deep-high-resolution-net.pytorch

deep-high-resolution-net.pytorch copied to clipboard

def calc_dists(preds, target, normalize): preds = preds.astype(np.float32) target = target.astype(np.float32) dists = np.zeros((preds.shape[1], preds.shape[0])) for n in range(preds.shape[0]): for c in range(preds.shape[1]): if target[n, c, 0] > 1 and target[n,...

ShihuaiXu

wangm-word

about data

9

Can this code use other data?For example, medical image, please give some specific Suggestions?thank you.

mrzhangzizhen123

Hello, all. Is there any tool to convert torch's HRnet model to tf-lite model?

APeiZou

hello, all有开发将torch的HRnet模型转换为tf-lite模型的工具吗？

APeiZou

Hello. I modified main() in demo/inference.py. [Description] While loop in main() does not terminate after the last frame of the video. I modified if condition so that while loop terminates...

kttaroha

训练的过程Accuracy都显示为0

11

使用mpii数据集训练过程中，所有的Accuracy都为0，包括各个关键点的精度都是为0，想请教下是否有遇到过同样问题

tongjiangwei

Relation between the metric Mean for MPII Val and [email protected] for MPII test

2

Thank you for releasing the code. The README of this repo lists out the validation accuracies of the MPII dataset in terms of **Mean**. On the other hand, the table...

abhi1kumar

Epoch: [209][0/696] Time 39.140s (39.140s) Speed 0.8 samples/s Data 29.137s (29.137s) Loss 0.00019 (0.00019) Accuracy 0.994 (0.994) Epoch: [209][100/696] Time 0.867s (1.182s) Speed 36.9 samples/s Data 0.000s (0.365s) Loss 0.00018...

YuQi9797

how to get 'scale' in mpii dataset?

2

The authors provide json files for MPII dataset (train.json, trainval.json..). I want to create json files for my custom dataset to use the code for MPII dataset. but I do...

tmtmaj