错误 "IndexError: 如何在Keras中使用训练好的模型预测输入图像?

我训练了一个模型来对9个类的图像进行分类,并使用model.save()将其保存。下面是我使用的代码。

from keras.applications.resnet50 import ResNet50, preprocess_input
from keras.layers import Dense, Dropout
from keras.models import Model
from keras.optimizers import Adam, SGD
from keras.preprocessing.image import ImageDataGenerator, image
from keras.callbacks import EarlyStopping, ModelCheckpoint
from sklearn.metrics import confusion_matrix, classification_report, accuracy_score
from keras import backend as K
import numpy as np
import matplotlib.pyplot as plt
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGE = True

# Define some constant needed throughout the script
N_CLASSES = 9
EPOCHS = 2
PATIENCE = 5
TRAIN_PATH= '/Datasets/Train/'
VALID_PATH = '/Datasets/Test/'
MODEL_CHECK_WEIGHT_NAME = 'resnet_monki_v1_chk.h5'



# Define model to be used we freeze the pre trained resnet model weight, and add few layer on top of it to utilize our custom dataset
K.set_learning_phase(0)
model = ResNet50(input_shape=(224,224,3),include_top=False, weights='imagenet', pooling='avg')
K.set_learning_phase(1)
x = model.output
x = Dense(512, activation='relu')(x)
x = Dropout(0.5)(x)
x = Dense(512, activation='relu')(x)
x = Dropout(0.5)(x)
output = Dense(N_CLASSES, activation='softmax', name='custom_output')(x)
custom_resnet = Model(inputs=model.input, outputs = output)

for layer in model.layers:
    layer.trainable = False

custom_resnet.compile(Adam(lr=0.001), loss='categorical_crossentropy', metrics=['accuracy'])
custom_resnet.summary()



# 4. Load dataset to be used
datagen = ImageDataGenerator(preprocessing_function=preprocess_input)
traingen = datagen.flow_from_directory(TRAIN_PATH, target_size=(224,224), batch_size=32, class_mode='categorical')
validgen = datagen.flow_from_directory(VALID_PATH, target_size=(224,224), batch_size=32, class_mode='categorical', shuffle=False)


# 5. Train Model we use ModelCheckpoint to save the best model based on validation accuracy
es_callback = EarlyStopping(monitor='val_acc', patience=PATIENCE, mode='max')
mc_callback = ModelCheckpoint(filepath=MODEL_CHECK_WEIGHT_NAME, monitor='val_acc', save_best_only=True, mode='max')
train_history = custom_resnet.fit_generator(traingen, steps_per_epoch=len(traingen), epochs= EPOCHS, validation_data=traingen, validation_steps=len(validgen), verbose=2, callbacks=[es_callback, mc_callback])


model.save('custom_resnet.h5')

训练成功了 为了在新图像上加载和测试该模型,我使用了以下代码。

from keras.models import load_model
import cv2
import numpy as np

class_names = ['A', 'B', 'C', 'D', 'E','F', 'G', 'H', 'R']

model = load_model('custom_resnet.h5')

model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

img = cv2.imread('/path to image/4.jpg')
img = cv2.resize(img,(224,224))
img = np.reshape(img,[1,224,224,3])

classes = np.argmax(model.predict(img), axis = -1)

print(classes)

它的输出结果是: [1915]

[1915]

为什么不会给出班级的实际值,为什么指数太大?我只有9个类!

我只有9个类!谢谢

解决方案:

你保存了原始的resnet_base而不是你的自定义模型。

您做了 model.save('custom_resnet.h5')

但是.., model = ResNet50(input_shape=(224,224,3),include_top=False, weights='imagenet', pooling='avg')

您需要在保存custom_resnet模型时,用 custom_resnet.save('custom_resnet.h5')

这就是为什么当你使用predict时,你得到的是(12048)个形状的特征而不是实际的预测。

更新的代码。

from keras.applications.resnet50 import ResNet50, preprocess_input
from keras.layers import Dense, Dropout
from keras.models import Model
from keras.optimizers import Adam, SGD
from keras.preprocessing.image import ImageDataGenerator, image
from keras.callbacks import EarlyStopping, ModelCheckpoint
from sklearn.metrics import confusion_matrix, classification_report, accuracy_score
from keras import backend as K
import numpy as np
import matplotlib.pyplot as plt
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGE = True

# Define some constant needed throughout the script
N_CLASSES = 9
EPOCHS = 2
PATIENCE = 5
TRAIN_PATH= '/Datasets/Train/'
VALID_PATH = '/Datasets/Test/'
MODEL_CHECK_WEIGHT_NAME = 'resnet_monki_v1_chk.h5'



# Define model to be used we freeze the pre trained resnet model weight, and add few layer on top of it to utilize our custom dataset
K.set_learning_phase(0)
model = ResNet50(input_shape=(224,224,3),include_top=False, weights='imagenet', pooling='avg')
K.set_learning_phase(1)
x = model.output
x = Dense(512, activation='relu')(x)
x = Dropout(0.5)(x)
x = Dense(512, activation='relu')(x)
x = Dropout(0.5)(x)
output = Dense(N_CLASSES, activation='softmax', name='custom_output')(x)
custom_resnet = Model(inputs=model.input, outputs = output)

for layer in model.layers:
    layer.trainable = False

custom_resnet.compile(Adam(lr=0.001), loss='categorical_crossentropy', metrics=['accuracy'])
custom_resnet.summary()



# 4. Load dataset to be used
datagen = ImageDataGenerator(preprocessing_function=preprocess_input)
traingen = datagen.flow_from_directory(TRAIN_PATH, target_size=(224,224), batch_size=32, class_mode='categorical')
validgen = datagen.flow_from_directory(VALID_PATH, target_size=(224,224), batch_size=32, class_mode='categorical', shuffle=False)


# 5. Train Model we use ModelCheckpoint to save the best model based on validation accuracy
es_callback = EarlyStopping(monitor='val_acc', patience=PATIENCE, mode='max')
mc_callback = ModelCheckpoint(filepath=MODEL_CHECK_WEIGHT_NAME, monitor='val_acc', save_best_only=True, mode='max')
train_history = custom_resnet.fit_generator(traingen, steps_per_epoch=len(traingen), epochs= EPOCHS, validation_data=traingen, validation_steps=len(validgen), verbose=2, callbacks=[es_callback, mc_callback])


custom_resnet.save('custom_resnet.h5')

推理代码:

from keras.models import load_model
import cv2
import numpy as np

class_names = ['A', 'B', 'C', 'D', 'E','F', 'G', 'H', 'R']

model = load_model('custom_resnet.h5')

model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

img = cv2.imread('/path to image/4.jpg')
img = cv2.resize(img,(224,224))
img = np.reshape(img,[1,224,224,3])

classes = np.argmax(model.predict(img), axis = -1)

print(classes)

给TA打赏
共{{data.count}}人
人已打赏
解决方案

如何在使用ActionListener按钮和GUI时向数组列表中添加项目?

2022-4-22 18:08:53

解决方案

在ngFor中使用ngfire2的firebase-src指令失败。

2022-4-22 18:08:55

0 条回复 A文章作者 M管理员
    暂无讨论,说说你的看法吧
个人中心
购物车
优惠劵
今日签到
有新私信 私信列表
搜索