def _spherical_upsampling(self, x):
"""Apply spherical paddings to the feature maps before bilinear upsampling.
Args:
x: [BATCH, HEIGHT, WIDTH, CHANNELS] input tensor.
Returns:
a tensor [BATCH, 2*(HEIGHT+2), 2*(WIDTH+2), CHANNELS].
"""
return UpSampling2D(interpolation='bilinear')(
geometry.equirectangular_padding(x, [[1, 1], [1, 1]]))
def __init__(self, filters, trans_down=True, **kwargs):
super(TransitionBlock, self).__init__(**kwargs)
self.filters = filters
self.trans_down = trans_down
self.bn = BatchNormalization()
self.relu = ReLU()
self.conv2d = Conv2D(filters=filters,
kernel_size=(1, 1),
padding="same")
if trans_down:
self.pool2d = AvgPool2D(pool_size=2, strides=2)
else:
self.pool2d = UpSampling2D(size=(2, 2))
''' Create the network. '''
factor = 1
print('FACTOR:', factor)
''' Create the network. '''
latent_size = 200
loc = Sequential([
Dense(int(factor * 128) * 7 * 7, input_dim=latent_size),
Reshape((7, 7, int(factor * 128))),
Conv2D(int(factor * 64), (5, 5),
padding='same',
kernel_initializer='he_uniform'),
LeakyReLU(),
BatchNormalization(),
UpSampling2D(size=(2, 2), interpolation='bilinear'),
ZeroPadding2D((2, 2)),
# LocallyConnected2D(int(factor*6), (5, 5), kernel_initializer='he_uniform'),
Conv2D(int(factor * 6), (5, 5), kernel_initializer='he_uniform'),
LeakyReLU(),
BatchNormalization(),
UpSampling2D(size=(2, 2), interpolation='bilinear'),
# LocallyConnected2D(int(factor*6), (3, 3), kernel_initializer='he_uniform'),
Conv2D(int(factor * 6), (3, 3), kernel_initializer='he_uniform'),
LeakyReLU(),
# LocallyConnected2D(1, (2, 2), use_bias=False, kernel_initializer='glorot_normal'),
Conv2D(1, (2, 2), use_bias=False, kernel_initializer='glorot_normal'),
Activation('relu')
])
def create_yolov3_model(nb_class, anchors, max_box_per_image, max_grid,
batch_size, warmup_batches, ignore_thresh, grid_scales,
obj_scale, noobj_scale, xywh_scale, class_scale):
input_image = Input(shape=(None, None, 3)) # net_h, net_w, 3
true_boxes = Input(shape=(1, 1, 1, max_box_per_image, 4))
true_yolo_1 = Input(
shape=(None, None, len(anchors) // 6,
4 + 1 + nb_class)) # grid_h, grid_w, nb_anchor, 5+nb_class
true_yolo_2 = Input(
shape=(None, None, len(anchors) // 6,
4 + 1 + nb_class)) # grid_h, grid_w, nb_anchor, 5+nb_class
true_yolo_3 = Input(
shape=(None, None, len(anchors) // 6,
4 + 1 + nb_class)) # grid_h, grid_w, nb_anchor, 5+nb_class
# Layer 0 => 4
x = _conv_block(input_image, [{
'filter': 32,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 0
}, {
'filter': 64,
'kernel': 3,
'stride': 2,
'bnorm': True,
'leaky': True,
'layer_idx': 1
}, {
'filter': 32,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 2
}, {
'filter': 64,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 3
}])
# Layer 5 => 8
x = _conv_block(x, [{
'filter': 128,
'kernel': 3,
'stride': 2,
'bnorm': True,
'leaky': True,
'layer_idx': 5
}, {
'filter': 64,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 6
}, {
'filter': 128,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 7
}])
# Layer 9 => 11
x = _conv_block(x, [{
'filter': 64,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 9
}, {
'filter': 128,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 10
}])
# Layer 12 => 15
x = _conv_block(x, [{
'filter': 256,
'kernel': 3,
'stride': 2,
'bnorm': True,
'leaky': True,
'layer_idx': 12
}, {
'filter': 128,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 13
}, {
'filter': 256,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 14
}])
# Layer 16 => 36
for i in range(7):
x = _conv_block(x, [{
'filter': 128,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 16 + i * 3
}, {
'filter': 256,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 17 + i * 3
}])
skip_36 = x
# Layer 37 => 40
x = _conv_block(x, [{
'filter': 512,
'kernel': 3,
'stride': 2,
'bnorm': True,
'leaky': True,
'layer_idx': 37
}, {
'filter': 256,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 38
}, {
'filter': 512,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 39
}])
# Layer 41 => 61
for i in range(7):
x = _conv_block(x, [{
'filter': 256,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 41 + i * 3
}, {
'filter': 512,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 42 + i * 3
}])
skip_61 = x
# Layer 62 => 65
x = _conv_block(x, [{
'filter': 1024,
'kernel': 3,
'stride': 2,
'bnorm': True,
'leaky': True,
'layer_idx': 62
}, {
'filter': 512,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 63
}, {
'filter': 1024,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 64
}])
# Layer 66 => 74
for i in range(3):
