Python EasyDict.AUGMENTOR Examples

Example #1

File: flownet_s_v2_quantize.py Project: OscarWang114/blueoil

# rotation          U([-17 deg, +17 deg])
# scaling           U([0.9, 2.0])
# Pixel-Wise transformation
# Gaussian noise    N(0, 1) * U([0.0, 0.04 * (255)])
# contrast          U([0.2, 1.4])
# color             U([0.5, 2.0])
# gamma             U([0.7, 1.5])
# brightness        1 + 0.2 * N(0, 1)

# NOTE (by KI-42) in this setup, I modified the augmentation setup described above a little bit.
# hue               U([-128 deg, 128 deg])
# brightness        U(0.6, 1.4)

DATASET.AUGMENTOR = Sequence([
    # Geometric transformation
    FlipLeftRight(0.5),
    FlipTopBottom(0.5),
    Translate(-0.2, 0.2),
    Rotate(-17, +17),
    Scale(1.0, 2.0),
    # Pixel-wise augmentation
    Brightness(0.6, 1.4),
    Contrast(0.2, 1.4),
    Color(0.5, 2.0),
    Gamma(0.7, 1.5),
    # Hue(-128.0, 128.0),
    GaussianNoise(10.0)
    # GaussianBlur(0.0, 2.0)
])
DATASET.PRE_PROCESSOR = PRE_PROCESSOR

Example #2

PRE_PROCESSOR = Sequence([Resize(size=IMAGE_SIZE), PerImageStandardization()])
POST_PROCESSOR = None

NETWORK = EasyDict()
NETWORK.OPTIMIZER_CLASS = tf.train.MomentumOptimizer
NETWORK.OPTIMIZER_KWARGS = {"momentum": 0.9}
NETWORK.LEARNING_RATE_FUNC = tf.train.piecewise_constant
NETWORK.LEARNING_RATE_KWARGS = {
    "values": [0.1, 0.01, 0.001, 0.0001],
    "boundaries": [40000, 60000, 80000],
}
NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT
NETWORK.WEIGHT_DECAY_RATE = 0.0001
NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
NETWORK.ACTIVATION_QUANTIZER_KWARGS = {'bit': 2, 'max_value': 2}
NETWORK.WEIGHT_QUANTIZER = binary_mean_scaling_quantizer
NETWORK.WEIGHT_QUANTIZER_KWARGS = {}

# dataset
DATASET = EasyDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence([
    Pad(2),
    Crop(size=IMAGE_SIZE),
    FlipLeftRight(),
])

Example #3

File: segnet_quantize_camvid_tune.py Project: yasumura-lm/blueoil

        },
    ]),
}

NETWORK = EasyDict()
NETWORK.OPTIMIZER_CLASS = None
NETWORK.OPTIMIZER_KWARGS = {}
NETWORK.LEARNING_RATE_FUNC = None
NETWORK.LEARNING_RATE_KWARGS = {}
NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT
NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
NETWORK.ACTIVATION_QUANTIZER_KWARGS = {'bit': 2, 'max_value': 2}
NETWORK.WEIGHT_QUANTIZER = binary_mean_scaling_quantizer
NETWORK.WEIGHT_QUANTIZER_KWARGS = {}

DATASET = EasyDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence([
    Brightness((0.75, 1.25)),
    Color((0.75, 1.25)),
    Contrast((0.75, 1.25)),
    FlipLeftRight(),
    Hue((-10, 10)),
])

DATASET.ENABLE_PREFETCH = False

Example #4

}
NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT
NETWORK.ANCHORS = anchors
NETWORK.OBJECT_SCALE = 5.0
NETWORK.NO_OBJECT_SCALE = 1.0
NETWORK.CLASS_SCALE = 1.0
NETWORK.COORDINATE_SCALE = 1.0
NETWORK.LOSS_IOU_THRESHOLD = 0.6
NETWORK.WEIGHT_DECAY_RATE = 0.0005
NETWORK.SCORE_THRESHOLD = score_threshold
NETWORK.NMS_IOU_THRESHOLD = nms_iou_threshold
NETWORK.NMS_MAX_OUTPUT_SIZE = nms_max_output_size
NETWORK.LOSS_WARMUP_STEPS = int(8000 / BATCH_SIZE)

# dataset
DATASET = EasyDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence([
    FlipLeftRight(),
    Brightness((0.75, 1.25)),
    Color((0.75, 1.25)),
    Contrast((0.75, 1.25)),
    Hue((-10, 10)),
    SSDRandomCrop(min_crop_ratio=0.7),
])
DATASET.ENABLE_PREFETCH = True

Example #5

# pretrain
IS_PRETRAIN = False
PRETRAIN_VARS = []
PRETRAIN_DIR = ""
PRETRAIN_FILE = ""

PRE_PROCESSOR = Sequence([Resize(size=IMAGE_SIZE), PerImageStandardization()])
POST_PROCESSOR = None

