model.predict()有一個奇怪的輸出

這是我用過的所有檔案，唯一沒有的就是圖片

匯入檔案資料，我的資料是狗的20個樣本和貓的20個樣本

import matplotlib.pyplot as plt
import os
import cv2
import random

DIR = 'assets'
CATEGORIES = ['Cat', 'Dog']

img_size = 50

training_data = []


def create_training_data():
    for category in CATEGORIES:
        path = os.path.join(DIR, category)
        class_num = CATEGORIES.index(category)
        for img in os.listdir(path):
            img_array = cv2.imread(os.path.join(path, img), cv2.IMREAD_GRAYSCALE)
            new_array = cv2.resize(img_array, (img_size, img_size))
            training_data.append([new_array, class_num])


create_training_data()
print(len(training_data))

# Shuffle the data
random.shuffle(training_data)

x_train = []
y_train = []

for featurs, label in training_data:
    x_train.append(featurs)
    y_train.append(label)

x_train = np.asarray(x_train).reshape(-1, img_size, img_size, 1)
y_train = np.array(y_train)

import pickle

pickle_out = open('x_train.pickle', 'wb')
pickle.dump(x_train, pickle_out)
pickle_out.close()

pickle_out = open('y_train.pickle', 'wb')
pickle.dump(y_train, pickle_out)
pickle_out.close()

訓練資料

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import pickle
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
import numpy as np
from tensorflow.keras.callbacks import TensorBoard

x_train = pickle.load(open('x_train.pickle', 'rb'))
y_train = pickle.load(open('y_train.pickle', 'rb'))

x_train = x_train / 255.0

print(x_train.shape)
model = keras.Sequential(
    [
        keras.Input(shape=(50, 50, 1)),
        layers.Conv2D(32, 3, activation='relu'),
        layers.MaxPooling2D(),
        layers.Flatten(),
        layers.Dense(10)
    ]
)
# inputs = keras.Input(shape=(50, 50, 1))
# x = layers.Conv2D(32, 3)(inputs)
# x = layers.BatchNormalization()(x)
# x = keras.activations.relu(x)
# x = layers.MaxPooling2D()(x)
# x = layers.Flatten()(x)
# outputs = layers.Dense(10, activation='softmax')(x)
# model = keras.Model(inputs=inputs, outputs=outputs)

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

model.fit(x_train, y_train, batch_size=2, epochs=100, validation_split=0.1)
model.save('trained_model')

測驗資料

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import cv2
import tensorflow as tf

CATEGORIES = ['Cat', 'Dog']


def format(file_path):
    size = 50
    img_array = cv2.imread(file_path, cv2.IMREAD_GRAYSCALE)
    new_array = cv2.resize(img_array, (size, size))
    return new_array.reshape(-1, size, size, 1)

model = tf.keras.models.load_model('trained_model')

prediction = model.predict([format('dog.jpg')])
print(prediction)

上面運行，但輸出看起來像這樣。

[[  -36.40766  -1036.2589   -1382.8297   -1486.9949   -1403.7932
    -56.355995 -1364.2837   -1351.6316   -1385.2439   -1392.8472  ]]

為什么它給我這么多數字而不是簡單的 1 或 0？我期待類似 [[0.]] 或 [[1.]] 的輸出

更新：我根據建議更改了代碼，但每次都預測完全相同的事情

編輯到訓練檔案

inputs = keras.Input(shape=(50, 50, 1))
x = layers.Conv2D(16, 3)(inputs)
x = layers.BatchNormalization()(x)
x = keras.activations.relu(x)

x = layers.Conv2D(32, 3)(x)
x = layers.BatchNormalization()(x)
x = keras.activations.relu(x)

x = layers.Conv2D(64, 3)(x)
x = layers.BatchNormalization()(x)
x = keras.activations.relu(x)

x = layers.Flatten()(x)
outputs = layers.Dense(1, activation='sigmoid')(x)

model = keras.Model(inputs=inputs, outputs=outputs)

print(model.summary())
model.compile(
    loss='binary_crossentropy',
    optimizer=keras.optimizers.Adam(3e-4),
    metrics=['accuracy']
)

model.fit(x_train, y_train, batch_size=2, epochs=100, validation_split=0.1)
model.save('saved_model')

測驗檔案的編輯

import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

import cv2
import tensorflow as tf

CATEGORIES = ['Bird', 'Cat', 'Dog']


def format(file_path):
    size = 50
    img = cv2.imread(file_path, cv2.IMREAD_GRAYSCALE)
    new_img = cv2.resize(img, (size, size))
    return new_img.reshape(-1, 50, 50, 1)


model = tf.keras.models.load_model('saved_model')

prediction = model.predict([format('cat.jpg')])
prediction2 = model.predict([format('dog.jpg')])
prediction3 = model.predict([format('bird.jpg')])
print(CATEGORIES[int(prediction[0][0])])
print(CATEGORIES[int(prediction2[0][0])])
print(CATEGORIES[int(prediction3[0][0])])

即使影像完全不同，現在也會顯示輸出。

Cat
Cat
Cat 

uj5u.com熱心網友回復：

我在這里看到了兩個問題。一、定義模型時

model = keras.Sequential(
    [
        keras.Input(shape=(50, 50, 1)),
        layers.Conv2D(32, 3, activation='relu'),
        layers.MaxPooling2D(),
        layers.Flatten(),
        layers.Dense(10)
    ]
)

由于您正在處理二元分類問題，因此應指定最后一層具有像這樣的 sigmoid 激活函式layers.Dense(10, activation='sigmoid')。這將具有將輸出范圍限制為 0 到 1 的效果。

但是，這仍然會為您提供該范圍之間的數字。這是因為當你實際做出預測時

prediction = model.predict([format('dog.jpg')])
print(prediction)

您沒有將 0.5 的閾值應用于預測（低于 0.5 被歸類為 0，高于 0.5 被歸類為 1）。這可以很容易地調整prediction = (model.predict([format('dog.jpg')]) > 0.5).astype("int32")。該.astype("int32")函式是必要的，否則您的預測將是布林值。

uj5u.com熱心網友回復：

對于二元分類，您的最后一層應該只有一個輸出（而不是在您的情況下是 10），并且應該使用 sigmo?d 激活函式。然后你應該在你的模型中再添加一個步驟。那是一個提議。

model = keras.Sequential(
    [
        keras.Input(shape=(50, 50, 1)),
        layers.Conv2D(32, 3, activation='relu'),
        layers.MaxPooling2D(),
        layers.Flatten(),
        layers.Dense(10, activation='relu'),
        layers.Dense(1, activation='sigmoid')
    ]
)

標籤：张量流

上一篇：Android：如何在Android中使用tensorflowlite擴展影像尺寸

下一篇：型別錯誤：應為float32，但得到了型別為“str”的auto。Tensorflow錯誤，告訴我如何修復它？