x = _conv_block(x, [{
'filter': 512,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 66 + i * 3
}, {
'filter': 1024,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 67 + i * 3
}])
# Layer 75 => 79
x = _conv_block(x, [{
'filter': 512,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 75
}, {
'filter': 1024,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 76
}, {
'filter': 512,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 77
}, {
'filter': 1024,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 78
}, {
'filter': 512,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 79
}],
do_skip=False)
# Layer 80 => 82
pred_yolo_1 = _conv_block(x, [{
'filter': 1024,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 80
}, {
'filter': (3 * (5 + nb_class)),
'kernel': 1,
'stride': 1,
'bnorm': False,
'leaky': False,
'layer_idx': 81
}],
do_skip=False)
loss_yolo_1 = YoloLayer(
anchors[12:], [1 * num
for num in max_grid], batch_size, warmup_batches,
ignore_thresh, grid_scales[0], obj_scale, noobj_scale, xywh_scale,
class_scale)([input_image, pred_yolo_1, true_yolo_1, true_boxes])
# Layer 83 => 86
x = _conv_block(x, [{
'filter': 256,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 84
}],
do_skip=False)
x = UpSampling2D(2)(x)
x = concatenate([x, skip_61])
# Layer 87 => 91
x = _conv_block(x, [{
'filter': 256,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 87
}, {
'filter': 512,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 88
}, {
'filter': 256,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 89
}, {
'filter': 512,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 90
}, {
'filter': 256,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 91
}],
do_skip=False)
# Layer 92 => 94
pred_yolo_2 = _conv_block(x, [{
'filter': 512,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 92
}, {
'filter': (3 * (5 + nb_class)),
'kernel': 1,
'stride': 1,
'bnorm': False,
'leaky': False,
'layer_idx': 93
}],
do_skip=False)
loss_yolo_2 = YoloLayer(
anchors[6:12], [2 * num
for num in max_grid], batch_size, warmup_batches,
ignore_thresh, grid_scales[1], obj_scale, noobj_scale, xywh_scale,
class_scale)([input_image, pred_yolo_2, true_yolo_2, true_boxes])
# Layer 95 => 98
x = _conv_block(x, [{
'filter': 128,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 96
}],
do_skip=False)
x = UpSampling2D(2)(x)
x = concatenate([x, skip_36])
# Layer 99 => 106
pred_yolo_3 = _conv_block(x, [{
'filter': 128,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 99
}, {
'filter': 256,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 100
}, {
'filter': 128,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 101
}, {
'filter': 256,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 102
}, {
'filter': 128,
'kernel': 1,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 103
}, {
'filter': 256,
'kernel': 3,
'stride': 1,
'bnorm': True,
'leaky': True,
'layer_idx': 104
}, {
'filter': (3 * (5 + nb_class)),
'kernel': 1,
'stride': 1,
'bnorm': False,
'leaky': False,
'layer_idx': 105
}],
do_skip=False)
loss_yolo_3 = YoloLayer(
anchors[:6], [4 * num for num in max_grid], batch_size, warmup_batches,
ignore_thresh, grid_scales[2], obj_scale, noobj_scale, xywh_scale,
class_scale)([input_image, pred_yolo_3, true_yolo_3, true_boxes])
train_model = Model(
[input_image, true_boxes, true_yolo_1, true_yolo_2, true_yolo_3],
[loss_yolo_1, loss_yolo_2, loss_yolo_3])
infer_model = Model(input_image, [pred_yolo_1, pred_yolo_2, pred_yolo_3])
return [train_model, infer_model]
""" Create the network. """
factor = 1
print("FACTOR:", factor)
""" Create the network. """
latent_size = 200
loc = Sequential([
Dense(int(factor * 128) * 7 * 7, input_dim=latent_size),
Reshape((7, 7, int(factor * 128))),
Conv2D(int(factor * 64), (5, 5),
padding="same",
kernel_initializer="he_uniform"),
LeakyReLU(),
BatchNormalization(),
UpSampling2D(size=(2, 2), interpolation="bilinear"),
ZeroPadding2D((2, 2)),
# LocallyConnected2D(int(factor*6), (5, 5), kernel_initializer='he_uniform'),
Conv2D(int(factor * 6), (5, 5), kernel_initializer="he_uniform"),
LeakyReLU(),
BatchNormalization(),
UpSampling2D(size=(2, 2), interpolation="bilinear"),
# LocallyConnected2D(int(factor*6), (3, 3), kernel_initializer='he_uniform'),
Conv2D(int(factor * 6), (3, 3), kernel_initializer="he_uniform"),
LeakyReLU(),
# LocallyConnected2D(1, (2, 2), use_bias=False, kernel_initializer='glorot_normal'),
Conv2D(1, (2, 2), use_bias=False, kernel_initializer="glorot_normal"),
Activation("relu"),
])
latent = Input(shape=(latent_size, ))