23-07-07

dev container 설정 - tqdm + tensorflow 자동 설치 env name = pso 로 자동 생성

.devcontainer/devcontainer.json

@@ -2,14 +2,20 @@
 // README at: https://github.com/devcontainers/templates/tree/main/src/miniconda
 {
 	"name": "Miniconda (Python 3)",
+	// Configure tool-specific properties.
 	"customizations": {
 		"vscode": {
 			"extensions": [
 				"ms-python.python",
-				"ms-toolsai.jupyter"
+				"ms-toolsai.jupyter",
+				"donjayamanne.python-extension-pack",
+				"tht13.python",
+				"esbenp.prettier-vscode",
+				"ms-python.black-formatter"
 			]
 		}
 	},
+	// Features to add to the dev container. More info: https://containers.dev/features.
 	"features": {
 		"ghcr.io/devcontainers/features/nvidia-cuda:1": {
 			"installCudnn": true
@@ -22,15 +28,13 @@
 			"version": "3.9"
 		}
 	},
-	"postCreateCommand": "conda env create --file environment.yaml --name pso"
-	// Features to add to the dev container. More info: https://containers.dev/features.
-	// "features": {},
 	// Use 'forwardPorts' to make a list of ports inside the container available locally.
 	// "forwardPorts": [],
 	// Use 'postCreateCommand' to run commands after the container is created.
-	// "postCreateCommand": "python --version",
+	"postCreateCommand": [
-	// Configure tool-specific properties.
+		"conda env create --file environment.yaml --name pso",
-	// "customizations": {},
+		"conda activate pso"
+	]
 	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
 	// "remoteUser": "root"
 }

.github/workflows/python-package-conda.yml

@@ -1,24 +0,0 @@
-name: Python Package using Conda
-
-on: [push]
-
-jobs:
-  build-linux:
-    runs-on: ubuntu-latest
-    strategy:
-      max-parallel: 5
-
-    steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python 3.9
-        uses: actions/setup-python@v3
-        with:
-          python-version: "3.9"
-      - name: Add conda to system path
-        run: |
-          # $CONDA is an environment variable pointing to the root of the miniconda directory
-          echo $CONDA/bin >> $GITHUB_PATH
-      - name: Install dependencies
-        run: |
-          conda env create --file environment.yaml --name pso
-          conda activate pso

auto_tunning.py

@@ -1,30 +1,25 @@
 # %%
 import os
-os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
+
+os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
 
 import tensorflow as tf
+
 tf.random.set_seed(777)  # for reproducibility
 
-from tensorflow import keras
+import gc
-from keras.datasets import mnist
+from datetime import date
-from keras.models import Sequential
-from keras.layers import Dense, Dropout, Flatten
-from keras.layers import Conv2D, MaxPooling2D
-from keras import backend as K
-
-# from pso_tf import PSO
-from pso import Optimizer
 
 import numpy as np
-
+from keras import backend as K
-from datetime import date
+from keras.datasets import mnist
+from keras.layers import Conv2D, Dense, Dropout, Flatten, MaxPooling2D
+from keras.models import Sequential
+from tensorflow import keras
 from tqdm import tqdm
 
-import gc
+from pso import Optimizer
 
-# print(tf.__version__)
-# print(tf.config.list_physical_devices())
-# print(f"Num GPUs Available: {len(tf.config.list_physical_devices('GPU'))}")
 
 def get_data():
     (x_train, y_train), (x_test, y_test) = mnist.load_data()
@@ -37,26 +32,30 @@ def get_data():
     print(f"x_test : {x_test[0].shape} | y_test : {y_test[0].shape}")
     return x_train, y_train, x_test, y_test
 
