epochs = 30
best_acc = 0.0
save_path = './googleNet.pth'
train_steps = len(train_loader)
for epoch in range(epochs):
# train
net.train()
running_loss = 0.0
train_bar = tqdm(train_loader)
for step, data in enumerate(train_bar):
images, labels = data
optimizer.zero_grad()
logits, aux_logits2, aux_logits1 = net(images.to(device))
loss0 = loss_function(logits, labels.to(device))
loss1 = loss_function(aux_logits1, labels.to(device))
loss2 = loss_function(aux_logits2, labels.to(device))
loss = loss0 + loss1 * 0.3 + loss2 * 0.3
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(epoch + 1,
epochs,
loss)
# validate
net.eval()
acc = 0.0 # accumulate accurate number / epoch
with torch.no_grad():
val_bar = tqdm(validate_loader, colour='green')
for val_data in val_bar:
val_images, val_labels = val_data
outputs = net(val_images.to(device)) # eval model only have last output layer
predict_y = torch.max(outputs, dim=1)[1]
acc += torch.eq(predict_y, val_labels.to(device)).sum().item()
val_accurate = acc / val_num
print('[epoch %d] train_loss: %.3f val_accuracy: %.3f' %
(epoch + 1, running_loss / train_steps, val_accurate))
if val_accurate > best_acc:
best_acc = val_accurate
torch.save(net.state_dict(), save_path)
print('Finished Training')
def main():
data_root = os.path.abspath(os.path.join(os.getcwd(), "../..")) # get data root path
image_path = data_root + "/data_set/flower_data/" # flower data set path
train_dir = image_path + "train"
validation_dir = image_path + "val"
# create direction for saving weights
if not os.path.exists("save_weights"):
os.makedirs("save_weights")
im_height = 224
im_width = 224
batch_size = 32
epochs = 30
def pre_function(img):
# img = im.open('test.jpg')
# img = np.array(img).astype(np.float32)
img = img / 255.
img = (img - 0.5) * 2.0
return img
# data generator with data augmentation
train_image_generator = ImageDataGenerator(preprocessing_function=pre_function,
horizontal_flip=True)
validation_image_generator = ImageDataGenerator(preprocessing_function=pre_function)
train_data_gen = train_image_generator.flow_from_directory(directory=train_dir,
batch_size=batch_size,
shuffle=True,
target_size=(im_height, im_width),
class_mode='categorical')
total_train = train_data_gen.n
# get class dict
class_indices = train_data_gen.class_indices
# transform value and key of dict
inverse_dict = dict((val, key) for key, val in class_indices.items())
# write dict into json file
json_str = json.dumps(inverse_dict, indent=4)
with open('class_indices.json', 'w') as json_file:
json_file.write(json_str)
val_data_gen = validation_image_generator.flow_from_directory(directory=validation_dir,
batch_size=batch_size,
shuffle=False,
target_size=(im_height, im_width),
class_mode='categorical')
total_val = val_data_gen.n
model = GoogLeNet(im_height=im_height, im_width=im_width, class_num=5, aux_logits=True)
# model.build((batch_size, 224, 224, 3)) # when using subclass model
model.summary()
# using keras low level api for training
loss_object = tf.keras.losses.CategoricalCrossentropy(from_logits=False)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.0003)
train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.CategoricalAccuracy(name='train_accuracy')
test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.CategoricalAccuracy(name='test_accuracy')
@tf.function
def train_step(images, labels):
with tf.GradientTape() as tape:
aux1, aux2, output = model(images, training=True)
loss1 = loss_object(labels, aux1)
loss2 = loss_object(labels, aux2)
loss3 = loss_object(labels, output)
loss = loss1 * 0.3 + loss2 * 0.3 + loss3
gradients = tape.gradient(loss, model.trainable_variables)
optimizer.apply_gradients(zip(gradients, model.trainable_variables))
train_loss(loss)
train_accuracy(labels, output)
@tf.function
def test_step(images, labels):
_, _, output = model(images, training=False)
t_loss = loss_object(labels, output)
test_loss(t_loss)
test_accuracy(labels, output)
best_test_loss = float('inf')
for epoch in range(1, epochs + 1):
train_loss.reset_states() # clear history info
train_accuracy.reset_states() # clear history info
test_loss.reset_states() # clear history info
test_accuracy.reset_states() # clear history info
for step in range(total_train // batch_size):
images, labels = next(train_data_gen)
train_step(images, labels)
for step in range(total_val // batch_size):
test_images, test_labels = next(val_data_gen)
test_step(test_images, test_labels)
template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
print(template.format(epoch,
train_loss.result(),
train_accuracy.result() * 100,
test_loss.result(),
test_accuracy.result() * 100))
if test_loss.result() < best_test_loss:
best_test_loss = test_loss.result()
model.save_weights("./save_weights/myGoogLeNet.h5")
AUTOTUNE = tf.data.experimental.AUTOTUNE
# load train dataset
train_dataset = tf.data.Dataset.from_tensor_slices((train_image_list, train_label_list))
train_dataset = train_dataset.shuffle(buffer_size=train_num)\
.map(process_train_img, num_parallel_calls=AUTOTUNE)\
.repeat().batch(batch_size).prefetch(AUTOTUNE)
# load train dataset
val_dataset = tf.data.Dataset.from_tensor_slices((val_image_list, val_label_list))
val_dataset = val_dataset.map(process_val_img, num_parallel_calls=tf.data.experimental.AUTOTUNE)\
.repeat().batch(batch_size)
# 实例化模型
model = GoogLeNet(im_height=224, im_width=224, class_num=5, aux_logits=True)
model.summary()
# using keras low level api for training
loss_object = tf.keras.losses.CategoricalCrossentropy(from_logits=False)
optimizer = tf.keras.optimizers.Adam(learning_rate=0.0003)
train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.CategoricalAccuracy(name='train_accuracy')
test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.CategoricalAccuracy(name='test_accuracy')
@tf.function
def train_step(images, labels):
im_width = 224
# load image
img = Image.open("../yjh.jpg")
# resize image to 224x224
img = img.resize((im_width, im_height))
plt.imshow(img)
# scaling pixel value and normalize
img = ((np.array(img) / 255.) - 0.5) / 0.5
# Add the image to a batch where it's the only member.
img = (np.expand_dims(img, 0))
# read class_indict
try:
json_file = open('./class_indices.json', 'r')
class_indict = json.load(json_file)
except Exception as e:
print(e)
exit(-1)
model = GoogLeNet(class_num=5, aux_logits=False)
model.summary()
model.load_weights("./save_weights/myGoogLenet.h5", by_name=True) # h5 format
# model.load_weights("./save_weights/myGoogLeNet.ckpt") # ckpt format
result = model.predict(img)
predict_class = np.argmax(result)
print(class_indict[str(predict_class)])
plt.show()
