djl

djl copied to clipboard

Tensorflow extensions on Windows not working

1

I tried to load the tensorflow-text extension as described in the documentation (https://djl.ai/docs/tensorflow/how_to_import_tensorflow_models_in_DJL.html) but was unable to do so under Windows. When calling `TensorFlow.loadLibrary()` I get `UnsatisfiedLinkError: no jnitensorflow in...

lucaro

When i am using tensorrt, the first return result is very slow.

4

When i am using tensorrt, the first return result is very slow. After I set follow option： .optEngine("OnnxRuntime") .optOption("ortDevice", "TensorRT") It takes more than 60 seconds for the model to...

mengpengfei

How to avoid false positive

1

Hi Team , I would like to use DJL API for our Automated testing areas to achive visual Testing. Here we are trying to compare two images where each images...

ashish143ti

Exception when running model on GPU: Exception in runBots:ai.djl.engine.EngineException: Could not run 'aten::empty_strided' with arguments from the 'CUDA' backend. This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build).

8

## Description I'm running inference on a model. The model was trained using [YoloV5 in PyTorch](https://github.com/ultralytics/yolov5), and then exported. The inference works perfectly with CPU. However, when I try to...

davpapp

Split EasyTrain to add EasyTrainer

1

This creates a more extensible and non-final class EasyTrainer to contain training functionality formerly in EasyTrain. There have been a few requests to be able to modify EasyTrain and this...

zachgk

The unzipped cache file of the criteria loading model is not verified. (criteria 加载模型的解压缓存文件未进行校验)

1

## Description 使用criteria加载模型，会在`~/.djl.ai/cache/`目录下解压缓存模型文件，但是该解压的文件夹名称未进行校验，导致模型修改后，还会加载已经缓存的模型 Using criteria to load the model, the cached model file will be unzipped in the `~ / .djl.ai / cache/` directory, but the name of the extracted...

fierceX

Create QuantileLoss.java

6

QuantileLoss for training toward a particular quantile, e.g. esimating close to the P75. ## Description ## Sometimes you want to train your estimator for a particular quantile, e.g. the 75th...

gforman44

Speech To Text Example

1

## Description Can documentation be created on how to convert text to speech using the new audio extension? Preferably an example. This is going to help users who are trying...

victorex27

What is this Dataset Artifact ?

3

hey i m implementing objectdetectiondataset with dogs breed images and annotations...while using objectdetectiondataset class i m changing artifact from "pikachu" to "Dogs" and i m getting this error: **java.io.FileNotFoundException: https://mlrepo.djl.ai/dataset/cv/ai/djl/basicdataset/gesture/metadata.json...

nikkisingh111333

tflite-engine do not support windows system well

2

I try to use tflite-engine in my projects and it threw a exception like the following while other engine would download the library automaticlly ``` SLF4J: Failed to load class...

hongyaohongyao