PhenomenalOnee

Hello, great explanation there. Can you please provide how to modify the training code ( data fetech and multiloss function ) to pass negative images without/with bounding boxes

AutoCast for mixed precision/fp16 fails?

1

I have tried to train the model using torch.cuda.amp.autocast() but the training doesn't seems to speeds up or memory usage remains same as with fp32 training. also model size remain...

How to make inference fast (by adding caching of key / values)

1

How can we implement the below caching technique in the code? That would be awesome. What I have tried to speed up the inference in my custom implementations for autoregressive...

Can you please provide your trained Discriminator model

Keras Implementaion

1

Great Work!! Can you provide this work in keras?

Negative Samples

13

As i am testing the model, i encounter it creates a lot of false positive detection on hands and necks with high confidence, can you tell me how to add...

Accuracy Issue

1

Really Nice Tutorial.. I have trained using code from https://github.com/siriusdemon/Build-Your-Own-Face-Model/tree/master/detection centerface detection and facing Accuracy Issue. Some Modifications I have done according to your repo as follows HeatMap generation using...

Demo

1

Really Nice Work.. Can you please merge your model with a person detection model to build a people tracking software like DeepSort (https://github.com/Qidian213/deep_sort_yolov3) Thank You

Results Problem?

3

Hello, Really amazing work. While doing inference, i faced the results are not as good as shown. I tested using the pre trained models: 1) faster_rcnn_RoITrans_r50_fpn_1x_dota  2) faster_rcnn_RoITrans_r50_fpn_1x_dota1_5 ...