I don't know if what I'm doing is correct. But I would like to use logcosh as a loss. So I put it inside a class as shown below:
class Logcosh(tf.keras.losses.Loss):
def __init__(self):
super().__init__()
def call(self, y_true, y_pred ):
return tf.keras.losses.logcosh(y_true, y_pred)
Then I called in my code:
LR = 0.0001
optim = keras.optimizers.Adam(LR)
dice_loss_se2 =Logcosh()
mae = tf.keras.losses.MeanAbsoluteError( )
metrics = [ mae,sm.metrics.IOUScore(threshold=0.5), sm.metrics.FScore(threshold=0.5) , dice_loss_se2]
model.compile(optimizer=optim,loss= dice_loss_se2,metrics= metrics)
LR = 0.0001
optim = keras.optimizers.Adam(LR)
train_gen = DataGen(train_ids, train_path, image_size=image_size, batch_size=batch_size)
valid_gen = DataGen(valid_ids, train_path, image_size=image_size, batch_size=batch_size)
train_steps = len(train_ids)//batch_size
valid_steps = len(valid_ids)//batch_size
history =model.fit_generator(train_gen, validation_data=valid_gen, steps_per_epoch=train_steps, validation_steps=valid_steps,
epochs=epochs)
But I got the below error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-59-fb657b903f55> in <module>
23 valid_steps = len(valid_ids)//batch_size
24
---> 25 history =model.fit_generator(train_gen, validation_data=valid_gen, steps_per_epoch=train_steps, validation_steps=valid_steps,
26 epochs=epochs)
~/.local/lib/python3.8/site-packages/keras/engine/training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
2207 'Please use `Model.fit`, which supports generators.',
2208 stacklevel=2)
-> 2209 return self.fit(
2210 generator,
2211 steps_per_epoch=steps_per_epoch,
~/.local/lib/python3.8/site-packages/keras/utils/traceback_utils.py in error_handler(*args, **kwargs)
65 except Exception as e: # pylint: disable=broad-except
66 filtered_tb = _process_traceback_frames(e.__traceback__)
---> 67 raise e.with_traceback(filtered_tb) from None
68 finally:
69 del filtered_tb
~/.local/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py in autograph_handler(*args, **kwargs)
1145 except Exception as e: # pylint:disable=broad-except
1146 if hasattr(e, "ag_error_metadata"):
-> 1147 raise e.ag_error_metadata.to_exception(e)
1148 else:
1149 raise
ValueError: in user code:
File "/storage/home/mm8755/.local/lib/python3.8/site-packages/keras/engine/training.py", line 1021, in train_function *
return step_function(self, iterator)
File "/storage/home/mm8755/.local/lib/python3.8/site-packages/keras/engine/training.py", line 1010, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/storage/home/mm8755/.local/lib/python3.8/site-packages/keras/engine/training.py", line 1000, in run_step **
outputs = model.train_step(data)
File "/storage/home/mm8755/.local/lib/python3.8/site-packages/keras/engine/training.py", line 864, in train_step
return self.compute_metrics(x, y, y_pred, sample_weight)
File "/storage/home/mm8755/.local/lib/python3.8/site-packages/keras/engine/training.py", line 957, in compute_metrics
self.compiled_metrics.update_state(y, y_pred, sample_weight)
File "/storage/home/mm8755/.local/lib/python3.8/site-packages/keras/engine/compile_utils.py", line 438, in update_state
self.build(y_pred, y_true)
File "/storage/home/mm8755/.local/lib/python3.8/site-packages/keras/engine/compile_utils.py", line 358, in build
self._metrics = tf.__internal__.nest.map_structure_up_to(y_pred, self._get_metric_objects,
File "/storage/home/mm8755/.local/lib/python3.8/site-packages/keras/engine/compile_utils.py", line 484, in _get_metric_objects
return [self._get_metric_object(m, y_t, y_p) for m in metrics]
File "/storage/home/mm8755/.local/lib/python3.8/site-packages/keras/engine/compile_utils.py", line 484, in <listcomp>
return [self._get_metric_object(m, y_t, y_p) for m in metrics]
File "/storage/home/mm8755/.local/lib/python3.8/site-packages/keras/engine/compile_utils.py", line 538, in _get_metric_object
raise ValueError(
ValueError: Metric should be a callable, received: <__main__.Logcosh object at 0x2b1db47964c0>
CodePudding user response：
The model.fit_generator is quite old but the idea is the same.
LogCosh that identifies identity as logarithms scales, how would you present similarity with limited information?
You see it has the behavior of the logarithms for the categorize tasks.