+
 def get_data_test():
     (x_train, y_train), (x_test, y_test) = mnist.load_data()
     x_test = x_test.reshape((10000, 28, 28, 1))
 
     return x_test, y_test
 
+
 def make_model():
     model = Sequential()
-    model.add(Conv2D(32, kernel_size=(5, 5),
+    model.add(
-              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=(3, 3)))
-    model.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))
+    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(128, activation='relu'))
+    model.add(Dense(128, activation="relu"))
-    model.add(Dense(10, activation='softmax'))
+    model.add(Dense(10, activation="softmax"))
 
     return model
 
+
 # %%
 model = make_model()
 x_test, y_test = get_data_test()
@@ -72,7 +71,18 @@ x_test, y_test = get_data_test()
 # loss = 'mean_absolute_percentage_error'
 # loss = 'mean_squared_error'
 
-loss = ['mse', 'categorical_crossentropy', 'binary_crossentropy', 'kullback_leibler_divergence', 'poisson', 'cosine_similarity', 'log_cosh', 'huber_loss', 'mean_absolute_error', 'mean_absolute_percentage_error']
+loss = [
+    "mse",
+    "categorical_crossentropy",
+    "binary_crossentropy",
+    "kullback_leibler_divergence",
+    "poisson",
+    "cosine_similarity",
+    "log_cosh",
+    "huber_loss",
+    "mean_absolute_error",
+    "mean_absolute_percentage_error",
+]
 n_particles = [50, 75, 100]
 c0 = [0.25, 0.35, 0.45, 0.55]
 c1 = [0.5, 0.6, 0.7, 0.8, 0.9]
@@ -99,8 +109,8 @@ if __name__ == "__main__":
                                         c1=c_1,
                                         w_min=w_m,
                                         w_max=w_M,
-                                        negative_swarm=n_s
+                                        negative_swarm=n_s,
-                                        )
+                                    )
 
                                     best_score = pso_mnist.fit(
                                         x_test,
@@ -111,8 +121,8 @@ if __name__ == "__main__":
                                         renewal="acc",
                                         empirical_balance=False,
                                         Dispersion=False,
-                                        check_point=25
+                                        check_point=25,
-                                        )
+                                    )
 
                                     del pso_mnist
                                     gc.collect()

environment.yaml

@@ -10,8 +10,8 @@ dependencies:
   - pandas=1.5.3=py39h417a72b_0
   - pip=23.0.1=py39h06a4308_0
   - python=3.9.16=h7a1cb2a_2
+  - tqdm=4.65.0=py39hb070fc8_0
   - pip:
       - numpy==1.23.5
       - nvidia-cudnn-cu11==8.6.0.163
       - tensorflow==2.12.0
-      - tqdm==4.65.1.dev3+g5587f0d

example.py

@@ -7,19 +7,19 @@ results with a number of independent runs of standard Backpropagation algorithm
 @author Mike Holcomb (mjh170630@utdallas.edu)
 """
 
+import tensorflow as tf
 from sklearn.datasets import load_iris
 from sklearn.model_selection import train_test_split
-import tensorflow as tf
 from tensorflow import keras
-from tensorflow.keras.models import Sequential
 from tensorflow.keras.layers import Dense
+from tensorflow.keras.models import Sequential
 
 from psokeras import Optimizer
 
-N = 50 # number of particles
+N = 50  # number of particles
-STEPS = 500 # number of steps
+STEPS = 500  # number of steps
-LOSS = 'mse' # Loss function
+LOSS = "mse"  # Loss function
-BATCH_SIZE = 32 # Size of batches to train on
+BATCH_SIZE = 32  # Size of batches to train on
 
 
 def build_model(loss):
@@ -30,12 +30,11 @@ def build_model(loss):
     :return: Keras dense model of predefined structure
     """
     model = Sequential()
-    model.add(Dense(4, activation='sigmoid', input_dim=4, use_bias=True))
+    model.add(Dense(4, activation="sigmoid", input_dim=4, use_bias=True))
-    model.add(Dense(4, activation='sigmoid', use_bias=True))
+    model.add(Dense(4, activation="sigmoid", use_bias=True))
-    model.add(Dense(3, activation='softmax', use_bias=True))
+    model.add(Dense(3, activation="softmax", use_bias=True))
 
