lucasoskorep/tensordex
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

creating model builder for faster model tweaking and iteration. Increased threads for training to better feed the GPU images from the image generator.

Browse Source
This commit is contained in:
Lucas
2022-05-25 19:47:30 -04:00
parent 5990351a47
commit 616c99c7f5
12 changed files with 189 additions and 171 deletions
Download Patch File Download Diff File Expand all files Collapse all files
4 - TransferLearningKeras.py
+51 -117
View File
@@ -7,26 +7,30 @@ import seaborn as sn
from PIL import ImageFile
from tensorflow import keras
from model_builders import ImageClassModelBuilder, ImageClassModels
ImageFile.LOAD_TRUNCATED_IMAGES = True
input_shape = (224, 224, 3)
batch_size = 64
model_name = "TF2_Mobilenet_V2_transfer"
batch_size = 32
model_name = f"mobilenetv2-dense1024-l1l2-25drop-{time()}"
# preproc = keras.applications.inception_v3.preprocess_input
preproc = keras.applications.mobilenet_v2.preprocess_input
train_idg = keras.preprocessing.image.ImageDataGenerator(
training_idg = keras.preprocessing.image.ImageDataGenerator(
horizontal_flip=True,
rescale=1. / 255,
# rotation_range=30,
# width_shift_range=[-.1, .1],
# height_shift_range=[-.1, .1],
# preprocessing_function=preproc
rotation_range=30,
width_shift_range=[-.1, .1],
height_shift_range=[-.1, .1],
)
train_gen = train_idg.flow_from_directory(
'./downloads',
testing_idg = keras.preprocessing.image.ImageDataGenerator(
horizontal_flip=True,
)
def get_gen(path, test_set=False):
idg = testing_idg if test_set else training_idg
return idg.flow_from_directory(
path,
target_size=(input_shape[0], input_shape[1]),
batch_size=batch_size,
class_mode='categorical',
@@ -34,156 +38,86 @@ train_gen = train_idg.flow_from_directory(
color_mode='rgb'
)
val_idg = keras.preprocessing.image.ImageDataGenerator(
horizontal_flip=True,
rescale=1. / 255,
# rotation_range=30,
# width_shift_range=[-.1, .1],
# height_shift_range=[-.1, .1],
# preprocessing_function=keras.applications.mobilenet_v2.preprocess_input
)
val_gen = val_idg.flow_from_directory(
'./data/val',
target_size=(input_shape[0], input_shape[1]),
batch_size=batch_size,
class_mode='categorical',
shuffle=True,
)
print((val_gen.classes))
nclass = len(train_gen.class_indices)
print(nclass)
# for _ in range(5):
# img, label = train_gen.next()
# print(img.shape) # (1,256,256,3)
# plt.imshow(img[0])
# plt.show()
# plt.imshow(
# base_model = vgg16.VGG16(
# weights='imagenet',
# include_top=False,
# input_shape=input_shape
# )
# base_model = keras.applications.InceptionV3(
# weights='imagenet',
# include_top=False,
# input_shape=input_shape
# )
# base_model = keras.applications.xception.Xception(
# weights='imagenet',
# include_top=False,
# input_shape=input_shape
# )
base_model = keras.applications.mobilenet_v2.MobileNetV2(
weights='imagenet',
include_top=False,
input_shape=input_shape
)
base_model.trainable = False
# i = keras.layers.Input([input_shape[0], input_shape[1], input_shape[2]])
i = base_model.input
# x = preproc(i)
# x = base_model
x = keras.layers.GlobalAveragePooling2D()(base_model.output)
x = keras.layers.Dense(1024, activation='relu')(x)
x = keras.layers.Dropout(0.5)(x)
output = keras.layers.Dense(nclass, activation='softmax')(x)
model = keras.Model(inputs=i, outputs=output)
model.compile(optimizer=keras.optimizers.Adam(learning_rate=.0001),
loss=keras.losses.CategoricalCrossentropy(),
metrics=['accuracy'])
model.summary()
print(model.output_shape)
def train_model(train_gen, val_gen):
model = ImageClassModelBuilder(
input_shape=input_shape,
n_classes=807,
optimizer=keras.optimizers.Adam(learning_rate=.0001),
pre_trained=True,
fine_tune=0,
base_model=ImageClassModels.MOBILENET_V2
).create_model()
# Train the model
file_path = "weights.mobilenet.best.hdf5"
checkpoint = keras.callbacks.ModelCheckpoint(file_path, monitor='val_loss', verbose=1, save_best_only=True,
checkpoint = keras.callbacks.ModelCheckpoint(f"./Models/keras/{model_name}.hdf5", monitor='val_loss', verbose=1,
save_best_only=True,
mode='min')
early = keras.callbacks.EarlyStopping(monitor="loss", mode="min", patience=15)
tensorboard = keras.callbacks.TensorBoard(
log_dir="logs/" + model_name + "{}".format(time()),
log_dir="logs/" + model_name,
histogram_freq=1,
write_graph=True,
write_images=True,
update_freq=1,
profile_batch=2,
embeddings_freq=1
embeddings_freq=1,
)
callbacks_list = [checkpoint, early, tensorboard] # early
callbacks_list = [checkpoint, early, tensorboard]
history = model.fit(
train_gen,
validation_data=val_gen,
epochs=20,
epochs=100,
batch_size=batch_size,
shuffle=True,
verbose=True,
callbacks=callbacks_list
workers=12,
callbacks=callbacks_list,
max_queue_size=1000
)
print(history)
return model
# Create Test generator
test_idg = keras.preprocessing.image.ImageDataGenerator(
rescale=1. / 255,
)
test_gen = test_idg.flow_from_directory(
'./data/test',
target_size=(input_shape[0], input_shape[1]),
batch_size=batch_size,
shuffle=False
)
len(test_gen.filenames)
score = model.evaluate_generator(test_gen, workers=1, steps=len(test_gen))
# predicts
predicts = model.predict_generator(test_gen, verbose=True, workers=1, steps=len(test_gen))
def test_model(model, test_gen):
print(len(test_gen.filenames))
score = model.evaluate(test_gen, workers=8, steps=len(test_gen))
predicts = model.predict(test_gen, verbose=True, workers=8, steps=len(test_gen))
print("Loss: ", score[0], "Accuracy: ", score[1])
print(score)
print(predicts)
print(type(predicts))
print(predicts.shape)
# Process the predictions
predicts = np.argmax(predicts,
axis=1)
# test_gen.reset()
label_index = {v: k for k, v in train_gen.class_indices.items()}
label_index = {v: k for k, v in test_gen.class_indices.items()}
predicts = [label_index[p] for p in predicts]
reals = [label_index[p] for p in test_gen.classes]
# Save the results
print(label_index)
print(test_gen.classes)
print(test_gen.classes.shape)
print(type(test_gen.classes))
df = pd.DataFrame(columns=['fname', 'prediction', 'true_val'])
df['fname'] = [x for x in test_gen.filenames]
df['prediction'] = predicts
df["true_val"] = reals
df.to_csv("sub1.csv", index=False)
# Processed the saved results
from sklearn.metrics import accuracy_score, confusion_matrix
acc = accuracy_score(reals, predicts)
conf_mat = confusion_matrix(reals, predicts)
print("Testing accuracy score is ", acc)
print("Confusion Matrix", conf_mat)
df_cm = pd.DataFrame(conf_mat, index=[i for i in list(set(reals))],
columns=[i for i in list(set(reals))])
plt.figure(figsize=(10, 7))
sn.heatmap(df_cm, annot=True)
plt.show()
if __name__ == "__main__":
train_gen = get_gen('./data/train')
val_gen = get_gen('./data/val')
test_gen = get_gen('./data/test', test_set=True)
model = train_model(train_gen, val_gen)
test_model(model, test_gen)
5 - TestModel.py
+10 -10
View File
@@ -31,17 +31,17 @@ test_gen = test_idg.flow_from_directory(
)
predicts = model.predict_generator(test_gen, verbose=True, workers=1, steps=len(test_gen))
predictions = model.predict_generator(test_gen, verbose=True, workers=1, steps=len(test_gen))
print(predicts)
print(type(predicts))
print(predicts.shape)
print(predictions)
print(type(predictions))
print(predictions.shape)
# Process the predictions
predicts = np.argmax(predicts,
predictions = np.argmax(predictions,
axis=1)
# test_gen.reset()
label_index = {v: k for k, v in test_gen.class_indices.items()}
predicts = [label_index[p] for p in predicts]
predictions = [label_index[p] for p in predictions]
reals = [label_index[p] for p in test_gen.classes]
# Save the results
@@ -51,15 +51,15 @@ print(test_gen.classes.shape)
print(type(test_gen.classes))
df = pd.DataFrame(columns=['fname', 'prediction', 'true_val'])
df['fname'] = [x for x in test_gen.filenames]
df['prediction'] = predicts
df['prediction'] = predictions
df["true_val"] = reals
df.to_csv("sub1_non_transfer.csv", index=False)
# Processed the saved results
acc = accuracy_score(reals, predicts)
conf_mat = confusion_matrix(reals, predicts)
print(classification_report(reals, predicts, labels=[l for l in label_index.values()]))
acc = accuracy_score(reals, predictions)
conf_mat = confusion_matrix(reals, predictions)
print(classification_report(reals, predictions, labels=[l for l in label_index.values()]))
print("Testing accuracy score is ", acc)
print("Confusion Matrix", conf_mat)
Models/keras/mobilenetv2-dense1024-l1l2-25drop-1653521962.9923482.hdf5
BIN
View File
Binary file not shown.
