djl

djl copied to clipboard

The test was failing on the machine installed cuda but no GPU ## Description ## Brief description of what this PR is about - If this change is a backward...

frankfliu

## Description ## Brief description of what this PR is about - If this change is a backward incompatible change, why must this change be made? - Interesting edge cases...

xyang16


liautumn

MXNet NLP GloVe model causes error "Native resource has been released already"

3

## Description When I try to use the MXNet zoo model `ai.djl.mxnet/glove/0.0.2/glove`, it throws the following error and I cannot use it for NLP word embedding: ``` Exception in thread...

tadayosi

## Description ## Brief description of what this PR is about - If this change is a backward incompatible change, why must this change be made? - Interesting edge cases...

frankfliu

Fixes: #3286 ## Description ## Brief description of what this PR is about - If this change is a backward incompatible change, why must this change be made? - Interesting...

frankfliu

TimeSeries API Bugs (frequency, context length, FEAT_DYNAMIC_REAL)

6

If we specify the frequency as required by the Lag class or as the GluonTS documentation says,  for example "1H", "H", "15min", we will get an exception: ``` Exception...

keklol5050

Can I load a pytorch pretrained model, and use its block to replace one in my network?

1

I want to embed the block inside my network

kobe2000

PaddlePaddle引擎使用paddleocr v4版本的模型识别图像时报错，是还不支持paddleocr的v4模型吗?

2

//Application.CV.Image Criteria recognitionCriteria = Criteria.builder() .optEngine("PaddlePaddle") .setTypes(Image.class, String.class) .optModelPath("V:\AI\paddle\ocr\model\en_PP-OCRv4_rec_1203-02") .optTranslator(new PpWordRecognitionTranslator()) .build(); recognitionModel = recognitionCriteria.loadModel(); Image img = ImageFactory.getInstance().fromFile(Path.of(filePath)); Predictor recognizer = recognitionModel.newPredictor(); String text = recognizer.predict(img); 这样报错，使用paddleocr v3 版本模型时，就没有问题，...

wxy5001

ONNX Engine Options Bug, ONNX features cannot be defined，It's a parameter type design problem

2

## Description **Generic parameters are inconsistent problem, fail to deliver correctly.** **Details code is as follows:** > code in **ai.djl.repository.zoo.Criteria** ```java public class Criteria { ... private Map options; private...

TommysLee