編集履歴

質問編集履歴

少なかったので書き足しました

2019/05/03 23:58

投稿

iLia

スコア14

test CHANGED Viewed

File without changes

test CHANGED Viewed

@@ -1,5 +1,201 @@
 ```ここに言語を入力
+# -*- coding: utf-8 -*-
+import keras
+from keras.datasets import mnist
+import matplotlib
+from matplotlib import pyplot
+import numpy as np
+from sklearn import datasets
+from sklearn.model_selection import cross_val_score as crv
+def sigmoid(x):
+    return 1 / (1 + np.exp(-x))
+def softmax(x):
+    expX = np.exp(x)
+    return expX / np.sum(expX)
+def cross_entropy_error(y,t):
+    delta = 1e-7
+    batch_size = y.shape[0]
+    idx= np.arange(batch_size)
+    return -np.sum(np.log(y[idx,t]+delta)) / batch_size
+def gradient(f,x):
+    if x.ndim == 1:
+        return gradient_sub(f,x)
+    else:
+        grad = np.zeros_like(x)
+        for index, xx in enumerate(x):
+            grad[index] = gradient_sub(f,xx)
+    return grad
+def gradient_sub(f,x):
+    h = 1e-4
+    grad = np.zeros_like(x)
+    for i in range(x.size):
+        val = x[i]
+        x[i] = val + h
+        fx1 = f(x)
+        x[i] = val - h
+        fx2 = f(x)
+        grad[i] = (fx1 - fx2) / (2*h)
+        x[i] = val
+    return grad
+class SampleNetwork:
+    def __init__(self):
+        input_size = 64
+        hidden_size = 50
+        output_size = 10
+        self.params = {}
+        self.params["w0"] = 0.01 * np.random.randn(input_size,hidden_size)
+        self.params["w1"] = 0.01 * np.random.randn(hidden_size,output_size)
+        self.params["b0"] = np.zeros(hidden_size)
+        self.params["b1"] = np.zeros(output_size)
+        self.learning_rate = 0.1
+def predict(self,x):
+    a0 = np.dot(x,self.params["w0"]) + self.params["b0"]
+    z0 = sigmoid(a0)
+    a1 = np.dot(z0,self.params["w1"]) + self.params["b1"]
+    y = softmax(a1)
+    return y
+def updata_params(self,x,t):
+    loss_W = lambda W: self.loss(x,t)
+    for key in self.params.keys():
+        grad = gradient(loss_W, self.params[key])
+        self.params[key] -= self.learning_rate*grad
+def loss(self,x,t):
+    y = self.predict(x)
+    return cross_entropy_error(y,t)
+def accurary(self,x,t):
+    y = self.predict(x)
+    y = np.argmax(y,axis=1)
+    acc = np.sum(y==t) / float(x.shape[0])
+    return acc
+digits = datasets.load_digits()
+X = digits.data
+T = digits.target
+(train_X, train_T), (test_X, test_T) = mnist.load_data()
+network = SampleNetwork()
+batch_size = 100
+iter_num = 300
+train_size = train_X.shape[0]
+erpoch_size = max(train_size//batch_size,1)
+loss_list = []
+train_accurary_list = []
+test_accurary_list = []
 for index in range(iter_num):
     batch_choice = np.random.choice(train_size,batch_size)
@@ -16,12 +212,50 @@
         train_accurary = network.accurary(train_X,train_T)
+        test_accurary = network.accurary(test_X,test_T)
         train_accurary_list.append(train_accurary)
-        test_accurary = network.accurary(test_X,test_T)
         test_accurary_list.append(test_accurary)
+pyplot.figure(figsize=(10,7))
+pyplot.subplot(2,2,1)
+pyplot.plot(np.arange(len(loss_list)),loss_list)
+pyplot.xlabel("iteration")
+pyplot.title("Cross Entropy Error")
+pyplot.subplot(2,2,2)
+pyplot.plot(np.arange(0,len(train_accurary_list),1),train_accurary_list,"b")
+pyplot.plot(np.arange(0,len(test_accurary_list),1),test_accurary_list,"ro")
+pyplot.xlabel("iteration(epoch)")
+pyplot.title("Accuary")
+pyplot.legend(("train","test"),loc = "lowrer right")
+pyplot.tight_layout()
 ```

