vedanshu

Can you tell how you run the SMAC for optimizing the hyperparameter? How did you create objective function to be minimized.

DCNv2 support

2

Trying to convert Faster RCNN R-50 DCNv2 to tensorRT, but I'm getting following error: ``` [TensorRT] ERROR: Parameter check failed at: engine.cpp::setBindingDimensions::948, condition: profileMaxDims.d[i] >= dimensions.d[i] [TensorRT] ERROR: Parameter check...

How to set UTC time to the camera

7

Hi, I want to set the TimeStamp of the camera to UTC time. My camera is connected to the computer. How to do this ?

Different implementation of PredictionModule

2

Hi, I was going through your code and found that you've used `len(cfg.aspect_ratios)` as a multiplication factor for [bbox_layer, conf_layer and coef_layer](https://github.com/feiyuhuahuo/Yolact_minimal/blob/d920c0563f54746426a006cd3af83ff3bae293cc/modules/yolact.py#L20): ``` self.bbox_layer = nn.Conv2d(256, len(cfg.aspect_ratios) * 4, kernel_size=3,...

Hi, I really liked your idea of implementing Yolact in tensorflow. I came around your repository around 4 months back. At that time, the repo was having a lot of...

I was wondering if for the detection of mask RCNN do we have to make following changes: > output_names = [BOXES_NAME, CLASSES_NAME, SCORES_NAME, NUM_DETECTIONS_NAME, MASKS_NAME] in the file "Step1_Object_detection_Colab_TensorRT.ipynb" ?...

Unsupported layer type: 'Reshape'

1

I'm using following prototxt file but it's throwing me a warning: ``` name: "VGG_ILSVRC_16_layers" input: "data" input_shape { dim: 1 dim: 3 dim: 224 dim: 224 } input: "im_info" input_shape...

RuntimeError: required keyword attribute 'value' is undefined

12

### 🐛 Describe the bug Hi, While loading loading a `.pt` file, I'm getting following error: ``` Traceback (most recent call last): File "", line 1, in File "/home/sort/miniconda3/envs/openmmlab/lib/python3.8/site-packages/torch/jit/_serialization.py", line...

Semantic segmentation

9

I'm not able to find code for Semantic segmentation. In the paper it's written that: ``` a linear layer is trained to predict class logits from a patch tokens. It...

Non strict checkpoint loading

1

### Description & Motivation Currently, I'm finetuning my model which are based on some very large models (like LLAMA and CLIP). I'm using some light weight adapters for fine tuning....