Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

notebook_tutorial for prediction with any video #128

Open
wants to merge 6 commits into
base: add-demo-script
Choose a base branch
from
Open

notebook_tutorial for prediction with any video #128

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
1e16a79
interchanging , and ) (syntax error)
Jan 7, 2018
28f5c20
Merge pull request #63 from TheGalileo/patch-1
harvitronix Jan 7, 2018
161f0de
Merge pull request #70 from harvitronix/add-demo-script
harvitronix Feb 15, 2018
fd5cafe
Minor
harvitronix Feb 26, 2018
e4219a8
update LRCN in models.py
Anner-deJong Jun 8, 2018
6c610cd
Merge pull request #91 from Anner-deJong/patch-3
harvitronix May 13, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
64 changes: 35 additions & 29 deletions models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,41 +99,47 @@ def lrcn(self):
Also known as an LRCN:
https://arxiv.org/pdf/1411.4389.pdf
"""
def add_default_block(model, kernel_filters, init, reg_lambda):

# conv
model.add(TimeDistributed(Conv2D(kernel_filters, (3, 3), padding='same',
kernel_initializer=init, kernel_regularizer=L2_reg(l=reg_lambda))))
model.add(TimeDistributed(BatchNormalization()))
model.add(TimeDistributed(Activation('relu')))
# conv
model.add(TimeDistributed(Conv2D(kernel_filters, (3, 3), padding='same',
kernel_initializer=init, kernel_regularizer=L2_reg(l=reg_lambda))))
model.add(TimeDistributed(BatchNormalization()))
model.add(TimeDistributed(Activation('relu')))
# max pool
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))

return model

initialiser = 'glorot_uniform'
reg_lambda = 0.001

model = Sequential()

model.add(TimeDistributed(Conv2D(32, (7, 7), strides=(2, 2),
activation='relu', padding='same'), input_shape=self.input_shape))
model.add(TimeDistributed(Conv2D(32, (3,3),
kernel_initializer="he_normal", activation='relu')))
# first (non-default) block
model.add(TimeDistributed(Conv2D(32, (7, 7), strides=(2, 2), padding='same',
kernel_initializer=initialiser, kernel_regularizer=L2_reg(l=reg_lambda)),
input_shape=self.input_shape))
model.add(TimeDistributed(BatchNormalization()))
model.add(TimeDistributed(Activation('relu')))
model.add(TimeDistributed(Conv2D(32, (3,3), kernel_initializer=initialiser, kernel_regularizer=L2_reg(l=reg_lambda))))
model.add(TimeDistributed(BatchNormalization()))
model.add(TimeDistributed(Activation('relu')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))

model.add(TimeDistributed(Conv2D(64, (3,3),
padding='same', activation='relu')))
model.add(TimeDistributed(Conv2D(64, (3,3),
padding='same', activation='relu')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))

model.add(TimeDistributed(Conv2D(128, (3,3),
padding='same', activation='relu')))
model.add(TimeDistributed(Conv2D(128, (3,3),
padding='same', activation='relu')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))

model.add(TimeDistributed(Conv2D(256, (3,3),
padding='same', activation='relu')))
model.add(TimeDistributed(Conv2D(256, (3,3),
padding='same', activation='relu')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))

model.add(TimeDistributed(Conv2D(512, (3,3),
padding='same', activation='relu')))
model.add(TimeDistributed(Conv2D(512, (3,3),
padding='same', activation='relu')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
# 2nd-5th (default) blocks
model = add_default_block(model, 64, init=initialiser, reg_lambda=reg_lambda)
model = add_default_block(model, 128, init=initialiser, reg_lambda=reg_lambda)
model = add_default_block(model, 256, init=initialiser, reg_lambda=reg_lambda)
model = add_default_block(model, 512, init=initialiser, reg_lambda=reg_lambda)

# LSTM output head
model.add(TimeDistributed(Flatten()))

model.add(Dropout(0.5))
model.add(LSTM(256, return_sequences=False, dropout=0.5))
model.add(Dense(self.nb_classes, activation='softmax'))

Expand Down
2 changes: 1 addition & 1 deletion train_cnn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@

# Helper: Save the model.
checkpointer = ModelCheckpoint(
filepath=os.path.join('data', 'checkpoints', 'inception.{epoch:03d}-{val_loss:.2f}.hdf5',)
filepath=os.path.join('data', 'checkpoints', 'inception.{epoch:03d}-{val_loss:.2f}.hdf5'),
verbose=1,
save_best_only=True)

Expand Down
6 changes: 3 additions & 3 deletions validate_rnn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,8 +37,8 @@ def validate(data_type, model, seq_length=40, saved_model=None,
print(rm.model.metrics_names)

def main():
model = 'mlp'
saved_model = 'data/ucf101/checkpoints/mlp-features.023-0.926.hdf5'
model = 'lstm'
saved_model = 'data/checkpoints/lstm-features.026-0.239.hdf5'

if model == 'conv_3d' or model == 'lrcn':
data_type = 'images'
Expand All @@ -48,7 +48,7 @@ def main():
image_shape = None

validate(data_type, model, saved_model=saved_model,
image_shape=image_shape)
image_shape=image_shape, class_limit=4)

if __name__ == '__main__':
main()