habana_frameworks.mediapipe.fn.Add
habana_frameworks.mediapipe.fn.Add¶
- Class:
habana_frameworks.mediapipe.fn.Add(**kwargs)
- Define graph call:
__call__(input1, input2)
- Parameter:
input1 - First input tensor to operator. Supported dimensions: minimum = 1, maximum = 5. Supported data types: INT16, INT32, FLOAT16, BFLOAT16, FLOAT32.
input2 - Second input tensor to operator. Supported dimensions: minimum = 1, maximum = 5. Supported data types: INT16, INT32, FLOAT16, BFLOAT16, FLOAT32.
Description:
The resulting tensor is formed from the summation of the two operands element-wise. This operator performs element-wise addition and supports Broadcasting
.
Computes output as: output = (input1 + input2), element-wise.
- Supported backend:
HPU, CPU
Keyword Arguments
kwargs |
Description |
---|---|
dtype |
Output data type.
|
Note
All input/output tensors must be of the same data type and must have the same dimensionality except in broadcast support where dimensionality can be different.
This operator is agnostic to the data layout.
Example: Add Operator
The following code snippet shows usage of Add operator:
from habana_frameworks.mediapipe import fn
from habana_frameworks.mediapipe.mediapipe import MediaPipe
from habana_frameworks.mediapipe.media_types import dtype as dt
# Create media pipeline derived class
class myMediaPipe(MediaPipe):
def __init__(self, device, queue_depth, batch_size, num_threads, dir):
super(myMediaPipe, self).__init__(
device,
queue_depth,
batch_size,
num_threads,
self.__class__.__name__)
self.inp1 = fn.ReadNumpyDatasetFromDir(num_outputs=1,
shuffle=False,
dir=dir,
pattern="inp_x_*.npy",
dense=True,
dtype=dt.FLOAT32,
device=device)
self.inp2 = fn.ReadNumpyDatasetFromDir(num_outputs=1,
shuffle=False,
dir=dir,
pattern="inp_y_*.npy",
dense=True,
dtype=dt.FLOAT32,
device=device)
self.add = fn.Add(dtype=dt.FLOAT32,
device=device)
def definegraph(self):
inp1 = self.inp1()
inp2 = self.inp2()
out = self.add(inp1, inp2)
return out, inp1, inp2
def main():
batch_size = 2
queue_depth = 2
num_threads = 1
dir = '/path/to/numpy/files'
device = 'hpu'
# Create media pipeline object
pipe = myMediaPipe(device, queue_depth, batch_size, num_threads, dir)
# Build media pipeline
pipe.build()
# Initialize media pipeline iterator
pipe.iter_init()
# Run media pipeline
out, inp1, inp2 = pipe.run()
if (device == 'cpu'):
# Copy data as numpy array
out = out.as_nparray()
inp1 = inp1.as_nparray()
inp2 = inp2.as_nparray()
else:
# Copy data to host from device as numpy array
out = out.as_cpu().as_nparray()
inp1 = inp1.as_cpu().as_nparray()
inp2 = inp2.as_cpu().as_nparray()
print("\ninp1 tensor shape:", inp1.shape)
print("inp1 tensor dtype:", inp1.dtype)
print("inp1 tensor data:\n", inp1)
print("\ninp2 tensor shape:", inp2.shape)
print("inp2 tensor dtype:", inp2.dtype)
print("inp2 tensor data:\n", inp2)
print("\nout tensor shape:", out.shape)
print("out tensor dtype:", out.dtype)
print("out tensor data:\n", out)
pipe.del_iter()
if __name__ == "__main__":
main()
The following is the output of Add operator:
inp1 tensor shape: (2, 3, 2, 3) inp1 tensor dtype: float32 inp1 tensor data: [[[[182. 227. 113.] [175. 128. 253.]] [[ 58. 140. 136.] [ 86. 80. 111.]] [[175. 196. 178.] [ 20. 163. 108.]]] [[[186. 254. 96.] [180. 64. 132.]] [[149. 50. 117.] [213. 6. 111.]] [[ 77. 11. 160.] [129. 102. 154.]]]] inp2 tensor shape: (2, 3, 2, 3) inp2 tensor dtype: float32 inp2 tensor data: [[[[ 56. 168. 82.] [157. 42. 155.]] [[ 62. 235. 238.] [ 94. 125. 192.]] [[125. 162. 1.] [206. 77. 123.]]] [[[138. 196. 246.] [137. 203. 7.]] [[217. 194. 11.] [167. 218. 226.]] [[ 68. 160. 254.] [243. 93. 70.]]]] out tensor shape: (2, 3, 2, 3) out tensor dtype: float32 out tensor data: [[[[238. 395. 195.] [332. 170. 408.]] [[120. 375. 374.] [180. 205. 303.]] [[300. 358. 179.] [226. 240. 231.]]] [[[324. 450. 342.] [317. 267. 139.]] [[366. 244. 128.] [380. 224. 337.]] [[145. 171. 414.] [372. 195. 224.]]]]