error while using the saved model

[un-lock-me]

When I want to use the saved mode to get prediction based on that, it raises

  File "/home/sgnbx/Downloads/projects/CRNN-with-STN-master/prediction.py", line 20, in <module>
    model = load_model('weightswithoutstnlrchanged.best.hdf5', custom_objects={"bknd": backend})
  File "/home/sgnbx/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/keras/engine/saving.py", line 419, in load_model
    model = _deserialize_model(f, custom_objects, compile)
  File "/home/sgnbx/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/keras/engine/saving.py", line 312, in _deserialize_model
    sample_weight_mode=sample_weight_mode)
  File "/home/sgnbx/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/keras/engine/training.py", line 129, in compile
    loss_functions.append(losses.get(loss.get(name)))
  File "/home/sgnbx/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/keras/losses.py", line 133, in get
    return deserialize(identifier)
  File "/home/sgnbx/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/keras/losses.py", line 114, in deserialize
    printable_module_name='loss function')
  File "/home/sgnbx/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 165, in deserialize_keras_object
    ':' + function_name)
ValueError: Unknown loss function:<lambda>

Do you have any idea of this?

this is my piece of code:

model = load_model('weightswithoutstnlrchanged.best.hdf5', custom_objects={"bknd": backend})
sgd = SGD(lr=0.0001, decay=1e-6, momentum=0.9, nesterov=True, clipnorm=5)
adam = optimizers.Adam()

model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=sgd)

I gave custom_object backend because firstly it did not recognize backend.
now it raising error for loss, and I tried to assign loss in the custom object but it did not work.or maybe I have to try something else.

can you please have a look on this.
Thank you

[un-lock-me]

Regarding this, I want to convert
model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=sgd) this part loss={'ctc': lambda y_true, y_pred: y_pred} to a function.

but I am not getting what are you doing here
can you please explain it so I can have the correspond function.

Thank you!

[sbillburg]

Regarding this, I want to convert
model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=sgd) this part loss={'ctc': lambda y_true, y_pred: y_pred} to a function.

but I am not getting what are you doing here
can you please explain it so I can have the correspond function.

Thank you!

the trained model is a compiled and complete network with weights, you can just use
model = load_model('weightswithoutstnlrchanged.best.hdf5')
print(model.predict(INPUT_IMAGE))
to show the result

[un-lock-me]

Regarding this, I want to convert
model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=sgd) this part loss={'ctc': lambda y_true, y_pred: y_pred} to a function.
but I am not getting what are you doing here
can you please explain it so I can have the correspond function.
Thank you!

the trained model is a compiled and complete network with weights, you can just use
model = load_model('weightswithoutstnlrchanged.best.hdf5')
print(model.predict(INPUT_IMAGE))
to show the result

Thank you so much for replying back.
But it does not work, raises error loss not found, bknd not found.
After searching I find this workaround giving custom_object to it.
It works well for bknd so not getting error for that but loss still raises error:
So with this code:
mlmodel = load_model('weightswithoutstnlrchanged.best.hdf5', custom_objects={"bknd": backend,'ctc':loss})
It raises this error:

    mlmodel = load_model('weightswithoutstnlrchanged.best.hdf5', custom_objects={"bknd": backend,'ctc':loss})
NameError: name 'loss' is not defined

[sbillburg]

See line 53, line 142 in CRNN_with_STN.py
Did you define 'ctc' before you use it?

[un-lock-me]

Actually yes, As per my search Keras has problem loading the model while there are custom layers.
I resolved it another way, however interested to know how can I do that while a custom loss there is in the code.

[un-lock-me]

@sbillburg Can you please let me know your idea toward this error?
when I use model.predict('boston.jpg') it throws this error. I believe we have to convert it to the correct format before feeding to the model.

