Pearl

Caused by op 'conv1/Conv2D', defined at: File "train.py", line 253, in main() ... ... UnknownError (see above for traceback): Failed to get convolution algorithm. This is probably because cuDNN failed...

Feature Request: Bilateral Filter

2

Really enjoy the performance and the library's API, Would you kindly consider support bilateral filter, which is too slow on CPU.

Training problem on lidar data only

8

I use lidar data only to train PointRcnn, is the bin-based loss of axis xyz still applicable? If not, where should I modify? In addition, how to set the params...

pip install paddlespeech报错

1

## General Question pip install paddlespeech报错： ERROR: Cannot install paddlespeech==0.0.1a0, paddlespeech==0.0.2a0, paddlespeech==0.1.0a0, paddlespeech==0.1.0a1, paddlespeech==0.1.0a2, paddlespeech==0.1.0a3, paddlespeech==0.1.0a4, paddlespeech==0.1.0a5 and paddlespeech==0.1.0a6 because these package versions have conflicting dependencies. The conflict is caused...

Absence of config.yml

1

@tanzby Hi. I'm using your code, but I can't find the config.yml.

Win7 Matlabr2014b cuda7.5 batch_size=1 max_size=100 @ShaoqingRen @rbgirshick I use script_fast_rcnn_VOC2007_ZF.m and script_fast_rcnn_VOC2007_vgg16.m to tain model on VOC2007, however, it shows that" Error using caffe_glog check error, please check log and...

@kunalmessi10 Hi， I use crf function you provided after the output of my segment model（e.g. deeplabv3）） But the segmentation effert becomes even worse. Is there any possible reason？

How to train yolo with my own dataset

5

@camel007 Hi. I want to train YOLO on my own dataset, but I don't know how to use your opensource. 1. Is leaky layer needed to add in the caffe/layers?...