-
In [How does FPGA compare to CPU and GPU acceleration](https://github.com/Xilinx/ml-suite/blob/master/docs/tutorials/faq.md#how-does-fpga-compare-to-cpu-and-gpu-acceleration) there a [See white paper …
-
## Intro
Use custom built OpenBlas static lib with dlib as external library in CMake project.
We're build dlib as external project in our CMake project and we would like to build OpenBlas as well …
-
generic wrapper for fitting model that predicts the activity of multiple (possibly simultaneously recorded) neurons. Modules should mostly work as they are. What's different?
Loading:
* specify sit…
-
Hi Alexey,
great work on this darknet fork! I would like to discuss a possible improvement for a better label path handling. Right now the path handling is builtin into the binary:
```cpp
void re…
-
how to use multi dnn object detectors like in function "std::vector evaluate_detectors"
-
Because of the update in 9.2, any module using SharpZipLib before will be incompatible, and updating makes it incompatible with previous DNNs.
This should be fixed. There is a way to intercept DLL…
-
Hi, very interesting approach.
Can you provide some estimates of time performance for predict image classification.
For example how much time takes to predict 28x28 RGB image, it will be great to se…
ghost updated
6 years ago
-
I am expecting the final model after quantization to have all integers in the range -128 to 127 , for 8 -bit symmetric linear quantization, but when I print out the model parameters I noticed that the…
-
### System information
- **Have I written custom code (as opposed to using a stock example script provided in TensorFlow)**:
no (slightly modified)
- **OS Platform and Distribution (e.g., Linux Ubu…
-
## Expected Behavior
Training and running a dnn on CPU with dlib linked against the multithreaded version of MKL should give a speedup of (CPU_Cores - 1) compared to MKL sequential.
## Current Beh…
Zyrin updated
6 years ago