liudadan

Can the model converted from torch2trt handle two images with unequal dimensions.

2

Can the model converted from torch2trt handle two images with unequal dimensions.

Can the code generate 19 dimension heatmaps?

3

Can the code generate 19 dimension heatmaps? What parts need to be modified?I trained with the coco dataset.I only modified the dataset part of yaml. DATASET: DATASET: coco_kpt DATASET_TEST: coco...

Where is the definition of eval? [DEKR](https://github.com/HRNet/DEKR)/[lib](https://github.com/HRNet/DEKR/tree/main/lib)/[dataset](https://github.com/HRNet/DEKR/tree/main/lib/dataset)/build.py / dataset = eval(cfg.DATASET.DATASET)( cfg, cfg.DATASET.TRAIN, heatmap_generator, offset_generator, transforms )

What is cfg? Where was it created?from config import cfg

I used the program to read the coco dataset and found that the code did not call the code of the cocoKeypoints class. But in fact, the program does call...

Why can reading obj ['segmentation '] generate rle and rles? Rles is iterative, and rle is not iterative. def get_mask(self, anno, img_info): m = np.zeros((img_info['height'], img_info['width'])) for obj in anno:...

Why do you re create the mask without using the label of the heatmap and the label of the paf as the mask

I want to train Litepose-S through Normal Training,which have pre-training model?