def jacard_coef(y_true, y_pred):
y_true_f = K.flatten(y_true)
y_pred_f = K.flatten(y_pred)
intersection = K.sum(y_true_f * y_pred_f)
return (intersection + 1.0) / (K.sum(y_true_f) + K.sum(y_pred_f) - intersection + 1.0)
def jacard_coef_loss(y_true, y_pred):
return -jacard_coef(y_true, y_pred)
if __name__ == "__main__":
""" Seeding : make result reproducible"""
np.random.seed(42)
tf.random.set_seed(42)
""" Folder for saving data """
create_dir("Jaccard_Unet")
""" Hyperparameters """
batch_size = 4
lr = 1e-4 #learning rate(0.0001)
num_epoch = 10 #no. of epochs
model_path = "Jaccard_Unet/Jaccard_Unet_v1.h5"
csv_path = "Jaccard_Unet/Jaccard_Unet.csv"
""" Dataset : 60 train/20 validation/20 testing"""
dataset_path = '/content/drive/MyDrive/ISIC2018'
(train_x, train_y), (valid_x, valid_y), (test_x, test_y) = load_data(dataset_path)
print(f"Train: {len(train_x)} - {len(train_y)}")
print(f"Valid: {len(valid_x)} - {len(valid_y)}")
print(f"Test: {len(test_x)} - {len(test_y)}")
train_dataset = tf_dataset(train_x, train_y, batch_size)
valid_dataset = tf_dataset(valid_x, valid_y, batch_size)
test_dataset = tf_dataset(test_x, test_y, batch_size)
train_steps = len(train_x)//batch_size
valid_steps = len(valid_x)//batch_size
test_steps = len(test_x)//batch_size
#do not forget about the reamainder
if len(train_x) % batch_size != 0:
train_steps += 1
if len(valid_x) % batch_size != 0:
valid_steps += 1
""" Build Model """
model = build_unet((H, W, 3))
model.compile(loss=[jaccard_coef_loss], optimizer=Adam(lr), metrics=[jaccard_coef])
callbacks = [
ModelCheckpoint(model_path, verbose=1, save_best_only=True), #save the weight
ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=3, min_lr=1e-7, verbose=1),
CSVLogger(csv_path),
TensorBoard(),
EarlyStopping(monitor='val_loss', patience=20, restore_best_weights=False)
]
#model.summary()
history_jacard = model.fit(
train_dataset,
epochs=num_epoch,
validation_data=valid_dataset,
steps_per_epoch=train_steps,
validation_steps=valid_steps,
callbacks=callbacks
)
所以，上面的代码是我训练过程的主要功能，10个epochs后，我想重新加载模型并再次训练它，因为我得到的jaccard分数并不理想。 但是当我用下面的代码重新加载它时：
with CustomObjectScope({'jaccard_coef_loss': jaccard_coef_loss, 'jaccard_coef': jaccard_coef}):
new_model = tf.keras.models.load_model("Jaccard_Unet/Jaccard_Unet_v1.h5")
new_history_jcard = new_model.fit(
train_dataset,
epochs=num_epoch,
validation_data=valid_dataset,
steps_per_epoch=train_steps,
validation_steps=valid_steps,
callbacks=callbacks
)
一些我无法理解的错误提示：
Epoch 1/10
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-190-605387750920> in <module>()
5 steps_per_epoch=train_steps,
6 validation_steps=valid_steps,
----> 7 callbacks=callbacks
8 )
9 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
984 except Exception as e: # pylint:disable=broad-except
985 if hasattr(e, "ag_error_metadata"):
--> 986 raise e.ag_error_metadata.to_exception(e)
987 else:
988 raise
TypeError: in user code:
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:855 train_function *
return step_function(self, iterator)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:845 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:1285 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:2833 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:3608 _call_for_each_replica
return fn(*args, **kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:840 run_step **
with ops.control_dependencies(_minimum_control_deps(outputs)):
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:2888 _minimum_control_deps
outputs = nest.flatten(outputs, expand_composites=True)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/util/nest.py:416 flatten
return _pywrap_utils.Flatten(structure, expand_composites)
TypeError: '<' not supported between instances of 'function' and 'str'
谁能帮帮我，我是深度学习的新手。