No such file or directory: 'Image'

Question

import tensorflow as tf
from matplotlib import pyplot as plt
import numpy as np
from PIL import Image
import os
np.set_printoptions(threshold = np.inf)
# 自制训练集（jpg，txt）
def generated(path,txt):
    f = open(txt,'r')
    contents = f.readlines()
    f.close()
    x,y_ = [],[]
    for content in contents:
        value = content.split()
        img_path = path = value[0]
        img = Image.open(img_path)
        img = np.array(img.convert('L'))
        img = img/255.
        x.append(img)
        y_.append(value[1])
        print('loading :'+content)

    x=np.array(x)
    y_ = np.array(y_)
    y_ = y_.astype(np.int64)
    return x,y_

# 定义数据路径
train_path = './dataset/Original Images/dataset_train_jpg/'
train_txt = './dataset/Groundtruths/dataset_train_jpg.txt'
x_train_savepath = './dataset/dataset_x_train.npy'
y_train_savepath = './dataset/dataset_y_train.npy'

test_path = './dataset/Original Images/dataset_test_jpg/'
test_txt = './dataset/Groundtruths/dataset_test_jpg.txt'
x_test_savepath = './dataset/dataset_x_test.npy'
y_test_savepath = './dataset/dataset_y_test.npy'

if os.path.exists(x_train_savepath) and os.path.exists(y_train_savepath) and os.path.exists(x_test_savepath) and os.path.exists(y_test_savepath):
    print('Load Datasets')
    x_train_save = np.load(x_train_savepath)
    y_train = np.load(y_train_savepath)
    x_test_save = np.load(x_test_savepath)
    y_test = np.load(x_test_savepath)
    x_train = np.reshape(x_train_save,(len(x_train_save),4288,2848))
    x_test = np.reshape(x_test_save, (len(x_test_save), 4288, 2848))
else:
    print('Generate Datasets')
    x_train, y_train = generated(train_path, train_txt)
    x_test, y_test = generated(test_path, test_txt)

    print('save Datasets')
    x_train_save = np.reshape(x_train, (len(x_train),-1))
    x_test_save = np.reshape(x_test, (len(x_test), -1))
    np.save(x_train_savepath, x_train_save)
    np.save(x_train_savepath, y_train)
    np.save(x_test_savepath, x_test_save)
    np.save(y_test_savepath,y_test)

# 神经网搭建
model = tf.keras.models.Sequential(
    # 第一层卷积
    tf.keras.layers.Con2D(filter=96, kernel_size=(3,3),padding='valid'),
    tf.keras.layers.BatchNormalization(),
    tf.keras.layers.Con2D(filter=128, kernel_size=(3,3),padding='valid'),
    tf.keras.layers.BatchNormalization(),
    tf.keras.layers.Conv2D(filter=256, kernel_size=(3,3),padding='same'),
    tf.keras.layers.BatchNormalization(),
    tf.keras.layers.Activation('sigmoid'),
    tf.keras.layers.AveragePooling2D(pool_size=(5,5),padding='valid'),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(256,activation='relu'),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Dense(96,activation='relu'),
    tf.keras.layers.Dense(20,activation='relu'),
    tf.keras.layers.Dense(5,activation='softmax')
)

model.compile(optimizer='nadam',loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),metrics=['sparse_categorical_accuracy'])

checkpoint_save_path = './checkpoint.ckpt'
if os.path.exists(checkpoint_save_path+'index'):
    print('load the model')
    model.load_weights(checkpoint_save_path)

cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath = checkpoint_save_path,save_weights_only=True,save_best_only=True)
history = model.fit(x_train,y_train, batch_size=32,epochs=10000, validation_data=(x_test,y_test), validation_freq=1,callbacks=[cp_callback])
model.summary()

print(model.trainable_variables)
file = open('./numtext.txt','w')
for v in model.trainable_variables:
    file.write(str(v.name)+'\n')
    file.write(str(v.shape)+'\n')
    file.write(str(v.numpy())+'\n')
file.close()

acc = history.history['sparse_categorical_accuracy']
val_acc = history.history['val_sparse_categorical_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']

plt.subplot(1, 2, 1)
plt.plot(acc, label='Training Accuracy')
plt.plot(val_acc, label="Validation Accuracy")
plt.title('Training and Validation Accuracy')
plt.legend()

plt.subplot(1, 2, 2)
plt.plot(loss, label='Training Loss')
plt.plot(val_loss, label="Validation Loss")
plt.title('Training and Validation Loss')
plt.legend()

plt.show()

这段代码，报[Errno 2] No such file or directory: 'Image'，怎么处理啊

Answer 1

中午好🌞🌞🌞
本答案参考ChatGPT-3.5

The error message "No such file or directory: 'Image'" suggests that you're trying to load an image using TensorFlow, but the file doesn't exist. This could be due to a number of reasons, including the incorrect file path, the file not being in the expected location, or the image file not being saved in the correct format.

Here's some sample code to help you locate and fix the issue:

# Find the file path
image_file_path = 'dataset/image.jpg'
# Check if the file exists
if os.path.isfile(image_file_path):
    # Load the image
    img = Image.open(image_file_path)
    
    # Convert the image from JPEG format to PNG format
    img = img.convert('RGB').convert('PNG')
else:
    print(f"The file {image_file_path} does not exist.")

In this example, we first find the file path of the image we want to use. If the file exists, we then try to load it using Image.open() function. We convert the image from JPEG format to PNG format using img.convert() method before saving it back to the same format. If the file doesn't exist, we print an error message indicating so.

If the code still returns errors after trying these steps, it may indicate that there are other issues with your training data, such as missing files or invalid images. In this case, you may need to gather more information about your dataset and the specific steps you took to generate it, and adjust the code accordingly.