Models/mobilenetv2-stock-all-fixed-v2/mobilenetv2.hdf5
BIN
View File
Binary file not shown.
Models/mobilenetv2-imagenet-all-v1/mobilenet-v2-imagenet-core.tflite → Models/tflite/mobilenetv2-imagenet-all-v1/mobilenet-v2-imagenet-core.tflite
View File
Models/mobilenetv2-stock-all-fixed-v2/labels.txt → Models/tflite/mobilenetv2-stock-all-fixed-v2/labels.txt
View File
Models/mobilenetv2-stock-all-fixed-v2/mobilenetv2.tflite → Models/tflite/mobilenetv2-stock-all-fixed-v2/mobilenetv2.tflite
View File
Models/mobilenetv2-stock-all-v1/labels.txt → Models/tflite/mobilenetv2-stock-all-v1/labels.txt
View File
Models/mobilenetv2-stock-all-v1/mobilenetv2.hdf5 → Models/tflite/mobilenetv2-stock-all-v1/mobilenetv2.hdf5
View File
model_builders/__init__.py
+1
View File
@@ -0,0 +1 @@
from .image_class_builder import ImageClassModelBuilder, ImageClassModels
model_builders/image_class_builder.py
+76
View File
@@ -0,0 +1,76 @@
from enum import Enum
from typing import Tuple
import tensorflow as tf
from tensorflow import keras
from .modelwrapper import ModelWrapper
class ImageClassModels(Enum):
INCEPTION_V3 = ModelWrapper(
keras.applications.InceptionV3,
keras.applications.inception_v3.preprocess_input
)
XCEPTION = ModelWrapper(
keras.applications.xception.Xception,
keras.applications.inception_v3.preprocess_input
)
MOBILENET_V2 = ModelWrapper(
keras.applications.mobilenet_v2.MobileNetV2,
keras.applications.mobilenet_v2.preprocess_input
)
class ImageClassModelBuilder(object):
def __init__(self,
input_shape: Tuple[int, int, int],
n_classes: int,
optimizer: tf.keras.optimizers.Optimizer = keras.optimizers.Adam(
learning_rate=.0001),
pre_trained: bool = True,
fine_tune: int = 0,
base_model: ImageClassModels = ImageClassModels.MOBILENET_V2):
self.input_shape = input_shape
self.n_classes = n_classes
self.optimizer = optimizer
self.pre_trained = pre_trained
self.fine_tune = fine_tune
self.base_model = base_model
def set_base_model(self, base_model: ImageClassModels):
self.base_model = base_model
def create_model(self):
base_model = self.base_model.value.model_func(
weights='imagenet' if self.pre_trained else None,
include_top=False
)
if self.pre_trained:
if self.fine_tune > 0:
for layer in base_model.layers[:-self.fine_tune]:
layer.trainable = False
else:
for layer in base_model.layers:
layer.trainable = False
i = tf.keras.layers.Input([self.input_shape[0], self.input_shape[1], self.input_shape[2]], dtype=tf.float32)
x = tf.cast(i, tf.float32)
x = self.base_model.value.model_preprocessor(x)
x = base_model(x)
x = keras.layers.GlobalAveragePooling2D()(x)
x = keras.layers.Dense(1024, activation='relu', kernel_regularizer=keras.regularizers.L1L2(l1=1e-5, l2=1e-5))(x)
x = keras.layers.Dropout(0.25)(x)
output = keras.layers.Dense(self.n_classes, activation='softmax')(x)
model = keras.Model(inputs=i, outputs=output)
model.compile(optimizer=self.optimizer,
loss=keras.losses.CategoricalCrossentropy(),
metrics=[
'accuracy',
# 'mse'
])
model.summary()
return model
model_builders/modelwrapper.py
+7
View File
@@ -0,0 +1,7 @@
from collections import Callable
class ModelWrapper(object):
def __init__(self, model_func:Callable, model_preprocessor:Callable):
self.model_func = model_func
self.model_preprocessor = model_preprocessor