Vidit

Results 10 issues of Vidit

in nextImg(self, b) 105 self.actualG = img 106 --> 107 self.nextPos() 108 109 # Printing index for recovery in nextPos(self) 67 gaps.append(int(gapBlockFirst)) 68 else: ---> 69 gapPositionSum += (len(pred) -...

bug

Hi, great work the results look really good. I had few questions regarding training 1. How long did you train the BSRNet? 2. Did you apply the proposed data degradation...

Has anybody trained and evaluated DeepLabv3+ on fb16? Thanks

I am getting an error while running the command "cd auto_yolo/auto_yolo/tf_ops/resampler_edge && make" Error msg: fatal error: tensorflow/core/framework/register_types.h: No such file or directory I am using tensorflow 1.13.1, tensorflow-probability 0.6.0,...

Hi, is there a paper associated with inswapper feature? Thanks

Thanks for the interesting work. I am curious how well does the model scale with the number of points. From the paper I see, that the model can predict ~16k...

Hi, thanks for your work. I had few questions 1. While training did you follow the two-stage process of first training a BSRNet and then training BSRGAN? 2. If yes,...

Thanks for the work. May I know if there is an explanation for the condition on the value of gamma in this [line](https://github.com/Shuai-Xie/DEAL/blob/06ff3ba29196e276376a9cf8d868d54fd2db2680/model/attention.py#L29) if self.gamma < -0.01: out = x...

Running the script with python runner.py is stuck and no output is given. I checked and the script is stuck at `from paint_with_words import paint_with_words`

Thanks a lot for your great work! May I know what is the inference speed for generating grounded images?