python keras

Question

前提・実現したいこと

pythonで画像判別をしたくネットのサンプルコードを使用してkerasで学習しようとしましたところ、エラーが発生しました。

参考サイト

発生している問題・エラーメッセージ

Using TensorFlow backend.
--- 田村 を処理中
ok, 0
WARNING:tensorflow:From C:\Users\tocch\Anaconda3\envs\opencv\lib\site-packages\keras\backend\tensorflow_backend.py:74: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.

learn.py:51: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(32, (3, 3), input_shape=(), padding="same")`
  model.add(Convolution2D(32, 3, 3, border_mode='same', input_shape=in_shape))
WARNING:tensorflow:From C:\Users\tocch\Anaconda3\envs\opencv\lib\site-packages\keras\backend\tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.

Traceback (most recent call last):
  File "learn.py", line 97, in <module>
    main()
  File "learn.py", line 46, in main
    model = model_train(X_train, y_train)
  File "learn.py", line 70, in model_train
    model = build_model(X.shape[1:])
  File "learn.py", line 51, in build_model
    model.add(Convolution2D(32, 3, 3, border_mode='same', input_shape=in_shape))
  File "C:\Users\tocch\Anaconda3\envs\opencv\lib\site-packages\keras\engine\sequential.py", line 165, in add
    layer(x)
  File "C:\Users\tocch\Anaconda3\envs\opencv\lib\site-packages\keras\engine\base_layer.py", line 414, in __call__
    self.assert_input_compatibility(inputs)
  File "C:\Users\tocch\Anaconda3\envs\opencv\lib\site-packages\keras\engine\base_layer.py", line 311, in assert_input_compatibility
    str(K.ndim(x)))
ValueError: Input 0 is incompatible with layer conv2d_1: expected ndim=4, found ndim=1 

該当のソースコード

# -*- coding: utf-8 -*-
from sklearn.model_selection import train_test_split
from keras.preprocessing.image import load_img, img_to_array
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils
import os, glob
import numpy as np
import matplotlib.pyplot as plt

root_dir = "C://Users//tocch//Desktop//face_認証//学習用"
categories = ["田村"]
nb_classes = len(categories)
image_size = 64

# CNN設定
BATCH_SIZE = 32
EPOCHS = 15

def init():
    X = []
    Y = []
    for idx, cat in enumerate(categories):
        files = glob.glob(root_dir + "/" + cat + "/_trimming/*")
        print("---", cat, "を処理中")
        for i, f in enumerate(files):
            img = load_img(f, target_size=(image_size,image_size))
            data = img_to_array(img)
            X.append(data)
            Y.append(idx)
    X = np.array(X)
    Y = np.array(Y)

    X_train, X_test, y_train, y_test = train_test_split(X, Y)
    xy = (X_train, X_test, y_train, y_test)
    np.save(root_dir + "//npy/face.npy", xy)
    print("ok,", len(Y))

def main():
    X_train, X_test, y_train, y_test = np.load(root_dir + "/npy/face.npy")
    X_train = X_train.astype("float") / 256
    X_test  = X_test.astype("float")  / 256
    y_train = np_utils.to_categorical(y_train, nb_classes)
    y_test  = np_utils.to_categorical(y_test, nb_classes)
    model = model_train(X_train, y_train)
    model_eval(model, X_test, y_test)

def build_model(in_shape):
    model = Sequential()
    model.add(Convolution2D(32, 3, 3, border_mode='same', input_shape=in_shape))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))
    model.add(Convolution2D(64, 3, 3, border_mode='same'))
    model.add(Activation('relu'))
    model.add(Convolution2D(64, 3, 3))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))
    model.add(Flatten())
    model.add(Dense(512))
    model.add(Activation('relu'))
    model.add(Dropout(0.5))
    model.add(Dense(nb_classes))
    model.add(Activation('softmax'))
    model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
    return model

def model_train(X, y):
    model = build_model(X.shape[1:])
    #history = model.fit(X, y, batch_size=BATCH_SIZE, nb_epoch=EPOCHS, validation_split=0.1)
    history = model.fit(X, y, batch_size=BATCH_SIZE, nb_epoch=EPOCHS, validation_split=0.1)

    json_string = model.to_json()
    open(os.path.join(root_dir + '/h5/cnn_model.json'), 'w').write(json_string)
    model.save_weights(root_dir + "/h5/face-model.h5")

    # グラフ表示
    plt.plot(range(1, EPOCHS + 1), history.history['acc'], label = "train-acc")
    plt.plot(range(1, EPOCHS + 1), history.history['loss'], label = "train-loss")
    plt.plot(range(1, EPOCHS + 1), history.history['val_acc'], label = "val-acc")
    plt.plot(range(1, EPOCHS + 1), history.history['val_loss'], label = "val-loss")
    plt.title('list')
    plt.xlabel('Epochs')
    plt.ylabel('Accuracy')
    plt.legend()
    plt.show()
    return model

def model_eval(model, X, y):
    score = model.evaluate(X, y)
    print('loss=', score[0])
    print('accuracy=', score[1])

if __name__ == "__main__":
    init()
    main()

補足情報（FW/ツールのバージョンなど）

ここにより詳細な情報を記載してください。

Comments

[meg_]

リンクは「リンクの挿入｣で記入しましょう。

[退会済みユーザー]

ああああああああああああああああああああああああああああああああああああああ

Answer 1

かいけつできました。

Comments

[fiveHundred]

具体的な解決手順を記載してください。