我正在尝试使用 keras 和 tensorflow 通过 u2net 实现脑肿瘤分割。我的模型已经训练好了。但在测试阶段，我收到此错误“值错误：所有输入数组必须具有相同的维数，但索引 0 处的数组具有 3 维，索引 4 处的数组具有 4 维”在测试模块中。我先用U-Net训练模型，然后改代码为U2net。这些是我的代码。谁能帮我解决这个问题？
指标模块：
import numpy as np
import tensorflow as tf
from tensorflow.keras import backend as K
smooth = 1e-15
def dice_coef(y_true, y_pred):
y_true = tf.keras.layers.Flatten()(y_true)
y_pred = tf.keras.layers.Flatten()(y_pred)
intersection = tf.reduce_sum(y_true * y_pred)
return (2. * intersection + smooth) / (tf.reduce_sum(y_true) + tf.reduce_sum(y_pred) + smooth)
def dice_loss(y_true, y_pred):
return 1.0 - dice_coef(y_true, y_pred)
unet模块：（是u2net，我只是把它命名为unet）
import os
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
import tensorflow as tf
from tensorflow.keras.layers import Input, Conv2D, BatchNormalization, Activation, MaxPool2D, UpSampling2D, Concatenate, Add
def conv_block(inputs, out_ch, rate=1):
x = Conv2D(out_ch, 3, padding="same", dilation_rate=1)(inputs)
x = BatchNormalization()(x)
x = Activation("relu")(x)
return x
def RSU_L(inputs, out_ch, int_ch, num_layers, rate=2):
""" Initial Conv """
x = conv_block(inputs, out_ch)
init_feats = x
""" Encoder """
skip = []
x = conv_block(x, int_ch)
skip.append(x)
for i in range(num_layers-2):
x = MaxPool2D((2, 2))(x)
x = conv_block(x, int_ch)
skip.append(x)
""" Bridge """
x = conv_block(x, int_ch, rate=rate)
""" Decoder """
skip.reverse()
x = Concatenate()([x, skip[0]])
x = conv_block(x, int_ch)
for i in range(num_layers-3):
x = UpSampling2D(size=(2, 2), interpolation="bilinear")(x)
x = Concatenate()([x, skip[i+1]])
x = conv_block(x, int_ch)
x = UpSampling2D(size=(2, 2), interpolation="bilinear")(x)
x = Concatenate()([x, skip[-1]])
x = conv_block(x, out_ch)
""" Add """
x = Add()([x, init_feats])
return x
def RSU_4F(inputs, out_ch, int_ch):
""" Initial Conv """
x0 = conv_block(inputs, out_ch, rate=1)
""" Encoder """
x1 = conv_block(x0, int_ch, rate=1)
x2 = conv_block(x1, int_ch, rate=2)
x3 = conv_block(x2, int_ch, rate=4)
""" Bridge """
x4 = conv_block(x3, int_ch, rate=8)
""" Decoder """
x = Concatenate()([x4, x3])
x = conv_block(x, int_ch, rate=4)
x = Concatenate()([x, x2])
x = conv_block(x, int_ch, rate=2)
x = Concatenate()([x, x1])
x = conv_block(x, out_ch, rate=1)
""" Addition """
x = Add()([x, x0])
return x
def u2net(input_shape, out_ch, int_ch, num_classes=1):
""" Input Layer """
inputs = Input(input_shape)
s0 = inputs
""" Encoder """
s1 = RSU_L(s0, out_ch[0], int_ch[0], 7)
p1 = MaxPool2D((2, 2))(s1)
s2 = RSU_L(p1, out_ch[1], int_ch[1], 6)
p2 = MaxPool2D((2, 2))(s2)
s3 = RSU_L(p2, out_ch[2], int_ch[2], 5)
p3 = MaxPool2D((2, 2))(s3)
s4 = RSU_L(p3, out_ch[3], int_ch[3], 4)
p4 = MaxPool2D((2, 2))(s4)
s5 = RSU_4F(p4, out_ch[4], int_ch[4])
p5 = MaxPool2D((2, 2))(s5)
""" Bridge """
b1 = RSU_4F(p5, out_ch[5], int_ch[5])
b2 = UpSampling2D(size=(2, 2), interpolation="bilinear")(b1)
""" Decoder """
d1 = Concatenate()([b2, s5])
d1 = RSU_4F(d1, out_ch[6], int_ch[6])
u1 = UpSampling2D(size=(2, 2), interpolation="bilinear")(d1)
