質問編集履歴
4
別の結果を追記
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -142,72 +142,30 @@
|
|
|
142
142
|
|
|
143
143
|
-----
|
|
144
144
|
|
|
145
|
+
仕方ないので特徴ベクトルで学習させた全結合層と畳み込み層(imagenet学習済みResnet)を結合させてFine tuningを行ってみましたが、
|
|
146
|
+
|
|
147
|
+
不思議な結果になりました。
|
|
148
|
+
|
|
145
149
|
```python
|
|
146
150
|
|
|
147
|
-
model
|
|
151
|
+
model.evaluate(test_image, test_encord)
|
|
148
152
|
|
|
149
|
-
|
|
153
|
+
# [0.2531382454914993, 0.6142322]
|
|
150
154
|
|
|
151
|
-
|
|
155
|
+
model.fit(train_image, train_encord, epochs=3, batch_size=16,validation_split=0.1)
|
|
152
156
|
|
|
153
|
-
|
|
157
|
+
# 2160/2160 [==============================] - 93s 43ms/sample - loss: 1.5922 - total_acc: 0.2333 - val_loss: 0.2954 - val_total_acc: 0.5643
|
|
154
158
|
|
|
155
|
-
|
|
159
|
+
model.evaluate(test_image, test_encord)
|
|
156
160
|
|
|
157
|
-
|
|
161
|
+
# [0.2892280397343725, 0.54681647]
|
|
158
162
|
|
|
159
|
-
|
|
163
|
+
model.evaluate(train_image, train_encord)
|
|
164
|
+
|
|
165
|
+
# [0.2311001866869706, 0.6222407]
|
|
160
166
|
|
|
161
167
|
```
|
|
162
168
|
|
|
163
|
-
|
|
169
|
+
悪い方向に学習するだけでなく、進捗で表示される結果とevaluateの結果が異なる等、何が起きているのか良く分かりません。
|
|
164
170
|
|
|
165
|
-
|
|
166
|
-
|
|
167
|
-
preprocessあり
|
|
168
|
-
|
|
169
|
-
|
|
170
|
-
|
|
171
|
-
---
|
|
172
|
-
|
|
173
|
-
Preprocess_inputの検証
|
|
174
|
-
|
|
175
|
-
```python
|
|
176
|
-
|
|
177
|
-
resnet.preprocess_input(image_array)
|
|
178
|
-
|
|
179
|
-
train_image, test_image, train_score, test_score = train_test_split(image_array, encorded, test_size=0.1, random_state=100)
|
|
180
|
-
|
|
181
|
-
conv_model = resnet.ResNet152(weights='imagenet', include_top=False, pooling="avg",input_shape=(224,224,3))
|
|
182
|
-
|
|
183
|
-
conv_model.trainable = False
|
|
184
|
-
|
|
185
|
-
|
|
186
|
-
|
|
187
|
-
top_model = Sequential()
|
|
188
|
-
|
|
189
|
-
top_model.add(Input(2048))
|
|
190
|
-
|
|
191
|
-
top_model.add(Dense(256, activation="relu"))
|
|
192
|
-
|
|
193
|
-
top_model.add(Dropout(0.5))
|
|
194
|
-
|
|
195
|
-
top_model.add(Dense(4, activation="sigmoid"))
|
|
196
|
-
|
|
197
|
-
|
|
198
|
-
|
|
199
|
-
model = Sequential([conv_model,top_model])
|
|
200
|
-
|
|
201
|
-
|
|
202
|
-
|
|
203
|
-
model.compile(optimizer="adam",
|
|
204
|
-
|
|
205
|
-
loss="binary_crossentropy",
|
|
206
|
-
|
|
207
|
-
metrics=[total_acc])
|
|
208
|
-
|
|
209
|
-
|
|
171
|
+
バグのような気もしてきたので環境を変えてみようかと思いますが、質問は数日で打ち切らせていただき、Tensorflowのコミュニティで聞いてみることにします。ありがとうございました。
|
|
210
|
-
|
|
211
|
-
```
|
|
212
|
-
|
|
213
|
-
|
3
Preprocess_inputの検証を追加
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -167,3 +167,47 @@
|
|
|
