将 Conv2D 用于图像有什么问题？

Question

首先我从文件夹和子文件夹中读取图片。然后我将图像更改为灰色并将大小调整为 100*200。我想将我的图像分类为 6 类。 当我想创建我的模型时，我不能使用 Conv2D，因为我有尺寸错误，但是当我使用 Conv1D 时，我没有任何错误并且神经网络正常工作。 我想使用 conv2D 因为我的数据是图像。我的问题是什么？

#load train_images
path_spec_train = "/home/narges/dataset/train_24/"
spec_train = glob.glob(path_spec_train + "**/*.png") 
spec_train.sort()

X_modify = []
width = 200
height = 100
for spec in spec_train:
    specs = cv2.imread(spec)
    specs = cv2.cvtColor(specs,cv2.COLOR_BGR2GRAY)
    specs = cv2.resize(specs ,(width, height))
    specs = specs / np.max(specs)
    specs = specs.astype(np.float32)
    X_modify.append(specs)

X_train = np.asarray(X_modify,dtype=np.float32)

#=======================================================
#load test_image

path_spec_test = "/home/narges/dataset/test_24/"
spec_test = glob.glob(path_spec_test + "**/*.png") 
spec_test.sort()

X_modify_t = []
width = 200
height = 100
for spec_t in spec_test:
    specs_test = cv2.imread(spec_t)
    specs_test = cv2.cvtColor(specs_test,cv2.COLOR_BGR2GRAY)
    specs_test = cv2.resize(specs_test ,(width, height))
    specs_test = specs_test / np.max(specs_test)
    specs_test = specs_test.astype(np.float32)
    X_modify_t.append(specs_test)

X_test = np.asarray(X_modify_t,dtype=np.float32)
#======================================================================
#label

spk_ID = [wavs[i].split('/')[-1].lower() for i in range(number_of_files)]

spk_ID_t = [wavs_t[i].split('/')[-1].lower() for i in range(number_of_files_t)]

label_no = [spk_ID[i].split('_')[-2] for i in range(number_of_files)]

Y_train = np_utils.to_categorical(label_no)

label_no_t = [spk_ID_t[i].split('_')[-2] for i in range(number_of_files_t)]

Y_test = np_utils.to_categorical(label_no_t)


#======================================================================
# Create my model
myinput = layers.Input(shape=(100,200))
conv1 = layers.Conv1D(32, 3, activation='relu', padding='same', strides=2)(myinput)
conv2 = layers.Conv1D(64, 3, activation='relu', padding='same', strides=2)(conv1)
flat = layers.Flatten()(conv2)
out_layer = layers.Dense(6, activation='softmax')(flat)
mymodel = Model(myinput, out_layer)
mymodel.summary()

mymodel.compile(optimizer=keras.optimizers.Adam(), loss=keras.losses.categorical_crossentropy, metrics=['accuracy'])

network_history = mymodel.fit(X_train, Y_train, batch_size=128, epochs=100)

pred = np.round(mymodel.predict(X_test))
print(classification_report(Y_test, pred))

Answer 1

您需要将渠道维度添加到您的输入训练数据中：

import numpy as np

X_train = np.expand_dims(X_train, axis=3)
X_test = np.expand_Dims(X_test, axis=3)

那么你的数据就会是4D的，比如(3312, 100, 200, 1)，就是灰度图（一个通道）。