I am trying to use this code to fit an ANN using Keras and then pickle it:
early_stopping = EarlyStopping(monitor='val_loss', patience=4, mode='auto')
model = Sequential()
model.add(Dense(units=40, kernel_initializer='random_uniform', input_dim=x_train.shape[1], activation='relu'))
model.add(Dense(units=1, kernel_initializer='random_uniform', activation='sigmoid', W_regularizer=reg))
model.compile(loss='binary_crossentropy', optimizer='adam')
model.fit(x=x_train, y=y_train, epochs=1, validation_data=(x_val, y_val), callbacks=[early_stopping])
pickle_file_and_path = 'C:/Bla/DLModel20180816.sav'
pickle.dump(model, open(pickle_file_and_path, 'wb'))
Unfortunately, I get:
pickle.dump(model, open(pickle_file_and_path, 'wb'))
TypeError: can't pickle _thread.RLock objects
Any ideas?
The canonical way of storing Keras models is to use the built-in model.save() method which will save the model into a HDF5 file.
Adapting your code:
model = Sequential()
model.add(Dense(units=40, kernel_initializer='random_uniform', input_dim=x_train.shape[1], activation='relu'))
model.add(Dense(units=1, kernel_initializer='random_uniform', activation='sigmoid', W_regularizer=reg))
model.compile(loss='binary_crossentropy', optimizer='adam')
model.fit(x=x_train, y=y_train, epochs=1, validation_data=(x_val, y_val), callbacks=[early_stopping])
# Save the model
model.save('./model.h5')
Afterwards, you can load it as follows:
from keras.models import load_model
model = load_model('./model.h5')
And start retraining or use the model for inference. Note that you can also store the only the weights with the save_weights() method. For the full documentation and more examples see the Keras website.
Related
The HAR dataset should be analyzed using LSTM and 1D CNN.
I need to check the graph of the change in loss and check the confusion matrix.
I don't know how to make init and forward functions in pytorch....
# define model
model = Sequential()
model.add(ConvLSTM2D(filters=64, kernel_size=(1,3), activation='relu', input_shape=(n_steps, 1, n_length, n_features)))
model.add(Dropout(0.1))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(n_outputs, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
# fit network
hist = model.fit(X_train, Y_train, epochs=epochs, validation_data=(X_test, Y_test), batch_size=batch_size, verbose=verbose)
# evaluate model
(loss, accuracy) = model.evaluate(X_test, Y_test, batch_size=batch_size, verbose=verbose)
print("[INFO] loss={:.4f}, accuracy: {:.4f}%".format(loss, accuracy * 100))
The above is an LSTM model implemented by keras.
model = Sequential()
model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(n_timesteps,n_features)))
model.add(Conv1D(filters=64, kernel_size=3, activation='relu', padding = 'same'))
model.add(Dropout(0.3))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dense(n_outputs, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
# fit network
history = model.fit(X_train, Y_train, validation_data=(X_test, Y_test),
epochs=epochs, batch_size=batch_size, callbacks = [checkpoint], verbose=verbose)
# evaluate model
(loss, accuracy) = model.evaluate(X_test, Y_test, batch_size=batch_size, verbose=verbose)
print("[INFO] loss={:.4f}, accuracy: {:.4f}%".format(loss, accuracy * 100))
The above is a 1D CNN model implemented by keras.
I started deep learning a few months ago, so I don't know. Help me.
I have the following code to run a vgg
checkpoint = tf.keras.callbacks.ModelCheckpoint(checkpoint_filepath+'MAssCalcVGG-noAug.h5',
monitor='val_loss', mode='auto', verbose=1,
save_best_only=True, save_freq='epoch'
)
#add custom fully-connected network on top of the already-trained base network
model = models.Sequential()
model.add(conv_base)
model.add(layers.Flatten())
model.add(layers.Dense(256, activation="relu"))
model.add(layers.Dense(1, activation="sigmoid"))
#freeze convolutional base
conv_base.trainable = False
model.compile(loss="binary_crossentropy",
optimizer=optimizers.Adam(lr=1e-3), # lr = 0.0001
metrics=METRICS)
#train fully-connected added part
history = model.fit(train_generat.flow(train_dataset_split,
train_labels_split,
batch_size=BATCH_SIZE,
shuffle=False),
steps_per_epoch=len(train_dataset_split) // BATCH_SIZE,
epochs=100,
validation_data=valid_generat.flow(valid_dataset_split,
valid_labels_split,
batch_size=BATCH_SIZE,
shuffle=False),
validation_steps=len(valid_labels_split) // BATCH_SIZE,
callbacks=[es, checkpoint, GarbageCollectorCallback()])
#model.save(save(os.path.join(checkpoint_filepath, 'MAssCalcVGG-noAug.h5'))))
model.summary()
but I get this:
NotImplementedError: Layer ModuleWrapper has arguments in `__init__` and therefore must override `get_config`
how can I fix it?
