def inputs(self):
return [
tf.TensorSpec((None, SHAPE, SHAPE, CHANNELS), tf.uint8,
'input_img'),
tf.TensorSpec((None, SHAPE, SHAPE, CHANNELS), tf.uint8,
'target_img')
]
def inputs(self):
ret = [
tf.TensorSpec((None, None, 3), tf.float32, 'image'),
tf.TensorSpec((None, None, cfg.RPN.NUM_ANCHOR), tf.int32,
'anchor_labels'),
tf.TensorSpec((None, None, cfg.RPN.NUM_ANCHOR, 4), tf.float32,
'anchor_boxes'),
tf.TensorSpec((None, 4), tf.float32, 'gt_boxes'),
tf.TensorSpec((None, ), tf.int64, 'gt_labels')
] # all > 0
if cfg.MODE_MASK:
ret.append(
tf.TensorSpec((None, None, None), tf.uint8, 'gt_masks_packed')
) # NR_GT x height x ceil(width/8), packed groundtruth masks
return ret
def inputs(self):
ret = [tf.TensorSpec((None, None, 3), tf.float32, 'image')]
num_anchors = len(cfg.RPN.ANCHOR_RATIOS)
for k in range(len(cfg.FPN.ANCHOR_STRIDES)):
ret.extend([
tf.TensorSpec((None, None, num_anchors), tf.int32,
'anchor_labels_lvl{}'.format(k + 2)),
tf.TensorSpec((None, None, num_anchors, 4), tf.float32,
'anchor_boxes_lvl{}'.format(k + 2))
])
ret.extend([
tf.TensorSpec((None, 4), tf.float32, 'gt_boxes'),
tf.TensorSpec((None, ), tf.int64, 'gt_labels')
]) # all > 0
if cfg.MODE_MASK:
ret.append(
tf.TensorSpec((None, None, None), tf.uint8, 'gt_masks_packed'))
return ret
def inputs(self):
"""
Define all the inputs (with type, shape, name) that the graph will need.
"""
return [tf.TensorSpec((None, IMAGE_SIZE, IMAGE_SIZE), tf.float32, 'input'),
tf.TensorSpec((None,), tf.int32, 'label')]
def inputs(self):
return [
tf.TensorSpec([None, INPUT_SHAPE, INPUT_SHAPE, 3], tf.float32,
'input'),
tf.TensorSpec([None], tf.int32, 'label')
]
def inputs(self):
return [tf.TensorSpec((None, IMAGE_SIZE, IMAGE_SIZE, 2), tf.float32, 'input'),
tf.TensorSpec((None,), tf.int32, 'label')]
def inputs(self):
return [tf.TensorSpec([None, self.image_shape, self.image_shape, 3], self.image_dtype, 'input'),
tf.TensorSpec([None], tf.int32, 'label')]
def inputs(self):
return [
tf.TensorSpec((None, 30, 30, 3), tf.float32, 'input'),
tf.TensorSpec((None, ), tf.int32, 'label')
]
def inputs(self):
# The inference graph only accepts a single image, which is different to the training model.
return [tf.TensorSpec((None, ), tf.string, 'input_img_bytes')]
def inputs(self):
return [
tf.TensorSpec([None, 40, 40, 3], tf.float32, 'input'),
tf.TensorSpec([None], tf.int32, 'label')
]