167
167
|
preprocessあり
|
|
168
168
|
|
|
169
169
|
|
|
170
|
+
|
|
171
|
+
---
|
|
172
|
+
|
|
173
|
+
Preprocess_inputの検証
|
|
174
|
+
|
|
175
|
+
```python
|
|
176
|
+
|
|
177
|
+
resnet.preprocess_input(image_array)
|
|
178
|
+
|
|
179
|
+
train_image, test_image, train_score, test_score = train_test_split(image_array, encorded, test_size=0.1, random_state=100)
|
|
180
|
+
|
|
181
|
+
conv_model = resnet.ResNet152(weights='imagenet', include_top=False, pooling="avg",input_shape=(224,224,3))
|
|
182
|
+
|
|
183
|
+
conv_model.trainable = False
|
|
184
|
+
|
|
185
|
+
|
|
186
|
+
|
|
187
|
+
top_model = Sequential()
|
|
188
|
+
|
|
189
|
+
top_model.add(Input(2048))
|
|
190
|
+
|
|
191
|
+
top_model.add(Dense(256, activation="relu"))
|
|
192
|
+
|
|
193
|
+
top_model.add(Dropout(0.5))
|
|
194
|
+
|
|
195
|
+
top_model.add(Dense(4, activation="sigmoid"))
|
|
196
|
+
|
|
197
|
+
|
|
198
|
+
|
|
199
|
+
model = Sequential([conv_model,top_model])
|
|
200
|
+
|
|
201
|
+
|
|
202
|
+
|
|
203
|
+
model.compile(optimizer="adam",
|
|
204
|
+
|
|
205
|
+
loss="binary_crossentropy",
|
|
206
|
+
|
|
207
|
+
metrics=[total_acc])
|
|
208
|
+
|
|
209
|
+
history = model.fit(train_image, train_score, epochs=20, batch_size=16,validation_split=0.1)
|
|
210
|
+
|
|
211
|
+
```
|
|
212
|
+
|
|
213
|
+
|
2
コードミスを修正
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -88,12 +88,6 @@
|
|
|
88
88
|
|
|
89
89
|
top_model.add(Dense(4, activation="sigmoid"))
|
|
90
90
|
|
|
91
|
-
top_model.compile(optimizer="adam",
|
|
92
|
-
|
|
93
|
-
loss="binary_crossentropy",
|
|
94
|
-
|
|
95
|
-
metrics=[total_acc])
|
|
96
|
-
|
|
97
91
|
|
|
98
92
|
|
|
99
93
|
model = Sequential([conv_model,top_model])
|
1
preprocess_input有無の差について追記
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -141,3 +141,35 @@
|
|
|
141
141
|
tensorflow version2.1.0のtf.kerasを使っています。
|
|
142
142
|
|
|
143
143
|
宜しくお願いします。
|
|
144
|
+
|
|
145
|
+
|
|
146
|
+
|
|
147
|
+
追記
|
|
148
|
+
|
|
149
|
+
-----
|
|
150
|
+
|
|
151
|
+
```python
|
|
152
|
+
|
|
153
|
+
model = resnet.ResNet152(weights='imagenet', include_top=False, pooling="avg")
|
|
154
|
+
|
|
155
|
+
image_feature = model.predict(image_data, verbose=1)
|
|
156
|
+
|
|
157
|
+
pc = PCA(n_components=2).fit_transform(image_feature)
|
|
158
|
+
|
|
159
|
+
pc1, pc2 = pc[:,0],pc[:,1]
|
|
160
|
+
|
|
161
|
+
plt.scatter(pc1, pc2, c=np.sum(encorded,axis=1), cmap="jet")
|
|
162
|
+
|
|
163
|
+
plt.colorbar()
|
|
164
|
+
|
|
165
|
+
plt.show()
|
|
166
|
+
|
|
167
|
+
```
|
|
168
|
+
|
|
169
|
+
preprocess無し
|
|
170
|
+
|
|
171
|
+
|
|
172
|
+
|
|
173
|
+
preprocessあり
|
|
174
|
+
|
|
175
|
+
|