-    model.compile(loss=loss,
+    model.compile(loss=loss, optimizer="adam")
-                  optimizer='adam')
 
     return model
 
@@ -52,11 +51,10 @@ def vanilla_backpropagation(x_train, y_train):
 
     for i in range(N):
         model_s = build_model(LOSS)
-        model_s.fit(x_train, y_train,
+        model_s.fit(x_train, y_train, epochs=STEPS, batch_size=BATCH_SIZE, verbose=0)
-                    epochs=STEPS,
+        train_score = model_s.evaluate(
-                    batch_size=BATCH_SIZE,
+            x_train, y_train, batch_size=BATCH_SIZE, verbose=0
-                    verbose=0)
+        )
-        train_score = model_s.evaluate(x_train, y_train, batch_size=BATCH_SIZE, verbose=0)
         if train_score < best_score:
             best_model = model_s
             best_score = train_score
@@ -66,11 +64,13 @@ def vanilla_backpropagation(x_train, y_train):
 if __name__ == "__main__":
     # Section I: Build the data set
     iris = load_iris()
-    x_train, x_test, y_train, y_test = train_test_split(iris.data,
+    x_train, x_test, y_train, y_test = train_test_split(
-                                                        keras.utils.to_categorical(iris.target, num_classes=None),
+        iris.data,
-                                                        test_size=0.5,
+        keras.utils.to_categorical(iris.target, num_classes=None),
-                                                        random_state=0,
+        test_size=0.5,
-                                                        stratify=iris.target)
+        random_state=0,
+        stratify=iris.target,
+    )
 
     # Section II: First run the backpropagation simulation
     model_s = vanilla_backpropagation(x_train=x_train, y_train=y_train)
@@ -84,13 +84,14 @@ if __name__ == "__main__":
     model_p = build_model(LOSS)
 
     # Instantiate optimizer with model, loss function, and hyperparameters
-    pso = Optimizer(model=model_p,
+    pso = Optimizer(
-                    loss=LOSS,
+        model=model_p,
-                    n=N,  # Number of particles
+        loss=LOSS,
-                    acceleration=1.0,  # Contribution of recursive particle velocity (acceleration)
+        n=N,  # Number of particles
-                    local_rate=0.6,    # Contribution of locally best weights to new velocity
+        acceleration=1.0,  # Contribution of recursive particle velocity (acceleration)
-                    global_rate=0.4    # Contribution of globally best weights to new velocity
+        local_rate=0.6,  # Contribution of locally best weights to new velocity
-                    )
+        global_rate=0.4,  # Contribution of globally best weights to new velocity
+    )
 
     # Train model on provided data
     pso.fit(x_train, y_train, steps=STEPS, batch_size=BATCH_SIZE)

iris.py

@@ -4,15 +4,14 @@ os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
 
 import gc
 
-import numpy as np
-import tensorflow as tf
-from pso import Optimizer
 from sklearn.datasets import load_iris
 from sklearn.model_selection import train_test_split
 from tensorflow import keras
 from tensorflow.keras import layers
 from tensorflow.keras.models import Sequential
 
+from pso import Optimizer
+
 
 def make_model():
     model = Sequential()

iris_tf.py

@@ -1,5 +1,6 @@
 import os
-os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
+
+os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
 
 import tensorflow as tf
 
@@ -11,22 +12,22 @@ if gpus:
     except RuntimeError as e:
         print(e)
 
+from sklearn.datasets import load_iris
+from sklearn.model_selection import train_test_split
 from tensorflow import keras
 from tensorflow.keras import layers
 from tensorflow.keras.models import Sequential
 
-from sklearn.datasets import load_iris
-from sklearn.model_selection import train_test_split
-
 
 def make_model():
     model = Sequential()
-    model.add(layers.Dense(10, activation='relu', input_shape=(4,)))
+    model.add(layers.Dense(10, activation="relu", input_shape=(4,)))
-    model.add(layers.Dense(10, activation='relu'))
+    model.add(layers.Dense(10, activation="relu"))
-    model.add(layers.Dense(3, activation='softmax'))
+    model.add(layers.Dense(3, activation="softmax"))
 
     return model
 
+
 def load_data():
     iris = load_iris()
     x = iris.data
@@ -34,18 +35,21 @@ def load_data():
 
     y = keras.utils.to_categorical(y, 3)
 
