dexception

------------DO NOT WASTE YOUR TIME-------------

3

Issued in interest by a fellow developer.

What is the cuda and cudnn required for this repo ?

8

What is the cuda and cudnn required for this repo ?

Please update the repo for Vehicle Detection

6

Hi, Can you please add the remaining part of the code for Vehicle Detection ? This would make this repo complete. Thanks. Awesome work buddy. Keep it up.

CPU usage is too high

1

For 1920x1080 resolution. The CPU is around 2 i7 cores. May the pipeline configured with TCP/UDP connection will yield more efficiency.

Zero Detections using Quantization [BUG]

2

Model Name: Yolov3-Tiny Trained Resolution: 832x832 Detections using Yolo2_light: 10 Detections using Yolo2_light -quantized: 0 Detections using TensorRT: 10 Detections using TensorRT int8: 7 Output: ``` Quantinization! old_weight_mult = 2.000000,...

TensorRT ?

1

TensorRT implementation ?

``` import numpy as np import nnvm.compiler import nnvm.testing import tvm from tvm.contrib import graph_runtime import mxnet as mx import cv2 from mxnet import ndarray as nd ctx = tvm.cpu()...

Onnx conversion

2

Model: opus-mt Won't be a bad idea to convert it to onnx.

Any change to see the accuracy before training our own model ?

Hindi Language NER Training format

15

I already have tagged data in the following format: **WORD tab POS_TAG tab NER** भारत NNP loc की PSP O पहली QO O महिला NNC O फोटो NN O जर्नलिस्ट...