d2 = Concatenate()([u1, s4])
d2 = RSU_L(d2, out_ch[7], int_ch[7], 4)
u2 = UpSampling2D(size=(2, 2), interpolation="bilinear")(d2)
d3 = Concatenate()([u2, s3])
d3 = RSU_L(d3, out_ch[8], int_ch[8], 5)
u3 = UpSampling2D(size=(2, 2), interpolation="bilinear")(d3)
d4 = Concatenate()([u3, s2])
d4 = RSU_L(d4, out_ch[9], int_ch[9], 6)
u4 = UpSampling2D(size=(2, 2), interpolation="bilinear")(d4)
d5 = Concatenate()([u4, s1])
d5 = RSU_L(d5, out_ch[10], int_ch[10], 7)
""" Side Outputs """
y1 = Conv2D(num_classes, 3, padding="same")(d5)
y2 = Conv2D(num_classes, 3, padding="same")(d4)
y2 = UpSampling2D(size=(2, 2), interpolation="bilinear")(y2)
y3 = Conv2D(num_classes, 3, padding="same")(d3)
y3 = UpSampling2D(size=(4, 4), interpolation="bilinear")(y3)
y4 = Conv2D(num_classes, 3, padding="same")(d2)
y4 = UpSampling2D(size=(8, 8), interpolation="bilinear")(y4)
y5 = Conv2D(num_classes, 3, padding="same")(d1)
y5 = UpSampling2D(size=(16, 16), interpolation="bilinear")(y5)
y6 = Conv2D(num_classes, 3, padding="same")(b1)
y6 = UpSampling2D(size=(32, 32), interpolation="bilinear")(y6)
y0 = Concatenate()([y1, y2, y3, y4, y5, y6])
y0 = Conv2D(num_classes, 3, padding="same")(y0)
y0 = Activation("sigmoid")(y0)
y1 = Activation("sigmoid")(y1)
y2 = Activation("sigmoid")(y2)
y3 = Activation("sigmoid")(y3)
y4 = Activation("sigmoid")(y4)
y5 = Activation("sigmoid")(y5)
y6 = Activation("sigmoid")(y6)
model = tf.keras.models.Model(inputs, outputs=[y0, y1, y2, y3, y4, y5, y6])
return model
def build_u2net(input_shape, num_classes=1):
out_ch = [64, 128, 256, 512, 512, 512, 512, 256, 128, 64, 64]
int_ch = [32, 32, 64, 128, 256, 256, 256, 128, 64, 32, 16]
model = u2net(input_shape, out_ch, int_ch, num_classes=num_classes)
return model
def build_u2net_lite(input_shape, num_classes=1):
out_ch = [64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64]
int_ch = [16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16]
model = u2net(input_shape, out_ch, int_ch, num_classes=num_classes)
return model
if __name__ == "__main__":
model = build_u2net_lite((256, 256, 3))
model.summary()
火车模块：
import os
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
import numpy as np
import cv2
from glob import glob
from sklearn.utils import shuffle
import tensorflow as tf
from tensorflow.keras.callbacks import ModelCheckpoint, CSVLogger, ReduceLROnPlateau, EarlyStopping, TensorBoard
from tensorflow.keras.optimizers import Adam
from sklearn.model_selection import train_test_split
from unet import build_u2net_lite
from metrics import dice_loss, dice_coef
""" Global parameters """
H = 256
W = 256
def create_dir(path):
if not os.path.exists(path):
os.makedirs(path)
def load_dataset(path, split=0.2):
images = sorted(glob(os.path.join(path, "images", "*.png")))
masks = sorted(glob(os.path.join(path, "masks", "*.png")))
split_size = int(len(images) * split)
train_x, valid_x = train_test_split(images, test_size=split_size, random_state=42)
train_y, valid_y = train_test_split(masks, test_size=split_size, random_state=42)
