add analize.py, increase batch size, fix to epoch 20 for image recognition

analize2.py

@@ -0,0 +1,59 @@
+#!/usr/bin/python3
+
+from tensorflow.keras.preprocessing.image import ImageDataGenerator
+
+img_size = (150, 150)
+batch_size = 128
+extract_path="../ds/raw-img"
+
+datagen = ImageDataGenerator(
+        rescale=1.0/255,
+        validation_split=0.2
+)
+
+def __dg(subset):
+    return datagen.flow_from_directory(extract_path,
+                                       target_size = img_size,
+                                       batch_size = batch_size,
+                                       class_mode = "categorical",
+                                       subset = subset,
+                                       shuffle = True)
+
+train_generator = __dg("training")
+val_generator = __dg("validation")
+
+
+from tensorflow.keras import models as m
+from tensorflow.keras import layers as l
+from tensorflow.keras import optimizers as o
+
+model = m.Sequential([
+    l.Input(shape=(150, 150, 3)),
+    l.Conv2D(96, (11, 11), strides=4, activation='relu'),
+    l.BatchNormalization(),
+    l.MaxPooling2D((3, 3), strides=2),
+
+    l.Conv2D(192, (5, 5), activation='relu', padding='same'),
+    l.BatchNormalization(),
+    l.MaxPooling2D((3, 3), strides=2),
+    l.Conv2D(256, (3, 3), activation='relu', padding='same'),
+    l.Conv2D(256, (3, 3), activation='relu', padding='same'),
+    l.Conv2D(160, (3, 3), activation='relu', padding='same'),
+    l.BatchNormalization(),
+    l.MaxPooling2D((3, 3), strides=2),
+    l.Flatten(),
+    l.Dense(1024, activation='relu'),
+    l.Dropout(0.5),
+    l.Dense(1024, activation='relu'),
+    l.Dropout(0.5),
+    l.Dense(10, activation='softmax'),
+])
+
+model.compile(optimizer = o.Adam(learning_rate = 0.0001),
+              loss = 'categorical_crossentropy',
+              metrics = ['accuracy'])
+
+model.load_weights("w2.weights.h5")
+
+l, a = model.evaluate(val_generator)
+print(f"Loss: {l}   Accuracy: {a}")

find2.py

@@ -39,7 +39,7 @@ model.compile(optimizer = o.Adam(learning_rate = 0.0001),
               loss = "categorical_crossentropy",
               metrics = ["accuracy"])
 
-model.load_weights("w2.weights.h5")
+model.load_weights("ep20.weights.h5")
 
 if len(argv) >= 2:
     for i in argv[1:]:

test2.py

@@ -3,7 +3,7 @@
 from tensorflow.keras.preprocessing.image import ImageDataGenerator
 
 img_size = (150, 150)
-batch_size = 128
+batch_size = 192
 extract_path="../ds/raw-img"
 
 datagen = ImageDataGenerator(