the code was perfectly working before probably I intentionally made a change to cause this.
model = Sequential()
model.add(Conv2D(50, (5,5), activation='relu', input_shape =(5,5,1), kernel_initializer='he_normal'))
model.add(Flatten())
model.add(Dense(1, activation='sigmoid'))
model.summary()
# compile the model
model.compile(loss='binary_crossentropy', optimizer= 'adam', metrics=['accuracy'])
model_checkpoint=ModelCheckpoint(r'C:\Users\globo\Desktop\Test_CNN\Results\Kernel5x5\Weights'+'\\'+test+'\model_test{epoch:02d}.h5',save_freq=1,save_weights_only=True)
# fit the model
history = model.fit(X_train, Y_train, epochs=10, batch_size=32, verbose=1, callbacks=[model_checkpoint], shuffle=True, validation_split=0.5)
I'm already extracting weights for each epoch with "ModelCheckpoint", but how can I extract flatten layer output for each epoch and save them?
doing this with sequential models is not feasible at all.
you should use functional API
inp = Input((5,5,1))
x = Conv2D(50, (5,5), activation='relu', kernel_initializer='he_normal')(inp)
xflatten = Flatten()(x)
out = Dense(1, activation='sigmoid')(xflatten)
main_model = Model(inp, out) # this works same as your model
flatten_model = Model(inp, xflatten) # and this only outputs the flatten layer and is not necessary to compile it because we won't train it, it just shows the output of a layer
main_model.compile(loss='binary_crossentropy', optimizer= 'adam', metrics=['accuracy'])
history = main_model.fit(X_train, Y_train, epochs=10, batch_size=32, verbose=1, callbacks=[model_checkpoint], shuffle=True, validation_split=0.5)
to see the flatten layers's output:
flatten_model.predict(X)
Since I cannot install h5py due to package inconsistency I am wondering if it is possible to save and load the weights in Keras to keep training your model on a new data. I know I can do the following:
old_weights = model.get_weights()
del model
new_model.set_weights(old_weights)
where model is the old model and new_model is the new one.Here is a complete example:
for i in training data:
model = Sequential()
model.add(Dense(20, activation='tanh', input_dim=Input))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mse')
model.fit(X, y, epochs=8, batch_size=16, shuffle=False, verbose=0)
new_model = Sequential()
new_model.add(Dense(20, activation='tanh', input_dim=Input))
new_model.add(Dense(1))
new_model.compile(optimizer='adam', loss='mse')
old_weights = model.get_weights()
del model
new_model.set_weights(old_weights)
model=new_model
I want after reading each training example (X and y are different at each iteration) save the weights and load it again and start from pre-trained model. I am not sure if my code does that since I am defining optimizer and model.compile again. Can anyone help me if the following code save the model and every iteration starts from pre-trained model.
You don't need to keep recompiling the model. Instead just fit your model multiple times after loading your samples.
from keras.models import Sequential
from keras.layers import Dense
model = Sequential()
model.add(Dense(20, activation='tanh', input_dim=Input))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mse')
# load the data into training_data
for data in training_data:
model.fit(data[0], data[1], epochs=8, batch_size=16, shuffle=False, verbose=0)
Here is a snapshot of my dataset, including its shape:
Now, here is the code I am using to build the NN:
# define the architecture of the network
model = Sequential()
model.add(Dense(50, input_dim=X_train.shape[1], init="uniform", activation="relu"))
model.add(Dense(38, activation="relu", kernel_initializer="uniform"))
model.add(Dense(1, activation = 'sigmoid'))
print("[INFO] compiling model...")
adam = Adam(lr=0.01)
model.compile(loss="binary_crossentropy", optimizer=adam,
metrics=["accuracy"])
model.fit(X_train, Y_train, epochs=50, batch_size=128,
verbose=1)
When I do this, I get the following error:
KeyError: '[233946 164308 296688 166151 276165 88219 117980 163503 182033 164328\n 188083 30380 37984 245771 308534 6215 181186 307488 172375 60446\n 29397 166681 5587 243263 103579 262182 107823 234790 258973 116433\n 199283 86118 172148 257334 286452 248407 81280 ...] not in index'
I haven't been able to find a solution to this. Any help would be much appreciated.
I believe that the input is not a numpy array as described in this github issue on the keras page
Try fitting the model using this:
model.fit(np.array(X_train), np.array(Y_train), epochs=50, batch_size=128,
verbose=1)
Which will cast the arrays as numpy arrays when fitting the data.