train_x, test_x = train_test_split(train_x, test_size=split_size, random_state=42)
train_y, test_y = train_test_split(train_y, test_size=split_size, random_state=42)
return (train_x, train_y), (valid_x, valid_y), (test_x, test_y)
def read_image(path):
path = path.decode()
x = cv2.imread(path, cv2.IMREAD_COLOR)
x = cv2.resize(x, (W, H))
x = x / 255.0
x = x.astype(np.float32)
return x
def read_mask(path):
path = path.decode()
x = cv2.imread(path, cv2.IMREAD_GRAYSCALE) ## (h, w)
x = cv2.resize(x, (W, H)) ## (h, w)
x = x / 255.0 ## (h, w)
x = x.astype(np.float32) ## (h, w)
x = np.expand_dims(x, axis=-1)## (h, w, 1)
return x
def tf_parse(x, y):
def _parse(x, y):
x = read_image(x)
y = read_mask(y)
return x, y
x, y = tf.numpy_function(_parse, [x, y], [tf.float32, tf.float32])
x.set_shape([H, W, 3])
y.set_shape([H, W, 1])
return x, y
def tf_dataset(X, Y, batch=2):
dataset = tf.data.Dataset.from_tensor_slices((X, Y))
dataset = dataset.map(tf_parse)
dataset = dataset.batch(batch)
dataset = dataset.prefetch(10)
return dataset
if __name__ == "__main__":
""" Seeding """
np.random.seed(42)
tf.random.set_seed(42)
""" Directory for storing files """
create_dir("files")
""" Hyperparameters """
batch_size = 4
lr = 1e-4
num_epochs = 500
model_path = os.path.join("files", "model.h5")
csv_path = os.path.join("files", "log.csv")
""" Dataset """
dataset_path = r"C:\Users\ruthw\Dataset"
(train_x, train_y), (valid_x, valid_y), (test_x, test_y) = load_dataset(dataset_path)
print(f"Train: {len(train_x)} - {len(train_y)}")
print(f"Valid: {len(valid_x)} - {len(valid_y)}")
print(f"Test : {len(test_x)} - {len(test_y)}")
train_dataset = tf_dataset(train_x, train_y, batch=batch_size)
valid_dataset = tf_dataset(valid_x, valid_y, batch=batch_size)
""" Model """
model = build_u2net_lite((H, W, 3))
model.compile(loss=dice_loss, optimizer=Adam(lr), metrics=[dice_coef])
callbacks = [
ModelCheckpoint(model_path, verbose=1, save_best_only=True),
ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=5, min_lr=1e-7, verbose=1),
CSVLogger(csv_path),
EarlyStopping(monitor='val_loss', patience=20, restore_best_weights=False),
]
model.fit(
train_dataset,
epochs=num_epochs,
validation_data=valid_dataset,
callbacks=callbacks
)
测试模块：
import os
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
import numpy as np
import cv2
import pandas as pd
from glob import glob
from tqdm import tqdm
import tensorflow as tf
from tensorflow.keras.utils import CustomObjectScope
from sklearn.metrics import f1_score, jaccard_score, precision_score, recall_score
from sklearn.model_selection import train_test_split
from metrics import dice_loss, dice_coef
from train import load_dataset
from unet import build_u2net_lite
""" Global parameters """
H = 256
W = 256
""" Creating a directory """
def create_dir(path):
if not os.path.exists(path):
os.makedirs(path)
def save_results(image, mask, y_pred, save_image_path):
mask = np.expand_dims(mask, axis=-1)
mask = np.concatenate([mask, mask, mask], axis=-1)