[ Sample ]:
import os
from os.path import exists
import tensorflow as tf
import tensorflow_io as tfio
import matplotlib.pyplot as plt
import numpy as np
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
[PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]
None
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
physical_devices = tf.config.experimental.list_physical_devices('GPU')
assert len(physical_devices) > 0, "Not enough GPU hardware devices available"
config = tf.config.experimental.set_memory_growth(physical_devices[0], True)
print(physical_devices)
print(config)
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Class and Definition
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
class Logcosh(tf.keras.losses.Loss):
def __init__(self):
super().__init__()
def call(self, y_true, y_pred ):
return tf.keras.losses.logcosh(y_true, y_pred)
def gen():
train_generator = tf.keras.preprocessing.image.ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
train_generator = train_generator.flow_from_directory(
directory,
target_size=(32, 32),
batch_size=BATCH_SIZE,
class_mode='categorical', # None # categorical # binary
subset='training')
return train_generator
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Variables
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
LR = 0.000001
directory = "F:\\datasets\\downloads\\Actors\\train\\"
train_steps = 33
val_steps = 1
epochs = 1500
BATCH_SIZE = 33
IMG_SIZE = (32, 32)
checkpoint_path = "F:\\models\\checkpoint\\" os.path.basename(__file__).split('.')[0] "\\TF_DataSets_01.h5"
checkpoint_dir = os.path.dirname(checkpoint_path)
loggings = "F:\\models\\checkpoint\\" os.path.basename(__file__).split('.')[0] "\\loggings.log"
if not exists(checkpoint_dir) :
os.mkdir(checkpoint_dir)
print("Create directory: " checkpoint_dir)
log_dir = checkpoint_dir
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
DataSet
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
train_generator = gen()
val_generator = train_generator
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Callback
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
class custom_callback(tf.keras.callbacks.Callback):
def on_epoch_end(self, epoch, logs={}):
if( logs['accuracy'] >= 0.97 ):
self.model.stop_training = True
custom_callback = custom_callback()
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Model Initialize
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
model = tf.keras.models.Sequential([
tf.keras.layers.InputLayer(input_shape=( 32, 32, 3 )),
tf.keras.layers.Normalization(mean=3., variance=2.),
tf.keras.layers.Normalization(mean=4., variance=6.),
tf.keras.layers.Dense(256, activation='relu'),
tf.keras.layers.Reshape((256, 32 * 32)),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(196, return_sequences=True, return_state=False)),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(196)),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(192, activation='relu'),
tf.keras.layers.Dense(2),
])
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Optimizer
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
optimizer = tf.keras.optimizers.Adam(LR)
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Loss Fn
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
lossfn = Logcosh()# <__main__.Logcosh object at 0x000001EFAFBB8DF0>
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Model Summary
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
model.compile(optimizer=optimizer, loss=lossfn, metrics=['accuracy'])
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Training
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
history = model.fit_generator(train_generator, epochs=epochs, verbose=1, callbacks=[custom_callback])
PATH = os.path.join('F:\\datasets\\downloads\\Actors\\train\\Pikaploy', '*.tif')
PATH_2 = os.path.join('F:\\datasets\\downloads\\Actors\\train\\Candidt Kibt', '*.tif')
files = tf.data.Dataset.list_files(PATH)
files_2 = tf.data.Dataset.list_files(PATH_2)
list_file = []
list_file_actual = []
list_label_actual = [ 'Pikaploy', 'Candidt Kibt' ]
for file in files.take(5):
image = tf.io.read_file( file )
image = tfio.experimental.image.decode_tiff(image, index=0)
list_file_actual.append(image)
image = tf.image.resize(image, [32,32], method='nearest')
image = tfio.experimental.color.rgba_to_rgb( image )
list_file.append(image)
for file in files_2.take(5):
image = tf.io.read_file( file )
image = tfio.experimental.image.decode_tiff(image, index=0)
list_file_actual.append(image)
image = tf.image.resize(image, [32,32], method='nearest')
image = tfio.experimental.color.rgba_to_rgb( image )
list_file.append(image)
plt.figure(figsize=(6, 6))
plt.title("Cat emotions recognition")
for i in range(len(list_file)):
img = tf.keras.preprocessing.image.array_to_img(
list_file[i],
data_format=None,
scale=True
)
img_array = tf.keras.preprocessing.image.img_to_array(img)
img_array = tf.expand_dims(img_array, 0)
predictions = model.predict(img_array)
score = tf.nn.softmax(predictions[0])
plt.subplot(6, 6, i 1)
plt.xticks([])
plt.yticks([])
plt.grid(False)
plt.imshow(list_file_actual[i])
plt.xlabel(str(round(score[tf.math.argmax(score).numpy()].numpy(), 2)) ":" str(list_label_actual[tf.math.argmax(score)]))
plt.show()
input('...')
[ Output ]:
