編集履歴

質問編集履歴

文法の修正

2020/07/01 06:58

投稿

koukiten

スコア6

test CHANGED Viewed

File without changes

test CHANGED Viewed

@@ -44,23 +44,7 @@
 path_one=path + '/パス/one'
-path_two=path + '/パス/two'
-path_three=path + '/パス/three'
-path_four=path + '/パス/four'
-path_five=path + '/パス/five'
-path_six=path + '/パス/six'
-path_seven=path + '/パス/seven'
-path_eight=path + '/パス/eight'
-path_nine=path + '/パス/nine'
-path_zero=path + '/パス/zero'
 in_size=(28,28)
@@ -69,24 +53,6 @@
 file_1=glob.glob(path_one +'/*.jpg')
-file_2=glob.glob(path_two +'/*.jpg')
-file_3=glob.glob(path_three +'/*.jpg')
-file_4=glob.glob(path_four +'/*.jpg')
-file_5=glob.glob(path_five +'/*.jpg')
-file_6=glob.glob(path_six +'/*.jpg')
-file_7=glob.glob(path_seven +'/*.jpg')
-file_8=glob.glob(path_eight +'/*.jpg')
-file_9=glob.glob(path_nine +'/*.jpg')
-file_0=glob.glob(path_zero +'/*.jpg')
@@ -120,250 +86,6 @@
-def load_dir_2(path,label):
-    for i in file_2:
-        img=cv2.imread(i)
-        img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
-        img=cv2.resize(img,in_size)
-        img=img/255.0
-        x.append(img)
-        y.append(label)
-    return [x,y]
-def load_dir_3(path,label):
-    for i in file_3:
-        img=cv2.imread(i)
-        img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
-        img=cv2.resize(img,in_size)
-        img=img/255.0
-        x.append(img)
-        y.append(label)
-    return [x,y]
-def load_dir_4(path,label):
-    for i in file_4:
-        img=cv2.imread(i)
-        img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
-        img=cv2.resize(img,in_size)
-        img=img/255.0
-        x.append(img)
-        y.append(label)
-    return [x,y]
-def load_dir_5(path,label):
-    for i in file_5:
-        img=cv2.imread(i)
-        img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
-        img=cv2.resize(img,in_size)
-        img=img/255.0
-        x.append(img)
-        y.append(label)
-    return [x,y]
-def load_dir_6(path,label):
-    for i in file_6:
-        img=cv2.imread(i)
-        img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
-        img=cv2.resize(img,in_size)
-        img=img/255.0
-        x.append(img)
-        y.append(label)
-    return [x,y]
-def load_dir_7(path,label):
-    for i in file_7:
-        img=cv2.imread(i)
-        img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
-        img=cv2.resize(img,in_size)
-        img=img/255.0
-        x.append(img)
-        y.append(label)
-    return [x,y]
-def load_dir_8(path,label):
-    for i in file_8:
-        img=cv2.imread(i)
-        img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
-        img=cv2.resize(img,in_size)
-        img=img/255.0
-        x.append(img)
-        y.append(label)
-    return [x,y]
-def load_dir_9(path,label):
-    for i in file_9:
-        img=cv2.imread(i)
-        img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
-        img=cv2.resize(img,in_size)
-        img=img/255.0
-        x.append(img)
-        y.append(label)
-    return [x,y]
-def load_dir_0(path,label):
-    for i in file_0:
-        img=cv2.imread(i)
-        img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
-        img=cv2.resize(img,in_size)
-        img=img/255.0
-        x.append(img)
-        y.append(label)
-    return [x,y]
-#kerasのモデルに入れられるように数値データに変換
-load_dir_1(path_one,1)
-load_dir_2(path_two,2)
-load_dir_3(path_three,3)
-load_dir_4(path_four,4)
-load_dir_5(path_five,5)
-load_dir_6(path_six,6)
-load_dir_7(path_seven,7)
-load_dir_8(path_eight,8)
-load_dir_9(path_nine,9)
-load_dir_0(path_zero,0)
 #print(y)
 #リストになっている数値データをnumpyの配列に変換
@@ -378,38 +100,6 @@
-#訓練データとラベルの確認
-print(x_train.shape,y_train.shape)
-#テストデータとラベルの次元の確認
-print(x_test.shape,y_test.shape)
-print(x_test[111].shape)
-#数値データをもとの大きさに戻す
-x_test[9]=x_test[9]*255
-#貼り付け
-plt.imshow(x_test[9])
-#表示
-plt.show()
-#ラベルの表示
-print(y_test[9])
@@ -419,32 +109,6 @@
 x_test=x_test.reshape(len(x_test),28,28,1).astype('float32')/255