-    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, shuffle=True, stratify=y)
+    x_train, x_test, y_train, y_test = train_test_split(
+        x, y, test_size=0.2, shuffle=True, stratify=y
+    )
 
     return x_train, x_test, y_train, y_test
 
+
 if __name__ == "__main__":
     model = make_model()
     x_train, x_test, y_train, y_test = load_data()
     print(x_train.shape, y_train.shape)
 
-    loss = ['categorical_crossentropy', 'accuracy','mse']
+    loss = ["categorical_crossentropy", "accuracy", "mse"]
-    metrics = ['accuracy']
+    metrics = ["accuracy"]
 
-    model.compile(optimizer='sgd', loss=loss[0], metrics=metrics[0])
+    model.compile(optimizer="sgd", loss=loss[0], metrics=metrics[0])
     model.fit(x_train, y_train, epochs=200, batch_size=32, validation_split=0.2)
     model.evaluate(x_test, y_test, batch_size=32)

mnist.py

@@ -5,14 +5,11 @@ os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
 
 import gc
 
-import tensorflow as tf
-from keras import backend as K
 from keras.datasets import mnist
 from keras.layers import Conv2D, Dense, Dropout, Flatten, MaxPooling2D
 from keras.models import Sequential
+
 from pso import Optimizer
-from tensorflow import keras
-from tqdm import tqdm
 
 
 def get_data():
@@ -24,6 +21,7 @@ def get_data():
 
     print(f"x_train : {x_train[0].shape} | y_train : {y_train[0].shape}")
     print(f"x_test : {x_test[0].shape} | y_test : {y_test[0].shape}")
+
     return x_train, y_train, x_test, y_test
 
 
@@ -92,6 +90,7 @@ if __name__ == "__main__":
             Dispersion=False,
             check_point=25,
         )
+
     except Exception as e:
         print(e)
     finally:

pso/optimizer.py

@@ -73,7 +73,11 @@ class Optimizer:
         self.g_best = None  # 최고 점수를 받은 가중치
         self.g_best_ = None  # 최고 점수를 받은 가중치 - 값의 분산을 위한 변수
         self.avg_score = 0  # 평균 점수
+
         self.save_path = None  # 저장 위치
+        self.renewal = "acc"
+        self.Dispersion = False
+        self.day = datetime.now().strftime("%m-%d-%H-%M")
 
         negative_count = 0
 
@@ -225,7 +229,6 @@ class Optimizer:
                     self.save_path = save_path
                     if not os.path.exists(save_path):
                         os.makedirs(save_path, exist_ok=True)
-                    self.day = datetime.now().strftime("%m-%d-%H-%M")
         except ValueError as e:
             print(e)
             sys.exit(1)

pso/particle.py

@@ -1,7 +1,6 @@
 import gc
 
 import numpy as np
-import tensorflow as tf
 from tensorflow import keras
 
 

xor.py

@@ -5,15 +5,12 @@ os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
 
 import numpy as np
 import tensorflow as tf
-
-# from pso_tf import PSO
-from pso import Optimizer
 from tensorflow import keras
 from tensorflow.keras import layers
+from tensorflow.keras.layers import Dense
 from tensorflow.keras.models import Sequential
 
-print(tf.__version__)
+from pso import Optimizer
-print(tf.config.list_physical_devices())
 
 
 def get_data():
@@ -23,12 +20,9 @@ def get_data():
 
 
 def make_model():
-    leyer = []
+    model = Sequential()
-    leyer.append(layers.Dense(2, activation="sigmoid", input_shape=(2,)))
+    model.add(layers.Dense(2, activation="sigmoid", input_shape=(2,)))
-    # leyer.append(layers.Dense(2, activation='sigmoid'))
+    model.add(layers.Dense(1, activation="sigmoid"))
-    leyer.append(layers.Dense(1, activation="sigmoid"))
-
-    model = Sequential(leyer)
 
     return model