Zhedong Zheng
Zhedong Zheng
OK. You may need to modify the `demo.py` a little bit, especially, for showing images, and only use `test.py` to extract the feature.
First of all, could you check the features? Are they wrong (for example, all zeros)? Second, you need to check the feature order with the corresponding image order? Do you...
`If we want to test on our own images, we need to change test.py and demo.py correct?` Yes. `In test.py, could we just refer to our dataset on line 248...
你好, 没有color jitter。 没有reranking。用了reranking，会更高一些。
Hi @NanWang294 sorry for the late response. It looks like your model can successfully extract feature. Could you check the numpy version and update numpy? If this not works, could...
@gubei528 Could you provide more details? The training seems not good? -> check whether the data folder arrangement is right. The training seems good ? -> check whether successfully read...
Hi @gubei528 You may try to set different camera name for every image first. If you want to find cross-camera tracking, you need to mute the image taken from the...
Hi @Wendy-J-412 You need to specify the dataset path. It seems there is no '../Market/pytorch/train" found
Hi @wangzhiyuanking While you use the `model.classifier.classifier = nn.Sequential()`, it removes the final linear classifier. Therefore, the model will output 512-dim feature. If you trained the model on Market (751...
The dataset path may be wrong. You need to check the path.