KERAS 低擬合損失和高損失評估

Question

我是 keras 的新手。 該代碼正在對有或沒有腫瘤的大腦的 MRI 圖像進行分類。 當我運行model.evaluate()以查看准確性時，即使在訓練模型時損失值很低（正常小於 1），我也會得到非常高的損失值，並且出現以下錯誤：

WARNING:tensorflow:6 out of the last 11 calls to <function Model.make_test_function.<locals>.test_function at 0x00000221AC143AF0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.

大部分代碼都是從這個鏈接復制而來的。

這是完整的代碼：

import numpy as np
import matplotlib.pyplot as plt
import os
import cv2

import tensorflow as tf
from tensorflow.keras.datasets import cifar10
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten
from tensorflow.keras.layers import Conv2D, MaxPooling2D

def load_data( DATADIR, IMG_SIZE, CATEGORIES ):
    data = []
    for category in CATEGORIES:  # do dogs and cats
        
        path = os.path.join(DATADIR,category)  # create path to dogs and cats
        class_num = CATEGORIES.index(category)  # get the classification  (0 or a 1). 0=dog 1=cat

        for img in os.listdir(path):  # iterate over each image per dogs and cats
            try:
                img_array = cv2.imread(os.path.join(path,img) ,cv2.IMREAD_GRAYSCALE)  # convert to array
                
                img_array = cv2.medianBlur(img_array,5)
                
                img_array = cv2.adaptiveThreshold(img_array,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C,cv2.THRESH_BINARY,11,2)
                
                new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))  # resize to normalize data size
                
                data.append([new_array, class_num])  # add this to our training_data
            except Exception as e:  # in the interest in keeping the output clean...
                pass
            #except OSError as e:
            #    print("OSErrroBad img most likely", e, os.path.join(path,img))
            #except Exception as e:
            #    print("general exception", e, os.path.join(path,img))
    return data

TRAIN_DATADIR = "F:\Train"
TEST_DATADIR = "F:\Test"

CATEGORIES = ["no", "yes"]
IMG_SIZE = 128
training_data = load_data(TRAIN_DATADIR, IMG_SIZE, CATEGORIES)
testing_data = load_data(TEST_DATADIR, IMG_SIZE, CATEGORIES)

print(len(training_data))

import random
random.shuffle(training_data)
random.shuffle(testing_data)

X_train = []
y_train = []

for features,label in training_data:
    X_train.append(features)
    y_train.append(label)

#print(X[0].reshape(-1, IMG_SIZE, IMG_SIZE, 1))

X_train = np.asarray(X_train)
y_train = np.asarray(y_train)

X_train = np.array(X_train).reshape(-1, IMG_SIZE, IMG_SIZE, 1)


X_test = []
y_test = []

for features,label in testing_data:
    X_test.append(features)
    y_test.append(label)

    
X_test = np.asarray(X_test)
y_test = np.asarray(y_test)
#print(X[0].reshape(-1, IMG_SIZE, IMG_SIZE, 1))

X_test = np.array(X_test).reshape(-1, IMG_SIZE, IMG_SIZE, 1)

X_train = X_train/255.0


model = Sequential()

model.add(Conv2D(32, (3, 3), input_shape = X_train.shape[1:]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(1))
model.add(Activation('sigmoid'))

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

model.fit(X_train, y_train, batch_size=10, epochs=15)

score = model.evaluate(X_test, y_test,verbose=1)

Answer 1

忽略警告。

您的低訓練損失和高評估損失意味着您的 model 過度擬合。 當您的驗證准確性開始增加時停止訓練。