-
**Is your feature request related to a problem? Please describe.**
There is apparently today no way to run any NN inference using the core engine.
There is also actually no easy way to infer a linea…
-
looks like we have inconsistency between the two classes.
For symmetric tensors `A*B = A_{ij} B_{ij}` (double contraction, returns scalar).
Whereas for non-symmetric tensor `A*B = A_{ij} B_{jk}`…
-
### 问题描述 Issue Description
参考文档：https://www.paddlepaddle.org.cn/inference/v2.1/user_guides/compile_ARM.html
1. cmake 参数
cmake .. -DPY_VERSION=3 -DPYTHON_EXECUTABLE=`which python3` -DWITH_ARM=ON -DW…
-
## Issue description
The efficient conversion between COO and CSR formats is important because constructing a sparse tensor is simplest when using COO format while many linear algebra operations in…
pearu updated
3 years ago
-
I trained and saved a model that uses a custom loss function (Keras version: 2.0.2):
`model.compile(optimizer=adam, loss=SSD_Loss(neg_pos_ratio=neg_pos_ratio, alpha=alpha).compute_loss)`
When I …
-
java.lang.IllegalStateException: Internal error: Unexpected failure when preparing tensor allocations: tensorflow/lite/kernels/reshape.cc:66 num_input_elements != num_output_elements (800 != 400)
…
-
Hi, I'm going to implement the postprocessing for the YOLOv4 model in the KotlinDL library, but it requires many different analogs of the NumPy functions.
Could you please add the analog of the [`n…
-
**System information**
- Have I written custom code (as opposed to using a stock example script provided in TensorFlow): yes
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 20.04
…
-
-
Should tensordot broadcast the contracted dimensions. For example, say we contract the first dimensions here
```py
tensordot(ones((3, 3)), ones((1, 3)), axes=((0,), (0,)))
```
The dimension 3 …