vedanshu

I've both usb and Gige. How to get UTC on GigeVision camera ?

For enabling IEEE1588/PTP support on camera, the link gives code in c++. Can you provide it in python please?

So, after enabling ptp on camera and using ptpd on linux (selecting ntp as master), I can use `time_stamp=res.TimeStamp()` to get the t_trigger ?

@feiyuhuahuo Thanks for the reply. I was also making Yolact minimal (but in TensorFlow). I tried to match the code as closely as possible with the original code, but still,...

@MysticStranger I tried your solution but I'm getting following error: ``` Traceback (most recent call last): File "infer_rt.py", line 58, in image_batch = torch.stack(image_batch, axis = 0).cuda() TypeError: expected Tensor...

@grimoire I changed the input tensor according my input image using the cli as follows: ``` sudo docker run --gpus all -it --rm -v /home/deploy/ved/:/models/ mmdet2trt_docker:v1.0 --fp16 True --max-workspace-gb 11...

I'm trying to use serialized model for the first time. I also tried using pytorch 1.11.0, but it didn't work.

In the Linear class, I can do the following: ``` nn.Linear(in_dim, 32x32) ``` Where, to get that # of classes in the output dims ?

@Alexankharin But this requires using a conv operation, but the paper specifically specifies using a dense linear layer. The only way I can think of doing it is as follows:...

Currently, I'm not providing pre-trained checkpoints. Will add coco pre-trained checkpoints in future.