Python set_param_values Exemples

Exemple #1

Fichier : predict_augmented_npy_maxout2048_extradense_dup3.py Projet : ANB2/kaggle-galaxies

xs_shared = [theano.shared(np.zeros((1,1,1,1), dtype=theano.config.floatX)) for _ in xrange(num_input_representations)]

idx = T.lscalar('idx')

givens = {
    l0.input_var: xs_shared[0][idx*BATCH_SIZE:(idx+1)*BATCH_SIZE],
    l0_45.input_var: xs_shared[1][idx*BATCH_SIZE:(idx+1)*BATCH_SIZE],
}

compute_output = theano.function([idx], l6.predictions(dropout_active=False), givens=givens)


print "Load model parameters"
layers.set_param_values(l6, analysis['param_values'])

print "Create generators"
# set here which transforms to use to make predictions
augmentation_transforms = []
for zoom in [1 / 1.2, 1.0, 1.2]:
    for angle in np.linspace(0, 360, 10, endpoint=False):
        augmentation_transforms.append(ra.build_augmentation_transform(rotation=angle, zoom=zoom))
        augmentation_transforms.append(ra.build_augmentation_transform(rotation=(angle + 180), zoom=zoom, shear=180)) # flipped

print "  %d augmentation transforms." % len(augmentation_transforms)


augmented_data_gen_valid = ra.realtime_fixed_augmented_data_gen(valid_indices, 'train', augmentation_transforms=augmentation_transforms, chunk_size=CHUNK_SIZE, target_sizes=input_sizes, ds_transforms=ds_transforms)
valid_gen = load_data.buffered_gen_mp(augmented_data_gen_valid, buffer_size=1)

Exemple #2

Fichier : predict_augmented_npy_maxout2048_extradense_pysexgen1_dup.py Projet : Keesiu/meta-kaggle

    for _ in range(num_input_representations)
]

idx = T.lscalar('idx')

givens = {
    l0.input_var: xs_shared[0][idx * BATCH_SIZE:(idx + 1) * BATCH_SIZE],
    l0_45.input_var: xs_shared[1][idx * BATCH_SIZE:(idx + 1) * BATCH_SIZE],
}

compute_output = theano.function([idx],
                                 l6.predictions(dropout_active=False),
                                 givens=givens)

print("Load model parameters")
layers.set_param_values(l6, analysis['param_values'])

print("Create generators")
# set here which transforms to use to make predictions
augmentation_transforms = []
for zoom in [1 / 1.2, 1.0, 1.2]:
    for angle in np.linspace(0, 360, 10, endpoint=False):
        augmentation_transforms.append(
            ra.build_augmentation_transform(rotation=angle, zoom=zoom))
        augmentation_transforms.append(
            ra.build_augmentation_transform(rotation=(angle + 180),
                                            zoom=zoom,
                                            shear=180))  # flipped

print("  %d augmentation transforms." % len(augmentation_transforms))

Exemple #3

Fichier : predict_augmented_npy_bigger.py Projet : GregAtHeron/kaggle-galaxies

xs_shared = [
    theano.shared(np.zeros((1, 1, 1, 1), dtype=theano.config.floatX)) for _ in xrange(num_input_representations)
]

idx = T.lscalar("idx")

givens = {
    l0.input_var: xs_shared[0][idx * BATCH_SIZE : (idx + 1) * BATCH_SIZE],
    l0_45.input_var: xs_shared[1][idx * BATCH_SIZE : (idx + 1) * BATCH_SIZE],
}

compute_output = theano.function([idx], l6.predictions(dropout_active=False), givens=givens)


print "Load model parameters"
layers.set_param_values(l6, analysis["param_values"])

print "Create generators"
# set here which transforms to use to make predictions
augmentation_transforms = []
for zoom in [1 / 1.2, 1.0, 1.2]:
    for angle in np.linspace(0, 360, 10, endpoint=False):
        augmentation_transforms.append(ra.build_augmentation_transform(rotation=angle, zoom=zoom))
        augmentation_transforms.append(
            ra.build_augmentation_transform(rotation=(angle + 180), zoom=zoom, shear=180)
        )  # flipped

print "  %d augmentation transforms." % len(augmentation_transforms)


augmented_data_gen_valid = ra.realtime_fixed_augmented_data_gen(