-print(x_train.shape,x_test.shape)
-#出力(ラベル、画像の次元など)
-(870, 28, 28) (870,)
-(218, 28, 28) (218,)
-(28, 28)
-4
-(870, 28, 28, 1) (218, 28, 28, 1)
@@ -458,168 +122,12 @@
 from keras.utils import to_categorical
-#x_train=x_train.reshape(-1,784).astype('float32')/255
-#x_test=x_test.reshape(-1,784).astype('float32')/255
 y_train=keras.utils.np_utils.to_categorical(y_train.astype('int32'),10)
 y_test=keras.utils.np_utils.to_categorical(y_test.astype('int32'),10)
-from keras import models
-from keras import layers
-from keras.layers import Dense,Dropout,MaxPooling2D,Convolution2D
-model=models.Sequential()
-model.add(layers.Conv2D(32,(3,3),activation='relu',input_shape=(28,28,1)))
-model.add(layers.MaxPooling2D((2,2)))
-model.add(Dropout(0.2))
-model.add(layers.Conv2D(64,(3,3),activation='relu'))
-model.add(layers.MaxPooling2D(2,2))
-model.add(Dropout(0.2))
-model.add(layers.Conv2D(64,(3,3),activation='relu'))
-model.add(layers.Flatten())
-model.add(layers.Dense(64,activation='relu'))
-model.add(layers.Dense(out_size,activation='softmax'))
-# データのシャッフル
-data_number = len(x_train)
-shuffled_num = np.arange(data_number)
-np.random.shuffle(shuffled_num)
-for i in range(data_number):
-    x_train[shuffled_num[i]], x_train[i] = x_train[i], x_train[shuffled_num[i]]
-    y_train[shuffled_num[i]], y_train[i] = y_train[i], y_train[shuffled_num[i]]
-print(y_train[9])
-#出力
-[0. 0. 1. 0. 0. 0. 0. 0. 0. 0.]
-from keras import optimizers
-model.compile(optimizer='adam',
-             loss='categorical_crossentropy',
-             metrics=['accuracy'])
-model.fit(x_train,y_train,batch_size=10,epochs=10)
-model.save('keras_number.h5')
-Epoch 1/10
-870/870 [==============================] - 1s 1ms/step - loss: 2.1910 - accuracy: 0.1920
-Epoch 2/10
-870/870 [==============================] - 1s 1ms/step - loss: 2.1406 - accuracy: 0.1943
-Epoch 3/10
-870/870 [==============================] - 1s 1ms/step - loss: 2.1419 - accuracy: 0.1828
-Epoch 4/10
-870/870 [==============================] - 1s 1ms/step - loss: 2.1349 - accuracy: 0.1874
-Epoch 5/10
-870/870 [==============================] - 1s 1ms/step - loss: 2.1318 - accuracy: 0.1805
-Epoch 6/10
-870/870 [==============================] - 1s 1ms/step - loss: 2.1369 - accuracy: 0.1897
-Epoch 7/10
-870/870 [==============================] - 1s 1ms/step - loss: 2.1393 - accuracy: 0.1885
-Epoch 8/100. 番号リスト
-870/870 [==============================] - 1s 1ms/step - loss: 2.1365 - accuracy: 0.1782
-Epoch 9/10
-870/870 [==============================] - 1s 988us/step - loss: 2.1387 - accuracy: 0.1897
-Epoch 10/10
-870/870 [==============================] - 1s 1ms/step - loss: 2.1336 - accuracy: 0.1816
 ```

文法の修正

2020/07/01 06:58

投稿

koukiten

スコア6

test CHANGED Viewed

File without changes

test CHANGED Viewed

@@ -376,20 +376,6 @@
 x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2)
-#print(x.shape)
-#print(y_train)
-In [14]:
@@ -442,7 +428,7 @@
+#出力(ラベル、画像の次元など)
 (870, 28, 28) (870,)
@@ -456,15 +442,11 @@
 4
 (870, 28, 28, 1) (218, 28, 28, 1)
-In [15]:
@@ -496,12 +478,6 @@
-In [16]:
 from keras import models
@@ -534,24 +510,6 @@
 model.add(layers.Dense(out_size,activation='softmax'))
-#model.add(layers.Dense(512,activation='relu',input_shape=(784,)))
-#model.add(Dropout(0.2))
-#model.add(Dense(512,activation='relu'))
-#model.add(Dropout(0.2))
-#model.add(layers.Dense(out_size,activation='softmax'))
-In [17]:
@@ -588,11 +546,11 @@
+#出力
 [0. 0. 1. 0. 0. 0. 0. 0. 0. 0.]
-In [18]:

文法の修正

2020/06/30 18:30

投稿

koukiten

スコア6

test CHANGED Viewed

File without changes

test CHANGED Viewed

@@ -6,7 +6,7 @@
 いろいろ試しては見ましたが、結果は変わりませんでした。
-数字の種類を減らした場合、lossと正解率は上がりましたがlossが減っていたりしたわけではなく単純に種類が減ったから正解率も上がっただけでした。
+数字の種類を減らした場合、数字のデータ数を増やすとlossと正解率は上がりましたがlossが減っていたりしたわけではなく単純に種類が減ったから正解率も上がっただけでした。
 何が原因なのかわからないのでご教授いただければ幸いです。
@@ -18,6 +18,12 @@
+```ここに言語を入力
 #画像フォルダから画像データを読み込む
 import glob,os
@@ -657,3 +663,5 @@
 Epoch 10/10
 870/870 [==============================] - 1s 1ms/step - loss: 2.1336 - accuracy: 0.1816
+```