23-07-09

dev container 조정

.devcontainer/devcontainer.json

@@ -16,7 +16,9 @@
 				"donjayamanne.python-extension-pack",
 				"tht13.python",
 				"esbenp.prettier-vscode",
-				"ms-python.black-formatter"
+				"ms-python.black-formatter",
+				"github.vscode-github-actions",
+				"eamodio.gitlens"
 			]
 		}
 	},

.vscode/settings.json

@@ -1,6 +1,5 @@
 {
     "[python]": {
         "editor.defaultFormatter": "ms-python.black-formatter"
-    },
-    "python.formatting.provider": "none"
+    }
 }

mnist.py

@@ -50,7 +50,7 @@ def make_model():
 
 # %%
 model = make_model()
-x_train, y_train, x_test, y_test = get_data()
+x_train, y_train = get_data_test()
 
 loss = [
     "mse",
@@ -73,9 +73,9 @@ if __name__ == "__main__":
             loss=loss[2],
             n_particles=100,
             c0=0.35,
-            c1=0.8,
-            w_min=0.4,
-            w_max=1.1,
+            c1=0.7,
+            w_min=0.5,
+            w_max=0.9,
             negative_swarm=0.2,
             mutation_swarm=0.1,
         )

mnist_tf.py

@@ -43,21 +43,14 @@ def get_data_test():
 def make_model():
     model = Sequential()
     model.add(
-        Conv2D(
-            32,
-            kernel_size=(5, 5),
-            strides=(1, 1),
-            padding="same",
-            activation="relu",
-            input_shape=(28, 28, 1),
+        Conv2D(32, kernel_size=(5, 5), activation="relu", input_shape=(28, 28, 1))
     )
-    )
-    model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
-    model.add(Conv2D(64, kernel_size=(2, 2), activation="relu", padding="same"))
+    model.add(MaxPooling2D(pool_size=(3, 3)))
+    model.add(Conv2D(64, kernel_size=(3, 3), activation="relu"))
     model.add(MaxPooling2D(pool_size=(2, 2)))
     model.add(Dropout(0.25))
     model.add(Flatten())
-    model.add(Dense(1000, activation="relu"))
+    model.add(Dense(128, activation="relu"))
     model.add(Dense(10, activation="softmax"))
 
     return model
@@ -66,7 +59,9 @@ def make_model():
 model = make_model()
 x_train, y_train, x_test, y_test = get_data()
 
-model.compile(optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"])
+model.compile(
+    optimizer="sgd", loss="sparse_categorical_crossentropy", metrics=["accuracy"]
+)
 
 print("Training model...")
 model.fit(x_train, y_train, epochs=1000, batch_size=128, verbose=1)

pso/optimizer.py

@@ -379,8 +379,10 @@ class Optimizer:
                         score[0] = np.inf
                     if score[1] == None:
                         score[1] = 0
+
                     loss = loss + score[0]
                     acc = acc + score[1]
+
                     if score[0] < min_loss:
                         min_loss = score[0]
                     if score[0] > max_loss: