huangh12

Results 7 comments of huangh12

Training loss

@maolin23 @TX2012LH @jgong5 @austingg same problem as you guys. I just train the net in VOC07(less than 500 images), it's quite weired the net fail to converge since the dataset...

Have a look at the results

Example like these: ![cat](https://cloud.githubusercontent.com/assets/18748036/23739672/08141d12-04db-11e7-8b05-a236d2fce64b.jpg) ![seg_cat](https://cloud.githubusercontent.com/assets/18748036/23739682/1069b896-04db-11e7-8ec3-8fe7d8b27819.png)

Difference between dilation8 and dilation10

Hello Timo-hab , I actually have the same question as yours. The input size sounds like a sliding window, but i find no obvious clue proves that. Have you understanded...

Operator with engine CUDNN is not available for operator Relu

Hello, I compiled Caffe2 with Cuda8.0 and Cudnn6.0.5 successfully. But when I run mnist.ipynb in the tutorial directory. It prints out `Operator with engine CUDNN is not available for operator...

Feature Request: Better decoding of blurry QR codes

@alexander-toschev I am curious whether your preprocessing steps improves the accuracy of QR code recognition or not.

How to change settings when installed via pip?

I am also puzzled by this..

interactive_conditional_samples.py crashes if there is more than one context token

**Update** The problem occurs with tf1.12/1.15 or tf2.0, but disappear with tf2.3.0 ------- I also meet this problem. After hours of debuging, I find it seems like a bug of...