NETWORK = EasyDict()
NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT
NETWORK.WEIGHT_DECAY_RATE = 0.0005
NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
NETWORK.ACTIVATION_QUANTIZER_KWARGS = {'bit': 2, 'max_value': 2}
NETWORK.WEIGHT_QUANTIZER = binary_mean_scaling_quantizer
NETWORK.WEIGHT_QUANTIZER_KWARGS = {}

# dataset
DATASET = EasyDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence([
    FlipLeftRight(),
])

Example #6

File: lm_flownet_5_c_quarter.py Project: ki-lm/blueoil

NETWORK.OPTIMIZER_KWARGS = {"beta1": 0.9, "beta2": 0.999}
NETWORK.LEARNING_RATE_FUNC = tf.train.piecewise_constant
NETWORK.LEARNING_RATE_KWARGS = {
    "values": [0.0001, 0.00005, 0.000025, 0.0000125, 0.00000625],
    "boundaries": [400000, 600000, 800000, 1000000],
}
NETWORK.CONV_DEPTH = CONV_DEPTH
NETWORK.DIV_FLOW = 20.0
NETWORK.WEIGHT_DECAY_RATE = 0.0004
NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT

# dataset
DATASET = EasyDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.SLICE_STEP = SLICE_STEP
DATASET.TRAIN_ENABLE_PREFETCH = True
DATASET.TRAIN_PROCESS_NUM = 10
DATASET.TRAIN_QUEUE_SIZE = 1000
DATASET.VALIDATION_ENABLE_PREFETCH = False
DATASET.VALIDATION_PRE_LOAD = False
DATASET.VALIDATION_PROCESS_NUM = 1
DATASET.VALIDATION_QUEUE_SIZE = 500
DATASET.VALIDATION_RATE = 0.1
DATASET.VALIDATION_SEED = 2019

DATASET.AUGMENTOR = AUGMENTOR
DATASET.PRE_PROCESSOR = PRE_PROCESSOR

Example #7

    Resize(size=IMAGE_SIZE),
    {% if quantize_first_convolution %}DivideBy255(){% else %}PerImageStandardization(){% endif %}
])
POST_PROCESSOR = None

NETWORK = EasyDict()
NETWORK.OPTIMIZER_CLASS = {{optimizer_class}}
NETWORK.OPTIMIZER_KWARGS = {{optimizer_kwargs}}
NETWORK.LEARNING_RATE_FUNC = {{learning_rate_func}}
NETWORK.LEARNING_RATE_KWARGS = {{learning_rate_kwargs}}

NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT
NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
NETWORK.ACTIVATION_QUANTIZER_KWARGS = {
    'bit': 2,
    'max_value': 2
}
NETWORK.WEIGHT_QUANTIZER = binary_mean_scaling_quantizer
NETWORK.WEIGHT_QUANTIZER_KWARGS = {}

DATASET = EasyDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence([{% if data_augmentation %}{% for augmentor in data_augmentation %}
    {{ augmentor[0] }}({% for d_name, d_value in augmentor[1] %}{{ d_name }}={{ d_value }}, {% endfor %}),{% endfor %}
{% endif %}])
DATASET.ENABLE_PREFETCH = {{ dataset_prefetch }}

Example #8

File: openimages_face_sample.py Project: hadusam/bluegrass

NETWORK.WEIGHT_DECAY_RATE = 0.0005
NETWORK.SCORE_THRESHOLD = score_threshold
NETWORK.NMS_IOU_THRESHOLD = nms_iou_threshold
NETWORK.NMS_MAX_OUTPUT_SIZE = nms_max_output_size
NETWORK.LOSS_WARMUP_STEPS = int(8000 / BATCH_SIZE)

# quantize
NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
NETWORK.ACTIVATION_QUANTIZER_KWARGS = {
    'bit': 2,
    'max_value': 2.0
}
NETWORK.WEIGHT_QUANTIZER = binary_channel_wise_mean_scaling_quantizer
NETWORK.WEIGHT_QUANTIZER_KWARGS = {}
NETWORK.QUANTIZE_FIRST_CONVOLUTION = False
NETWORK.QUANTIZE_LAST_CONVOLUTION = False

# dataset
DATASET = EasyDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence([
    Brightness(value=(0.75, 1.25), ),
    Color(value=(0.75, 1.25), ),
    FlipLeftRight(probability=0.5, ),
    Hue(value=(-10, 10), ),
    SSDRandomCrop(min_crop_ratio=0.3, ),
])
DATASET.ENABLE_PREFETCH = True

Example #9

File: lm_bisenet_quantize_camvid.py Project: ytfksw/blueoil

NETWORK = EasyDict()
NETWORK.OPTIMIZER_CLASS = tf.compat.v1.train.AdamOptimizer
NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT
NETWORK.WEIGHT_DECAY_RATE = 0.
NETWORK.AUXILIARY_LOSS_WEIGHT = 0.5
NETWORK.USE_FEATURE_FUSION = True
NETWORK.USE_ATTENTION_REFINEMENT = True
NETWORK.USE_TAIL_GAP = True
NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
NETWORK.ACTIVATION_QUANTIZER_KWARGS = {'bit': 2, 'max_value': 2}
NETWORK.WEIGHT_QUANTIZER = binary_channel_wise_mean_scaling_quantizer
NETWORK.WEIGHT_QUANTIZER_KWARGS = {}

