object-detection

Enhancement

A discussion in #614 revealed a good place for improvement - we should ensure that input image is continuous upon start of the augmentation pipeline. This could be implemented by adding image = np.ascontiguousarray(image) to image and mask targets.

A proposed place to add this call - somewhere at the beginning of A.Compose.__call__.

我发现很多人在使用voc格式的数据集时，和我遇到了同样的问题，训练时AP一直为0，
今早，仔细检查后，我也找到了真正的原因，主要是数据加载的地方出现了问题，还是我们自己太不仔细了

解决流程思路： 解决YOLOX训练时AP为0

Hi,
I need to download the something-to-something and jester datasets. But the 20bn website "https://20bn.com" are not available for weeks, the error message is "503 Service Temporarily Unavailable".

I have already downloaded the video data of something-to-something v2, and I need the label dataset. For the Jester, I need both video and label data. Can someone share me the

Add documentation (initially just for the TabularPredictor) explaining what feature engineering AutoGluon does for the user by default:

• what is the universe of types each column can be
• how do we infer types per column
• for each type, what further feature engineering is done (e.g. ngrams and the date parsing I just submitted)
• what are the parameters used for the heuristics
• how does