from keras.optimizers import Adam, RMSprop
import numpy as np
import pandas as pd
from define_model import create_model
from utilities import get_image_tensor, get_callbacks
from sklearn.model_selection import StratifiedKFold, train_test_split
# Set up data
iceberg = pd.read_json('data/train.json')
train_data, test_data = train_test_split(iceberg,
train_size=.75,
random_state=123)
train_images = get_image_tensor(train_data)
test_images = get_image_tensor(test_data)
# Run Experiments on adam lr
lrs = [0.002, 0.001, 0.0005]
for i in range(3):
model = create_model()
optimizer = Adam(lr=lrs[i])
model.compile(optimizer=optimizer,
loss='binary_crossentropy',
metrics=['accuracy'])
hist = model.fit(train_images,
train_data.is_iceberg,
epochs=1,
batch_size=101,
callbacks=get_callbacks(
'data/train_weights_adam' + str(i) + '.hdf5', 4),
from sklearn.model_selection import train_test_split
from keras.models import Sequential
from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten, Dropout
from keras.optimizers import Adam
from keras.callbacks import ModelCheckpoint
from utilities import get_image_tensor
from define_models import create_model
score_data_location = 'data/test.hdf'
hyper_p = ('elu', 3, 2)
model = create_model(2, False, False)
model.load_weights('data/train_weightsnone_.hdf5')
model.compile(optimizer = Adam(), loss = 'binary_crossentropy',
metrics = ['accuracy'])
submission_data = pd.read_hdf(score_data_location)
#submission_data.to_hdf('data/test.hdf', 'data', mode = 'w')
submission = pd.DataFrame()
submission['id'] = submission_data['id']
submission_data = get_image_tensor(submission_data, extra_channel = 'none')
results = model.predict(submission_data)
results = results.reshape(results.shape[0])
submission['is_iceberg'] = results
submission.to_csv('data/submission.csv', index = False)
#print(model.evaluate(x_test, test_target))
# Decent improvement so far, up to 71% test set
from keras.optimizers import Adam, RMSprop
import numpy as np
import pandas as pd
from define_model import create_model
from utilities import get_image_tensor, get_callbacks
from sklearn.model_selection import StratifiedKFold, train_test_split
model = create_model(2, False, False)
optim = RMSprop(lr=0.0001)
model.compile(optimizer=optim,
loss='binary_crossentropy',
metrics=['accuracy'])
iceberg = pd.read_json('data/train.json')
iceberg['inc_angle'] = iceberg['inc_angle'].replace('na', -1).astype(float)
train_data, test_data = train_test_split(iceberg,
train_size=.75,
random_state=123)
train_images = get_image_tensor(train_data, 'none')
test_images = get_image_tensor(test_data, 'none')
hist = model.fit(train_images,
train_data.is_iceberg,
epochs=30,
batch_size=13,
callbacks=get_callbacks('data/train_weights.hdf5', 5),
validation_data=(test_images, test_data.is_iceberg))
print(hist)
pd.DataFrame(hist.history).to_csv('data/smaller_batch.csv')
score_data_location = '../architecture_experiments/data/test.hdf'
model = create_model(nchannels=2,
base_size=42,
drop=0.06767,
activation='relu',
normalize_batches=False,
angle=False)
model.load_weights('data/train_weights_9.hdf5')
model.compile(optimizer=Adam(),
loss='binary_crossentropy',
metrics=['accuracy'])
submission_data = pd.read_hdf(score_data_location)
#submission_data.to_hdf('data/test.hdf', 'data', mode = 'w')
submission = pd.DataFrame()
submission['id'] = submission_data['id']
submission_data = get_image_tensor(submission_data,
extra_channel='none',
normalize=False)
results = model.predict(submission_data)
results = results.reshape(results.shape[0])
submission['is_iceberg'] = results
submission.to_csv('data/submission.csv', index=False)
#print(model.evaluate(x_test, test_target))
# Decent improvement so far, up to 71% test set
from utilities import get_image_tensor, get_callbacks
from sklearn.model_selection import StratifiedKFold, train_test_split
# Set up data
iceberg = pd.read_json('data/train.json')
iceberg['inc_angle'] = iceberg['inc_angle'].replace('na', -1)
train_data, test_data = train_test_split(iceberg,
train_size=.75,
random_state=123)
pars = [(chan, norm, angle) for chan in ('none', 'diff', 'avg')
for angle in (True, False) for norm in (True, False)]
# Run Experiments on
for p in pars:
train_images = get_image_tensor(train_data, extra_channel=p[0])
test_images = get_image_tensor(test_data, extra_channel=p[0])
if p[0] == 'none':
model = create_model(2, p[1], p[2])
else:
model = create_model(3, p[1], p[2])
optimizer = mypotim = RMSprop(lr=0.001)
model.compile(optimizer=optimizer,
loss='binary_crossentropy',
metrics=['accuracy'])
pars_suffix = p[0] + '_' + 'norm_' * p[1] + 'angle_' * p[2]
print(pars_suffix)
}
# Set up data
iceberg = pd.read_json('data/train.json')
train_data, test_data = train_test_split(iceberg,
train_size=.8,
random_state=123)
# Run Experiments on
for i in range(hyperparameter_bounds['n_experiments']):
hyp = get_hyperparameters(hyperparameter_bounds)
print(hyp)
train_images = get_image_tensor(train_data,
extra_channel='none',
normalize=False)
test_images = get_image_tensor(test_data,
extra_channel='none',
normalize=False)
model = create_model(nchannels=2,
base_size=hyp['base_size'],
drop=hyp['dropout'],
activation=hyp['activation'],
normalize_batches=hyp['bn'],
angle=False)
model.compile(optimizer=Adam(lr=hyp['lr']),
loss='binary_crossentropy',
metrics=['accuracy'])
iceberg = pd.read_json('data/train.json')
iceberg['inc_angle'] = iceberg['inc_angle'].replace('na', -1)
train_data, test_data = train_test_split(iceberg,
train_size=.8,
random_state=123)
pars = [(learn, normalize) for learn in (0.0005, 0.0002, 0.0001)
for normalize in (True, False)]
j = 20
# Run Experiments on
for p in pars:
j += 1
train_images = get_image_tensor(train_data,
extra_channel='avg',
normalize=p[1])
test_images = get_image_tensor(test_data,
extra_channel='avg',
normalize=p[1])
model = create_model(3, False, False)
optimizer = Adam(lr=p[0])
model.compile(optimizer=optimizer,
loss='binary_crossentropy',
metrics=['accuracy'])
hist = model.fit(train_images,
train_data.is_iceberg,