このような感じですか？

2019/05/03 23:57

投稿

iLia

スコア14

test CHANGED Viewed

File without changes

test CHANGED Viewed

@@ -1,220 +1,4 @@
-### 前提・実現したいこと
-エラーを解決したいです
+```ここに言語を入力
-### 発生している問題・エラーメッセージ
-update_params
-### 該当のソースコード
-# -*- coding: utf-8 -*-
-import keras
-from keras.datasets import mnist
-import matplotlib
-from matplotlib import pyplot
-import numpy as np
-from sklearn import datasets
-from sklearn.model_selection import cross_val_score as crv
-def sigmoid(x):
-    return 1 / (1 + np.exp(-x))
-def softmax(x):
-    expX = np.exp(x)
-    return expX / np.sum(expX)
-def cross_entropy_error(y,t):
-    delta = 1e-7
-    batch_size = y.shape[0]
-    idx= np.arange(batch_size)
-    return -np.sum(np.log(y[idx,t]+delta)) / batch_size
-def gradient(f,x):
-    if x.ndim == 1:
-        return gradient_sub(f,x)
-    else:
-        grad = np.zeros_like(x)
-        for index, xx in enumerate(x):
-            grad[index] = gradient_sub(f,xx)
-    return grad
-def gradient_sub(f,x):
-    h = 1e-4
-    grad = np.zeros_like(x)
-    for i in range(x.size):
-        val = x[i]
-        x[i] = val + h
-        fx1 = f(x)
-        x[i] = val - h
-        fx2 = f(x)
-        grad[i] = (fx1 - fx2) / (2*h)
-        x[i] = val
-    return grad
-class SampleNetwork:
-    def __init__(self):
-        input_size = 64
-        hidden_size = 50
-        output_size = 10
-        self.params = {}
-        self.params["w0"] = 0.01 * np.random.randn(input_size,hidden_size)
-        self.params["w1"] = 0.01 * np.random.randn(hidden_size,output_size)
-        self.params["b0"] = np.zeros(hidden_size)
-        self.params["b1"] = np.zeros(output_size)
-        self.learning_rate = 0.1
-def predict(self,x):
-    a0 = np.dot(x,self.params["w0"]) + self.params["b0"]
-    z0 = sigmoid(a0)
-    a1 = np.dot(z0,self.params["w1"]) + self.params["b1"]
-    y = softmax(a1)
-    return y
-def updata_params(self,x,t):
-    loss_W = lambda W: self.loss(x,t)
-    for key in self.params.keys():
-        grad = gradient(loss_W, self.params[key])
-        self.params[key] -= self.learning_rate*grad
-def loss(self,x,t):
-    y = self.predict(x)
-    return cross_entropy_error(y,t)
-def accurary(self,x,t):
-    y = self.predict(x)
-    y = np.argmax(y,axis=1)
-    acc = np.sum(y==t) / float(x.shape[0])
-    return acc
-digits = datasets.load_digits()
-X = digits.data
-T = digits.target
-(train_X, train_T), (test_X, test_T) = mnist.load_data()
-network = SampleNetwork()
-batch_size = 100
-iter_num = 300
-train_size = train_X.shape[0]
-erpoch_size = max(train_size//batch_size,1)
-loss_list = []
-train_accurary_list = []
-test_accurary_list = []
 for index in range(iter_num):
@@ -238,56 +22,20 @@
         test_accurary_list.append(test_accurary)
-pyplot.figure(figsize=(10,7))
-pyplot.subplot(2,2,1)
+```
-pyplot.plot(np.arange(len(loss_list)),loss_list)
-pyplot.xlabel("iteration")
-pyplot.title("Cross Entropy Error")
-pyplot.subplot(2,2,2)
-pyplot.plot(np.arange(0,len(train_accurary_list),1),train_accurary_list,"b")
-pyplot.plot(np.arange(0,len(test_accurary_list),1),test_accurary_list,"ro")
-pyplot.xlabel("iteration(epoch)")
-pyplot.title("Accuary")
-pyplot.legend(("train","test"),loc = "lowrer right")
-pyplot.tight_layout()
+＃エラー
+Using TensorFlow backend.
+Traceback (most recent call last):
+  File "number.py", line 103, in <module>
+    network.update_params(x_batch,t_batch)
-### 試したこと
-エラーコードがどういう意味なのかを調べましたが、解決方法がわかりませんでした。
-### 補足情報（FW/ツールのバージョンなど）
+AttributeError: 'SampleNetwork' object has no attribute 'update_params'
-MacBook Pro Python VScode

修正しました

2019/05/03 22:33

投稿

iLia

スコア14

test CHANGED Viewed

File without changes

test CHANGED Viewed

@@ -1,6 +1,26 @@
+### 前提・実現したいこと
-＃＃＃コードです
+エラーを解決したいです
+### 発生している問題・エラーメッセージ
+update_params
+### 該当のソースコード
+# -*- coding: utf-8 -*-
 import keras
@@ -246,12 +266,28 @@
-＃＃＃エラー
+### 試したこと
-AttributeError: 'SampleNetwork' object has no attribute 'update_params'
-エラーの意味は調べたのですが、SampleNetworkの中にどうやって入れればいいのかがわかりません
+エラーコードがどういう意味なのかを調べましたが、解決方法がわかりませんでした。
+### 補足情報（FW/ツールのバージョンなど）
+MacBook Pro Python VScode