y_pred = np.expand_dims(y_pred, axis=-1)
y_pred = np.concatenate([y_pred, y_pred, y_pred], axis=-1)
y_pred = y_pred * 255
line = np.ones((H, 10, 3)) * 255
cat_images = np.concatenate([image, line, mask, line, y_pred], axis=1)
cv2.imwrite(save_image_path, cat_images)
if __name__ == "__main__":
""" Seeding """
np.random.seed(42)
tf.random.set_seed(42)
""" Directory for storing files """
create_dir("results")
""" Load the model """
with CustomObjectScope({"dice_coef": dice_coef, "dice_loss": dice_loss}):
model = tf.keras.models.load_model(os.path.join("files", "model.h5"))
""" Dataset """
dataset_path = r"C:\Users\ruthw\Dataset"
(train_x, train_y), (valid_x, valid_y), (test_x, test_y) = load_dataset(dataset_path)
""" Prediction and Evaluation """
SCORE = []
for x, y in tqdm(zip(test_x, test_y), total=len(test_y)):
""" Extracting the name """
name = x.split("/")[-1]
""" Reading the image """
image = cv2.imread(x, cv2.IMREAD_COLOR) ## [H, w, 3]
image = cv2.resize(image, (W, H)) ## [H, w, 3]
x = image/255.0 ## [H, w, 3]
x = np.expand_dims(x, axis=0) ## [1, H, w, 3]
""" Reading the mask """
mask = cv2.imread(y, cv2.IMREAD_GRAYSCALE)
mask = cv2.resize(mask, (W, H))
""" Prediction """
y_pred = model.predict(x, verbose=0)[0]
y_pred = np.squeeze(y_pred, axis=-1)
y_pred = y_pred >= 0.5
y_pred = y_pred.astype(np.int32)
""" Saving the prediction """
save_image_path = os.path.join("results", name)
save_results(image, mask, y_pred, save_image_path)
""" Flatten the array """
mask = mask/255.0
mask = (mask > 0.5).astype(np.int32).flatten()
y_pred = y_pred.flatten()
""" Calculating the metrics values """
f1_value = f1_score(mask, y_pred, labels=[0, 1], average="binary")
jac_value = jaccard_score(mask, y_pred, labels=[0, 1], average="binary")
recall_value = recall_score(mask, y_pred, labels=[0, 1], average="binary", zero_division=0)
precision_value = precision_score(mask, y_pred, labels=[0, 1], average="binary", zero_division=0)
SCORE.append([name, f1_value, jac_value, recall_value, precision_value])
""" Metrics values """
score = [s[1:]for s in SCORE]
score = np.mean(score, axis=0)
print(f"F1: {score[0]:0.5f}")
print(f"Jaccard: {score[1]:0.5f}")
print(f"Recall: {score[2]:0.5f}")
print(f"Precision: {score[3]:0.5f}")
df = pd.DataFrame(SCORE, columns=["Image", "F1", "Jaccard", "Recall", "Precision"])
df.to_csv("files/score.csv")
#%%
The error I am getting :
Traceback (most recent call last):
File "C:\Users\ruthw\Unet\test.py", line 80, in <module>
save_results(image, mask, y_pred, save_image_path)
File "C:\Users\ruthw\Unet\test.py", line 36, in save_results
cat_images = np.concatenate([image, line, mask, line, y_pred], axis=1)
File "<__array_function__ internals>", line 180, in concatenate
ValueError: all the input arrays must have same number of dimensions, but the array at index 0 has 3 dimension(s) and the array at index 4 has 4 dimension(s)
I have tried using append, rowstack and column stack function but was unable to figure out how to use them.