habana_frameworks.mediapipe.fn.Cast
habana_frameworks.mediapipe.fn.Cast¶
- Class:
habana_frameworks.mediapipe.fn.Cast(**kwargs)
- Define graph call:
__call__(input)
- Parameter:
input - Input tensor to operator. Supported dimensions: minimum = 1, maximum = 5. Supported data types: UINT8, UINT16, UINT32, INT8, INT16, INT32, FLOAT16, BFLOAT16, FLOAT32.
Description:
This operator changes the data type of the input tensor.
- Supported backend:
HPU
Keyword Arguments
kwargs |
Description |
---|---|
round_mode |
Rounding mode selection.
|
dtype |
Output data type.
|
Note
Input and output tensors must have the different data type. Self cast is not allowed.
Cast between all supported data types is allowed.
Example: Cast Operator
The following code snippet shows usage of Cast operator, decoder output is casted to FLOAT32. Print of output image array shows float numbers.
from habana_frameworks.mediapipe import fn
from habana_frameworks.mediapipe.mediapipe import MediaPipe
from habana_frameworks.mediapipe.media_types import imgtype as it
from habana_frameworks.mediapipe.media_types import dtype as dt
class myMediaPipe(MediaPipe):
def __init__(self, device, queue_depth, batch_size, img_h, img_w, dir):
super(
myMediaPipe,
self).__init__(
device,
queue_depth,
batch_size,
self.__class__.__name__)
self.input = fn.ReadImageDatasetFromDir(shuffle=False,
dir=dir,
format="jpg")
# WHCN -> CWHN
self.decode = fn.ImageDecoder(device="hpu",
output_format=it.RGB_I,
resize=[img_w, img_h])
self.cast = fn.Cast(dtype=dt.FLOAT32)
def definegraph(self):
jpegs, labels = self.input()
images = self.decode(jpegs)
images = self.cast(images)
return images, labels
def main():
batch_size = 6
img_width = 224
img_height = 224
queue_depth = 3
img_dir="/path/to/images"
# Create media pipeline object
pipe = myMediaPipe('hpu', queue_depth, batch_size,
img_height, img_width, img_dir)
# Build media pipeline
pipe.build()
# Initialize media pipeline iterator
pipe.iter_init()
# Run media pipeline
images, labels = pipe.run()
# Copy data to host from device as numpy array
images = images.as_cpu().as_nparray()
labels = labels.as_cpu().as_nparray()
# Display data
print(images)
if __name__ == "__main__":
main()
The following is the output of Cast operator:
[[[[122. 113. 94.]
[121. 112. 93.]
[119. 111. 94.]
...
[108. 99. 114.]
[108. 99. 114.]
[109. 100. 115.]]
...
[[101. 125. 78.]
[100. 123. 78.]
[ 97. 120. 78.]
...
[ 41. 50. 44.]
[ 42. 51. 46.]
[ 45. 54. 49.]]]]