Unless MXNet team fixed this, I would suggest "hacking" the issue by generating the synthetic dataset with the use of both "positive" and "negative" samples in the following way. Keep the annotated images as they are, crop some boxes out of them and embed crops into the negative images, say, one crop per negative image to some random position. Everything outside the crop should be considered as the background, that you probably want to achieve.
--- [Visit Topic](https://discuss.mxnet.apache.org/t/how-to-use-an-image-without-targets-negative-image-as-a-train-image-to-train-a-detection-net/3978/4) or reply to this email to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.mxnet.apache.org/email/unsubscribe/31c5640e2eb2018f2ed7be06ba9b4c7aa70f88d08791d41736ad028beee85281).
