Q&A
エラーの原因とこのCNNのプログラムの詳しい仕組みを知りたいです。
先輩から頂いたプログラムをanaconda promptで動かして、パソコンの画像フォルダに入っている画像の処理をしようとしているのですが、学習がされていなかったり、プログラムをいじる内にエラーが発生したりと、なさけないのですが分からないことだらけです。たたみ込みやプーリングなどの仕組みはざっくりと分かるのですが、プログラムに書かれているコードの一つ一つがどういう役割・意味を持って要るのかが分かりません。
発生している問題・エラーメッセージ
ValueError: Cannot feed value of shape (32, 28, 28) for Tensor 'input/inputs:0', which has shape '(?, 28, 28, 1)'
該当のソースコード
# coding: utf-8 # In[10]: import os import glob import sys import cv2 import tensorflow as tf import numpy as np import pandas as pd from numpy.random import permutation import time image_size = 28#次元 image_channnel = 1 imgpx = image_size * image_size * image_channnel#画像サイズ category = 6 np.random.seed(1) flags = tf.app.flags FLAGS = flags.FLAGS flags.DEFINE_string('log_path', '/tmp/cnn/', 'Directory to put the training data') flags.DEFINE_string('save_name', os.getcwd() + '/var.ckpt', 'path to save variables') flags.DEFINE_integer('max_steps', 200, 'Number of steps to run trainer') flags.DEFINE_integer('batch_size', 32, '') flags.DEFINE_integer('training_epoch', 100, '') flags.DEFINE_integer('validation_interval', 10, 'validation interval') flags.DEFINE_float('learning_rate', 1e-4, 'Initial learning rate') flags.DEFINE_float('dropout_keep_prob', 0.5, '') def next_batch(data, label, batch_size): perm = np.arange(data.shape[0]) np.random.shuffle(perm) return data[perm][:batch_size], label[perm][:batch_size] def input_placeholder(size, channel, label): with tf.name_scope('input') as scope: inputs = tf.placeholder("float", [None, size, size, channel], 'inputs') labels = tf.placeholder("float", [None, label], 'labels') dropout_keep_prob = tf.placeholder("float", None, 'keep_prob') learning_rate = tf.placeholder("float", None, name='learning_rate') return inputs, labels, dropout_keep_prob, learning_rate def get_im(path): # reading imagefile and resizing img = cv2.imread(path, 0) resize = cv2.resize(img, (image_size, image_size)) return resize def read_train_data(ho=0): # read train and validation data train_data = [] train_target = [] for j in range(3, 6): path = 'c:/Users/mitsutaka/Documents/resize/data2/%i/*.png'%(j)# files = sorted(glob.glob(path)) for fl in files: flbase = os.path.basename(fl) img = get_im(fl) img = np.array(img, dtype=np.float32) img -= np.mean(img) img /= np.std(img) tmp = np.zeros(3) tmp[int(j-3)] = 1 train_data.append(img) train_target.append(tmp) train_data = np.array(train_data, dtype=np.float32) train_target = np.array(train_target, dtype=np.uint8) # shuffle #perm = permutation(len(train_target))#permutation:シャッフル #train_data = train_data[perm] #train_target = train_target[perm] return train_data, train_target def read_test_data(test_class): path = 'c:/Users/mitsutaka/Documents/%i/*.png'%(test_class)# files = sorted(glob.glob(path)) X_test = [] X_test_id = [] for fl in files: flbase = os.path.basename(fl) img = get_im(fl)#画像データの取得 img = np.array(img, dtype=np.float32) img -= np.mean(img)#mean:平均 img /= np.std(img)#std：標準偏差 X_test.append(img) X_test_id.append(flbase) test_data = np.array(X_test, dtype=np.float32) return test_data, X_test_id def inference(images_placeholder, keep_prob): def weight(shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial) def bias(shape): initial = tf.zeros(shape) return tf.Variable(initial) def conv2d(x, W):#strides幅, padding余白 return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME') def MaxPooling(x):#tensorflow-APIより使用, 最大値を抽出 return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides =[1, 2, 2, 1], padding='SAME')#[1, 2, 2, 1]は2*2の意味 （[1, 3, 3, 1]は3*3の意味） x_image = tf.reshape(images_placeholder, [-1, image_size, image_size, image_channnel]) tf.summary.image('input', x_image, 10) #全結合層 with tf.name_scope('Convolution1') as scope:#畳み込み1層目 W_conv1 = weight([3, 3, image_channnel, 32]) b_conv1 = bias([32])#バイアス加算 h_conv1 = tf.nn.relu(conv2d(images_placeholder, W_conv1) + b_conv1) with tf.name_scope('Convolution2') as scope: W_conv2 = weight([3, 3, 32, 32]) b_conv2 = bias([32]) h_conv2 = tf.nn.relu(conv2d(h_conv1, W_conv2) + b_conv2) with