KimBomm

ProposalLayer: only CPU evaluation is supported at the moment.

12

I made a complete code for FasterRCNN evaluator by C++. Of course i used [CNTK.GPU](https://www.nuget.org/packages/CNTK.GPU/2.2.0) version from Nuget. It works fine only on CPU.....(elapsed time is 11s) But It fails...

tensor dimension mismatch

4

Dear @talebolano . I got below error. Is this my problem? and how can i fix this problem if not. ``` E:\TSpring(YOLO)4classes-new2>python sparsity_train.py -sr --s 0.0001 --image_folder 4classes-new2.data --cfg darknet53.cfg...

line 64 line 74 line 83, 87 (error occured when use variable starts with "from") (e.g. from_numpy) line 137 (replace .(dot) has error occurrence) line 167(missded main_file)

Ah..Sorry I have a same problem. C:\SSD\C++\mxnet-ssd.cpp\build\vc14\Release>ssd.exe person.jpg [18:23:22] C:\MXNET\mxnet\mxnet\dmlc-core\include\dmlc/logging.h:304: [18:23:22] C:\MXNET\mxnet\mxnet\nnvm\src\core\op.cc:55: Check failed: op != nullptr Operator Scale is not registered As you said i tried to download a...

Hello! Could you tell me how to display an image at the top of a Topic like this?

2


Proposal for Optimizing transformers.BertTokenizerFast

4

### Feature request The `transformers.BertTokenizerFast` tokenizer, implemented in Rust, is excellent but has been shown to lag behind other implementations in performance. For instance, [PaddleNLP's BertTokenizerFast](https://paddlenlp.readthedocs.io/en/stable/_modules/paddlenlp/experimental/faster_tokenizer.html), a `C++` implementation, provides...