python - 训练中的 TensorFlow 错误：tensorflow.python.framework.errors_impl.InvalidArgumentError

Question

我一直在尝试使用 CNN 训练一个模型来检测照片中的猫。我一直在使用这些数据集：

1. https://www.kaggle.com/shaunthesheep/microsoft-catsvsdogs-dataset
2. https://www.kaggle.com/balraj98/facades-dataset

我一直收到此错误：

tensorflow.python.framework.errors_impl.InvalidArgumentError:  Input size should match (header_size + row_size * abs_height) but they differ by 2
     [[{{node decode_image/DecodeImage}}]]
     [[IteratorGetNext]] [Op:__inference_train_function_962]

Function call stack:
train_function

这是代码（我从早期项目中重用并调整了它）：

import matplotlib.pyplot as plt

import numpy as np
import os
import PIL 
import tensorflow as tf

from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential


batch_size = 64
img_height = 180
img_width = 180





train_ds = tf.keras.preprocessing.image_dataset_from_directory(
  "D://datasets and work//archive(2)//PetImages",
  validation_split=0.2,

  subset="training",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)

val_ds = tf.keras.preprocessing.image_dataset_from_directory(
  "D://datasets and work//archive(2)//PetImages",
  validation_split=0.2,

  subset="validation",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)



class_names = train_ds.class_names
print(class_names)
AUTOTUNE = tf.data.AUTOTUNE

train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)

num_classes = 2
data_augmentation = tf.keras.Sequential([
  layers.experimental.preprocessing.RandomZoom(0.1)
])

# horizontal image flipping is ok, chexnet did it;implement it later, Sahal
model = Sequential([
  layers.experimental.preprocessing.Rescaling(1./255),
  layers.Conv2D(32, 2, padding='same', activation='relu'),
  layers.MaxPooling2D(pool_size=(2, 2), strides=(1, 1), padding='valid'),
  layers.Conv2D(32, 2, padding='same', activation='relu'),
  layers.MaxPooling2D(pool_size=(2, 2), strides=(1, 1), padding='valid'),
  layers.Conv2D(64, 2, padding='same', activation='relu'),
  layers.MaxPooling2D(pool_size=(2, 2), strides=(1, 1), padding='valid'),
  layers.Conv2D(8, 2, padding='same', activation='relu'),
#  layers.Dropout(0.1),
  layers.Flatten(),
  layers.Dense(128, activation='relu'),
  layers.Dense(num_classes)
])

model.compile(optimizer=tf.optimizers.Adam(learning_rate=0.01),
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits = True),
              metrics=['accuracy'])

epochs=10
history = model.fit(
  train_ds,
  validation_data=val_ds,
  epochs=epochs
)

（我使用的是 TensorFlow 2.4.0 版和 Python 3.8.7 版）

标签： pythontensorflowmachine-learningdeep-learningtensorflow2.0