Traceback (most recent call last):
  File "/home/sgnbx/Downloads/projects/CRNN-with-STN-master/CRNN_with_STN.py", line 170, in <module>
    print model.predict('boston.jpg')
  File "/home/sgnbx/anaconda3/envs/tf_gpu/lib/python2.7/site-packages/keras/engine/training.py", line 1149, in predict
    x, _, _ = self._standardize_user_data(x)
  File "/home/sgnbx/anaconda3/envs/tf_gpu/lib/python2.7/site-packages/keras/engine/training.py", line 751, in _standardize_user_data
    exception_prefix='input')
  File "/home/sgnbx/anaconda3/envs/tf_gpu/lib/python2.7/site-packages/keras/engine/training_utils.py", line 92, in standardize_input_data
    data = [standardize_single_array(x) for x in data]
  File "/home/sgnbx/anaconda3/envs/tf_gpu/lib/python2.7/site-packages/keras/engine/training_utils.py", line 27, in standardize_single_array
    elif x.ndim == 1:
AttributeError: 'str' object has no attribute 'ndim'

[yosraammar]

when I load a ctc model I have this problem: ValueError: Unknown loss function:
any help please.

pad each output label to maximum text length

train_padded_txt = pad_sequences(training_txt, maxlen=max_label_len, padding='post', value = len(char_list))
valid_padded_txt = pad_sequences(valid_txt, maxlen=max_label_len, padding='post', value = len(char_list))

input with shape of height=32 and width=128

input with shape of height=32 and width=128

inputs = Input(shape=(32,128,1))

convolution layer with kernel size (3,3)

conv_1 = Conv2D(64, (3,3), activation = 'relu', padding='same')(inputs)

poolig layer with kernel size (2,2)

pool_1 = MaxPool2D(pool_size=(2, 2), strides=2)(conv_1)

conv_2 = Conv2D(128, (3,3), activation = 'relu', padding='same')(pool_1)
pool_2 = MaxPool2D(pool_size=(2, 2), strides=2)(conv_2)

conv_3 = Conv2D(256, (3,3), activation = 'relu', padding='same')(pool_2)

conv_4 = Conv2D(256, (3,3), activation = 'relu', padding='same')(conv_3)

poolig layer with kernel size (2,1)

pool_4 = MaxPool2D(pool_size=(2, 1))(conv_4)

conv_5 = Conv2D(512, (3,3), activation = 'relu', padding='same')(pool_4)

Batch normalization layer

batch_norm_5 = BatchNormalization()(conv_5)

conv_6 = Conv2D(512, (3,3), activation = 'relu', padding='same')(batch_norm_5)
batch_norm_6 = BatchNormalization()(conv_6)
pool_6 = MaxPool2D(pool_size=(2, 1))(batch_norm_6)

conv_7 = Conv2D(512, (2,2), activation = 'relu')(pool_6)

squeezed = Lambda(lambda x: K.squeeze(x, 1))(conv_7)

bidirectional LSTM layers with units=128

blstm_1 = Bidirectional(LSTM(128, return_sequences=True, dropout = 0.2))(squeezed)
blstm_2 = Bidirectional(LSTM(128, return_sequences=True, dropout = 0.2))(blstm_1)

outputs = Dense(len(char_list)+1, activation = 'softmax')(blstm_2)

model to be used at test time

act_model = Model(inputs, outputs)

act_model.summary()

#the CTC loss fnction is to predict the output text, it is very helpfull for the
#text recognition topic.
labels = Input(name='the_labels', shape=[max_label_len], dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')

def ctc_lambda_func(args):
y_pred, labels, input_length, label_length = args

return K.ctc_batch_cost(labels, y_pred, input_length, label_length)

loss_out = Lambda(ctc_lambda_func, output_shape=(1,), name='ctc')([outputs, labels, input_length, label_length])

#model to be used at training time
model = Model(inputs=[inputs, labels, input_length, label_length], outputs=loss_out)

#train the model

model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer = 'adam')
filepath= "/home/yosra/Downloads/best_model.hdf5"
checkpoint = ModelCheckpoint(filepath=filepath, monitor='val_loss', verbose=1, save_best_only=True, mode='auto')

callbacks_list = [checkpoint]
training_img = np.array(training_img)
train_input_length = np.array(train_input_length)
train_label_length = np.array(train_label_length)

valid_img = np.array(valid_img)
valid_input_length = np.array(valid_input_length)
valid_label_length = np.array(valid_label_length)

model.fit(x=[training_img, train_padded_txt, train_input_length, train_label_length],
y=np.zeros(len(training_img)), batch_size=batch_size,
epochs = epochs,
validation_data = ([valid_img, valid_padded_txt, valid_input_length, valid_label_length],[np.zeros(len(valid_img))]),
verbose = 1, callbacks = callbacks_list)

model.save(filepath)

#test the model
from keras.models import load_model

load the saved best model weights

new_model = load_model(filepath)