deepdetect
deepdetect copied to clipboard
Deep Learning API and Server in C++14 support for Caffe, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE
#### Configuration - Version of DeepDetect: - [ ] Locally compiled on: - [ ] Ubuntu 18.04 LTS - [ ] Other: - [ ] Docker CPU - [x] Docker...
…applying a softmax to the model output (default enabled) Note: not sure if `_module._softmax_preprocess` (see torchmodule.h) is the right place to store this value, happy to move it around if...
Update to fix some dlib regressions, and update the dlib version (which also fixes one new issue with opencv4). This should be merged after https://github.com/jolibrain/deepdetect/pull/1448.
Hi, as you all know, Java is underrated, and it is now in 2022 a reality that C++ is doomed to fail. Therefore I would strongly suggest to give up...
For example,` /xxxxxx.jpg` really does not exist, I would expect a message like "unable to open file" or similar, but I get an error about the size of the file....
## feat: use DTO for NCNN init parameters ## refactor(dto): example service_create+ncnn The Service Create call works, but most parameters doesn't. Supported parameters are only those declared in the DTO...