-
When tried to run model-for-market1501.py after the h5 file was made, this error showed up. Keras and other libs are installed
Using TensorFlow backend.
default dim order is: tf
please input yo…
-
Hellow,
I used GX1080*1 8G and ran demo.sh. Got this problem:
usage: main.py [-h] [--nThread NTHREAD] [--cpu] [--nGPU NGPU]
[--datadir DATADIR] [--data_train DATA_TRAIN]
…
-
Hi, where can we find the datasets with -pose-map.
Is there a way to generate this, or do you offer the dataset?
-
First of all, thank you for this project, its very cool.
I see that on the Market 1501 dataset, the number of classes is 751. If we apply a model trained on the Market 1501 dataset to a domain with…
-
-
Thank you for your contribution to the computer community!
As shown in the question. I found osnetx1 in the configs folder_ In the configuration file of 0, the rerank was changed to Ture, but an erro…
-
Hi,
Thank you for your work.
When I tried to train my model according to the parameters you provided in [configs.yaml](https://github.com/NVlabs/DG-Net/blob/master/configs/latest.yaml), I found th…
-
Hello @Ha0Tang ,
I tried to reproduce the results of the Keypoint guided person Image generation using your C2GAN code on Market1501 data.
I downloaded the data from https://www.kaggle.com/pengcw1…
-
-
我是刚接触行人reid问题，我这边有一些问题想要咨询一下。因为reid模型实际是一个特征提取模型，那这个模型在我理解来应该是有不错的泛化性的，比如现在使用market1501数据集和DG-Market数据集训练了一个特征提取模型，然后我用test.py加载这个模型去跑msmt17的验证，我发现结果的map几乎等于0。
我想知道这个的原因是什么，是reid模型不具有泛化性呢，还是验证的流程会有一些…