Training Multi Class Image classification model - tensorflow

Question

I am trying to create a model using Tensorflow and Python, I get the data from a folder on my pc
The Folder Structure
An Example from the data
Almost all data are the same size [237 items,223 items,495 items,387 items,301 items]
That's how I load my data:
lables = {'Basic T-shrit':0, 'Bikini Bottom':1, 'Cargo Pants':2, 'Jeans':3, 'Oversize T-Shirt':4}
#Data
train_datagen = ImageDataGenerator(rescale=1/256)
train_generator = train_datagen.flow_from_directory(
'Dataset', # This is the source directory for training images
target_size=(256, 256), # All images will be resized to 200 x 200
batch_size=batch_size,
# Specify the classes explicitly
classes = lables,
# Since we use categorical_crossentropy loss, we need categorical labels
class_mode='categorical')
That's a model I tried:
#Model
model = Sequential()
model.add(Conv2D(32, (3,3), 1, activation='relu', input_shape=(image_width,image_height,3)))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(32,3,3, activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(64,3,3, activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(64,3,3, activation='relu'))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(categorys_size, activation='softmax'))
model.summary()
model.compile(loss='categorical_crossentropy',
optimizer="adam",
metrics=['acc'])
Then I start the learning process:
model.fit_generator(train_generator,
steps_per_epoch=epoch_steps,
epochs=Epoch,
validation_data=train_generator)
But it's not working good, The model sees the oversize shirt and normal shirt the same and any kind of pants as jeans
Model Train result
Then I tested this model:
model = tf.keras.models.Sequential([
keras.layers.Conv2D(32, kernel_size=(5, 5), activation=tf.keras.activations.relu, input_shape=IMAGE_SHAPE),
keras.layers.MaxPooling2D(pool_size=(2, 2)),
keras.layers.BatchNormalization(axis = 1),
keras.layers.Dropout(0.22),
keras.layers.Conv2D(32, kernel_size=(5, 5), activation=tf.keras.activations.relu),
keras.layers.AveragePooling2D(pool_size=(2, 2)),
keras.layers.BatchNormalization(axis = 1),
keras.layers.Dropout(0.25),
keras.layers.Conv2D(32, kernel_size=(4, 4), activation=tf.keras.activations.relu),
keras.layers.AveragePooling2D(pool_size=(2, 2)),
keras.layers.BatchNormalization(axis = 1),
keras.layers.Dropout(0.15),
keras.layers.Conv2D(32, kernel_size=(3, 3), activation=tf.keras.activations.relu),
keras.layers.AveragePooling2D(pool_size=(2, 2)),
keras.layers.BatchNormalization(axis = 1),
keras.layers.Dropout(0.15),
keras.layers.Flatten(),
keras.layers.Dense(256, activation=tf.keras.activations.relu,kernel_regularizer=keras.regularizers.l2(0.001)),
#keras.layers.Dropout(0.25),
keras.layers.Dense(64, activation=tf.keras.activations.relu,kernel_regularizer=keras.regularizers.l2(0.001)),
#keras.layers.Dropout(0.1),
keras.layers.Dense(len(lables), activation=tf.keras.activations.softmax)])
model.compile(optimizer=tf.keras.optimizers.Adam(),
loss=tf.keras.losses.sparse_categorical_crossentropy,
metrics=['accuracy'])
Then I start learning:
#Start Learning
checkpoint_path="/chk/cp-{epoch:04d}.ckpt"
cp_callback = tf.keras.callbacks.ModelCheckpoint(checkpoint_path,
save_weights_only=True,
verbose=1,
period=10)
model.fit(train,
epochs=Epoch,callbacks = [cp_callback],
validation_data=val,verbose=1)
And that's how I load the data
data = tf.keras.utils.image_dataset_from_directory('Dataset',labels = 'inferred',image_size = (192,192))
data_iterator = data.as_numpy_iterator()
batch = data_iterator.next()
fig, ax = plt.subplots(ncols=4, figsize=(20,20))
for idx, img in enumerate(batch[0][:4]):
ax[idx].imshow(img.astype(int))
ax[idx].title.set_text(batch[1][idx])
#Scale Data
data = data.map(lambda x,y: (x/192, y))
data.as_numpy_iterator().next()
train_size = int(len(data)*.7)
val_size = int(len(data)*.2)
test_size = int(len(data)*.1)
print(train_size)
train = data.take(train_size)
val = data.skip(train_size).take(val_size)
test = data.skip(train_size+val_size).take(test_size)
What I am doing wrong? and is the data I collected good enough for what I am trying to do? Am I missing something ?
Thanks