tf.name_scope('Pooling1') as scope: h_pool1 = MaxPooling(h_conv2) with tf.name_scope('FullyConnected1') as scope: flat = tf.contrib.layers.flatten(h_pool1) tensor_shape = flat.get_shape().as_list() W_fc1 = weight([tensor_shape[1], 1024]) b_fc1 = bias([1024]) h_fc1 = tf.nn.relu(tf.matmul(flat, W_fc1) + b_fc1) h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) with tf.name_scope('FullyConnected2') as scope: W_fc2 = weight([1024, 1024]) b_fc2 = bias([1024]) h_fc2 = tf.nn.relu(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) h_fc2_drop = tf.nn.dropout(h_fc2, keep_prob) with tf.name_scope('SoftMax') as scope: W_sf = weight([1024, 3]) b_sf = bias([3]) y = tf.nn.softmax(tf.matmul(h_fc2_drop, W_sf) + b_sf) return y def loss(logits, labels): with tf.name_scope('loss'): loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = logits, labels = labels)) tf.summary.scalar('loss', loss) return loss def training(loss, learning_rate): train_step = tf.train.AdamOptimizer(learning_rate).minimize(loss) return train_step def accuracy(logits, labels): with tf.name_scope('accuracy'): correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(labels, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) tf.summary.scalar('accuracy', accuracy) return accuracy def train(): inputs, labels, dropout_keep_prob, learning_rate =input_placeholder(image_size, image_channnel, 3) logits = inference(inputs, dropout_keep_prob) acc = accuracy(logits, labels) loss_value = loss(logits, labels) train = training(loss_value, learning_rate) sess = tf.Session() sess.run(tf.global_variables_initializer()) merged = tf.summary.merge_all() train_writer = tf.summary.FileWriter(FLAGS.log_path + '/train/', sess.graph) validation_writer = tf.summary.FileWriter(FLAGS.log_path + '/validation/') saver = tf.train.Saver() if os.path.isfile(FLAGS.save_name): saver.restore(sess, FLAGS.save_name) ho = 0 train_dataset, train_labels = read_train_data(ho) validation_dataset, validation_labels = read_train_data(ho) i=0 print("Initialized") cur_learning_rate = FLAGS.learning_rate # 処理前の時刻 t1 = time.time() for epoch in range(FLAGS.training_epoch): step = 0 if epoch % 10 == 0 and epoch > 0: cur_learning_rate /= 10 for start, end in zip(range(0, len(train_dataset), FLAGS.batch_size), range(FLAGS.batch_size, len(train_dataset), FLAGS.batch_size)): step += 1 batch_data = train_dataset[start:end] batch_labels = train_labels[start:end] print(step) feed_dict_batch ={inputs: batch_data, labels: batch_labels, dropout_keep_prob: FLAGS.dropout_keep_prob, learning_rate: cur_learning_rate} if i% FLAGS.validation_interval == 0: summary, _, loss_batch, acc_batch = sess.run([merged, train, loss_value, acc], feed_dict=feed_dict_batch) train_writer.add_summary(summary, i) summary_valid, loss_valid, acc_valid = sess.run([merged, loss_value, acc], feed_dict={inputs: validation_dataset, labels: np.squeeze(validation_labels), dropout_keep_prob: 1.0}) validation_writer.add_summary(summary_valid, i) print('----------------------------------') print('epoch:', epoch + 1, ', step:', step) print("Batch loss: {:.2f}".format(loss_batch)) print("Batch accuracy: {0:.01%}".format(acc_batch)) print("Validation loss: {:.2f}".format(loss_valid)) print("Validation acuuracy: {0:.01%}".format(acc_valid)) else: sess.run(train, feed_dict=feed_dict_batch) i+=1 # 処理後の時刻 t2 = time.time() # 経過時間を表示 elapsed_time = t2-t1 print(f"経過時間：{elapsed_time}") train_writer.close() validation_writer.close() if __name__ == '__main__': param = sys.argv run_type = param[1] if run_type == 'train': train()
試したこと
ライブラリを変えたりプログラムの書き換えなども行いましたが、コレをいじるとどう変わるのかが理解し切れていません・・・。参考書やサンプルコードを利用してもエラーばかりでどうにも出来ない状況です。
補足情報（FW/ツールのバージョンなど）
tensorflowは1.10で実施しています
回答1件
0
ベストアンサー
入力層に与えるデータは形状が (?, 28, 28, 1) を期待されているのに、(32, 28, 28) となっているというエラーです。
おそらく形状が (28, 28) のグレースケール画像を流そうとしてエラーとなっているので、
np.expand_dims(x, axis=-1) で (32, 28, 28) を (32, 28, 28, 1) にしてください。
投稿2018/10/17 08:19
編集2018/10/17 08:19
総合スコア21956
あなたの回答
tips
プレビュー
バッドをするには、ログインかつ
こちらの条件を満たす必要があります。
2018/10/17 09:12
2018/10/17 12:47 編集
2018/10/17 14:07