habana_frameworks.mediapipe.fn.SSDEncode
habana_frameworks.mediapipe.fn.SSDEncode¶
- Class:
habana_frameworks.mediapipe.fn.SSDEncode(**kwargs)
- Define graph call:
__call__(boxes, labels, lengths)
Parameter:
boxes - Input tensor of bounding boxes (each bbox should be in [left, top, right, bottom] format). size=[batch, 200, 4] Supported dimensions: minimum = 3, maximum = 3. Supported data types: FLOAT32.
labels - Input tensor of image labels for each bounding box. size=[batch, 200]. Supported dimensions: minimum = 2, maximum = 2. Supported data types: UINT32.
lengths - Input tensor of number of bounding boxes per image. size=[batch]. Supported dimensions: minimum = 1, maximum = 1. Supported data types: UINT32.
Description:
SSDEncode operator encodes input bounding boxes and labels using predefined 8732 SSD anchor boxes.
- Supported backend:
CPU
Output:
Output Value |
Description |
|---|---|
boxes |
List of encoded (wrt 8732 anchors) bounding boxes for every image [x, y, w, h]. |
labels |
List of labels for every encoded bounding box. |
Example: SSDEncode Operator
The following code snippet shows usage of SSDEncode operator:
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
import matplotlib.pyplot as plt
import os
g_display_timeout = os.getenv("DISPLAY_TIMEOUT") or 5
class myMediaPipe(MediaPipe):
def __init__(self, device, queue_depth, batch_size, num_threads,
op_device, dir, ann_file, img_h, img_w):
super(
myMediaPipe,
self).__init__(
device,
queue_depth,
batch_size,
num_threads,
self.__class__.__name__)
self.input = fn.CocoReader(root=dir,
annfile=ann_file,
seed=1234,
shuffle=False,
drop_remainder=True,
num_slices=1,
slice_index=0,
partial_batch=False,
device='cpu')
self.reshape_ids = fn.Reshape(size=[batch_size],
tensorDim=1,
layout='',
dtype=dt.UINT32, device='hpu')
self.ssd_crop_win_gen = fn.SSDCropWindowGen(num_iterations=1,
seed=1234,
device='cpu')
self.ssd_encode = fn.SSDEncode(device='cpu')
self.decode = fn.ImageDecoder(device="hpu",
output_format=it.RGB_P,
resize=[img_w, img_h])
# WHCN -> CWHN
self.transpose = fn.Transpose(permutation=[2, 0, 1, 3],
tensorDim=4,
dtype=dt.UINT8)
def definegraph(self):
# Train pipe
jpegs, ids, sizes, boxes, labels, lengths, batch = self.input()
# ssd crop window generation
sizes, boxes, labels, lengths, windows = self.ssd_crop_win_gen(
sizes, boxes, labels, lengths)
images = self.decode(jpegs, windows)
# ssd encode
boxes, labels = self.ssd_encode(boxes, labels, lengths)
images = self.transpose(images)
return images, boxes, labels
def display_images(images, batch_size, cols):
rows = (batch_size + 1) // cols
plt.figure(figsize=(10, 10))
for i in range(batch_size):
ax = plt.subplot(rows, cols, i + 1)
plt.imshow(images[i])
plt.axis("off")
plt.show(block=False)
plt.pause(g_display_timeout)
plt.close()
def run(device, op_device):
batch_size = 6
img_width = 300
img_height = 300
num_threads = 1
queue_depth = 2
base_dir = os.environ['DATASET_DIR']
base_dir = base_dir+"/coco_data/"
dir = base_dir + "/imgs/"
ann_file = base_dir + "/annotation.json"
# Create MediaPipe object
pipe = myMediaPipe(device, queue_depth, batch_size, num_threads,
op_device, dir, ann_file, img_height, img_width)
# Build MediaPipe
pipe.build()
# Initialize MediaPipe iterator
pipe.iter_init()
# Run MediaPipe
images, boxes, labels = pipe.run()
# Copy data to host from device as numpy array
images = images.as_cpu().as_nparray()
boxes = boxes.as_nparray()
labels = labels.as_nparray()
del pipe
print('coco boxes dtype:', boxes.dtype)
print('coco boxes:', boxes)
print('coco labels dtype:', labels.dtype)
print('coco labels:', labels)
display_images(images, batch_size, 3)
if __name__ == "__main__":
dev_opdev = {'mixed': ['cpu']}
for dev in dev_opdev.keys():
for op_dev in dev_opdev[dev]:
run(dev, op_dev)
SSB BBox Encode Output Images 1
- 1
The following is the output of SSDMetadata operator:
coco boxes dtype: float32
coco boxes: [[[0.01333333 0.01333333 0.07 0.07 ]
[0.04 0.01333333 0.07 0.07 ]
[0.06666667 0.01333333 0.07 0.07 ]
...
[0.5 0.5 0.9557719 0.9557719 ]
[0.5 0.5 1. 0.6151829 ]
[0.5 0.5 0.6151829 1. ]]
[[0.01333333 0.01333333 0.07 0.07 ]
[0.04 0.01333333 0.07 0.07 ]
[0.06666667 0.01333333 0.07 0.07 ]
...
[0.5 0.5 0.9557719 0.9557719 ]
[0.5 0.5 1. 0.6151829 ]
[0.5 0.5 0.6151829 1. ]]
[[0.01333333 0.01333333 0.07 0.07 ]
[0.04 0.01333333 0.07 0.07 ]
[0.06666667 0.01333333 0.07 0.07 ]
...
[0.5 0.5 0.9557719 0.9557719 ]
[0.5 0.5 1. 0.6151829 ]
[0.5 0.5 0.6151829 1. ]]
[[0.01333333 0.01333333 0.07 0.07 ]
[0.04 0.01333333 0.07 0.07 ]
[0.06666667 0.01333333 0.07 0.07 ]
...
[0.5 0.5 0.9557719 0.9557719 ]
[0.5 0.5 1. 0.6151829 ]
[0.5 0.5 0.6151829 1. ]]
[[0.01333333 0.01333333 0.07 0.07 ]
[0.04 0.01333333 0.07 0.07 ]
[0.06666667 0.01333333 0.07 0.07 ]
...
[0.49218747 0.45380607 0.98437494 0.90761214]
[0.49218747 0.45380607 0.98437494 0.90761214]
[0.49218747 0.45380607 0.98437494 0.90761214]]
[[0.01333333 0.01333333 0.07 0.07 ]
[0.04 0.01333333 0.07 0.07 ]
[0.06666667 0.01333333 0.07 0.07 ]
...
[0.5441176 0.49999997 0.9117647 0.99999994]
[0.5441176 0.49999997 0.9117647 0.99999994]
[0.5441176 0.49999997 0.9117647 0.99999994]]]
coco labels dtype: int32
coco labels: [[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]
[0 0 0 ... 2 2 2]
[0 0 0 ... 2 2 2]]