def parse_anchor_parameters(config):
ratios = np.array(
list(map(float, config['anchor_parameters']['ratios'].split(' '))),
keras.backend.floatx())
scales = np.array(
list(map(float, config['anchor_parameters']['scales'].split(' '))),
keras.backend.floatx())
sizes = list(map(int, config['anchor_parameters']['sizes'].split(' ')))
strides = list(map(int, config['anchor_parameters']['strides'].split(' ')))
return AnchorParameters(sizes, strides, ratios, scales)
def parse_anchor_parameters(config):
ratios = np.array(
list(map(float, config['anchor_parameters']['ratios'].split(' '))),
keras.backend.floatx())
scales = np.array(
list(map(float, config['anchor_parameters']['scales'].split(' '))),
keras.backend.floatx())
sizes = list(map(int, config['anchor_parameters']['sizes'].split(' ')))
strides = list(map(int, config['anchor_parameters']['strides'].split(' ')))
assert (len(sizes) == len(strides)
), "sizes and strides should have an equal number of values"
return AnchorParameters(sizes, strides, ratios, scales)
def __init__(
self,
phi=1,
image_sizes=(512, 640, 768, 896, 1024, 1280, 1408),
misc_effect=None,
visual_effect=None,
batch_size=1,
group_method="random", # one of 'none', 'random', 'ratio'
shuffle_groups=True,
detect_text=False,
detect_quadrangle=False,
):
"""
Initialize Generator object.
Args:
batch_size: The size of the batches to generate.
group_method: Determines how images are grouped together (defaults to 'ratio', one of ('none', 'random', 'ratio')).
shuffle_groups: If True, shuffles the groups each epoch.
image_sizes:
"""
self.misc_effect = misc_effect
self.visual_effect = visual_effect
self.batch_size = int(batch_size)
self.group_method = group_method
self.shuffle_groups = shuffle_groups
self.detect_text = detect_text
self.detect_quadrangle = detect_quadrangle
self.image_size = image_sizes[phi]
self.groups = None
self.anchor_parameters = (AnchorParameters.default if
not self.detect_text else AnchorParameters(
ratios=(0.25, 0.5, 1.0, 2.0),
sizes=(16, 32, 64, 128, 256)))
self.anchors = anchors_for_shape((self.image_size, self.image_size),
anchor_params=self.anchor_parameters)
self.num_anchors = self.anchor_parameters.num_anchors()
# Define groups
self.group_images()
# Shuffle when initializing
if self.shuffle_groups:
random.shuffle(self.groups)
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
phi = 3
weighted_bifpn = False
model_path = 'checkpoints/2020-02-20/csv_02_1.6506_2.5878_w.h5'
image_sizes = (512, 640, 768, 896, 1024, 1280, 1408)
image_size = image_sizes[phi]
# classes = [
# 'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair',
# 'cow', 'diningtable', 'dog', 'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor',
# ]
classes = ['text']
num_classes = len(classes)
anchor_parameters = AnchorParameters(
ratios=(0.25, 0.5, 1., 2.),
sizes=(16, 32, 64, 128, 256))
score_threshold = 0.4
colors = [np.random.randint(0, 256, 3).tolist() for i in range(num_classes)]
model, prediction_model = efficientdet(phi=phi,
weighted_bifpn=weighted_bifpn,
num_classes=num_classes,
num_anchors=anchor_parameters.num_anchors(),
score_threshold=score_threshold,
detect_quadrangle=True,
anchor_parameters=anchor_parameters,
)
prediction_model.load_weights(model_path, by_name=True)
import glob
from tensorflow.keras.optimizers import Adam, SGD
from augmentor.color import VisualEffect
from augmentor.misc import MiscEffect
from model import efficientdet
from losses import smooth_l1, focal, smooth_l1_quad
from efficientnet import BASE_WEIGHTS_PATH, WEIGHTS_HASHES
from utils.anchors import AnchorParameters
from generators.ship import ShipGenerator
from eval.common import evaluate
import numpy as np
AnchorParameters.ship = AnchorParameters(
sizes=[32, 64, 128, 256, 512],
strides=[8, 16, 32, 64, 128],
ratios=np.array([0.25, 0.5, 2, 4], keras.backend.floatx()),
scales=np.array([0.25, 0.5, 0.75, 1.0, 1.25], keras.backend.floatx()),
)
def main():
phi = 1
weighted_bifpn = False
image_sizes = (512, 640, 768, 896, 1024, 1280, 1408)
image_size = image_sizes[phi]
score_threshold = 0.9
nms_threshold = 0.5
common_args = {
'batch_size': 1,
'phi': phi,