DATASET = EasyDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence([
    Resize(size=IMAGE_SIZE),
    Brightness((0.75, 1.25)),
    Color((0.75, 1.25)),
    Contrast((0.75, 1.25)),
    FlipLeftRight(),
    Hue((-10, 10)),
])
DATASET.ENABLE_PREFETCH = True

Example #10

File: lm_single_pose_v1_quantize_mscoco.py Project: ytfksw/blueoil

step_per_epoch = 149813 // BATCH_SIZE

NETWORK = EasyDict()
NETWORK.OPTIMIZER_CLASS = tf.compat.v1.train.AdamOptimizer
NETWORK.OPTIMIZER_KWARGS = {}
NETWORK.LEARNING_RATE_FUNC = tf.compat.v1.train.piecewise_constant
NETWORK.LEARNING_RATE_KWARGS = {
    "values": [1e-4, 1e-3, 1e-4, 1e-5],
    "boundaries": [5000, step_per_epoch * 5, step_per_epoch * 10],
}
NETWORK.STRIDE = STRIDE
NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT
NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
NETWORK.ACTIVATION_QUANTIZER_KWARGS = {'bit': 2, 'max_value': 2}
NETWORK.WEIGHT_QUANTIZER = binary_channel_wise_mean_scaling_quantizer
NETWORK.WEIGHT_QUANTIZER_KWARGS = {}

DATASET = EasyDict()
DATASET.IMAGE_SIZE = IMAGE_SIZE
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence(
    [Brightness((0.75, 1.25)),
     Color((0.75, 1.25)),
     Contrast((0.75, 1.25))])
DATASET.ENABLE_PREFETCH = True

Example #11

File: for_predict_object_detection.py Project: smilejx/blueoil

        data_format=DATA_FORMAT,
    ),
    ExcludeLowScoreBox(threshold=0.05),
    NMS(
        iou_threshold=0.5,
        classes=CLASSES,
    ),
])

NETWORK = EasyDict()
NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT
NETWORK.ANCHORS = anchors
NETWORK.WEIGHT_DECAY_RATE = 0.0005
NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
NETWORK.ACTIVATION_QUANTIZER_KWARGS = {'bit': 2, 'max_value': 2}
NETWORK.WEIGHT_QUANTIZER = binary_mean_scaling_quantizer
NETWORK.WEIGHT_QUANTIZER_KWARGS = {}

# dataset
DATASET = EasyDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence([
    FlipLeftRight(is_bounding_box=True),
])

Example #12

NETWORK.OPTIMIZER_KWARGS = {'momentum': 0.9}
NETWORK.LEARNING_RATE_FUNC = tf.compat.v1.train.piecewise_constant
NETWORK.LEARNING_RATE_KWARGS = {
    'values': [0.001, 0.0001, 1e-05, 1e-06],
    'boundaries': [25781, 51562, 77343]
}

NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT
NETWORK.WEIGHT_DECAY_RATE = 0.0005

# quantize
NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
NETWORK.ACTIVATION_QUANTIZER_KWARGS = {'bit': 2, 'max_value': 2}
NETWORK.WEIGHT_QUANTIZER = binary_mean_scaling_quantizer
NETWORK.WEIGHT_QUANTIZER_KWARGS = {}

# dataset
DATASET = EasyDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence([
    Brightness(value=(0.75, 1.25), ),
    Color(value=(0.75, 1.25), ),
    FlipLeftRight(probability=0.5, ),
    Hue(value=(-10, 10), ),
])
DATASET.ENABLE_PREFETCH = True

Example #13

File: semantic_segmentation.tpl.py Project: ytfksw/blueoil

    Resize(size=IMAGE_SIZE),
    {% if quantize_first_convolution %}DivideBy255(){% else %}PerImageStandardization(){% endif %}
])
POST_PROCESSOR = None

NETWORK = EasyDict()
NETWORK.OPTIMIZER_CLASS = {{optimizer_class}}
NETWORK.OPTIMIZER_KWARGS = {{optimizer_kwargs}}
NETWORK.LEARNING_RATE_FUNC = {{learning_rate_func}}
NETWORK.LEARNING_RATE_KWARGS = {{learning_rate_kwargs}}

NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT
NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
NETWORK.ACTIVATION_QUANTIZER_KWARGS = {
    'bit': 2,
    'max_value': 2
}
NETWORK.WEIGHT_QUANTIZER = binary_mean_scaling_quantizer
NETWORK.WEIGHT_QUANTIZER_KWARGS = {}

DATASET = EasyDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence([{% if data_augmentation %}{% for aug_name, aug_val in data_augmentation.items() %}
    {{ aug_name }}({% for param_name, param_value in aug_val %}{{ param_name }}={{ param_value }}, {% endfor %}),{% endfor %}
{% endif %}])
DATASET.ENABLE_PREFETCH = {{ dataset_prefetch }}