zzdang

mobilenetv3 转onnx遇到个错

6

请问转onnx模型时遇到: Type Error: Type parameter (T) bound to different types (tensor(float) and tensor(int64) in node (Add_4) 大神们遇到了吗,咋解决呀

I try to add rcnn mask in RCNN model , I know the output_masks loss can be get by : **keras_rcnn.layers.MaskRCNN()[target_proposals, output_deltas, target_masks, output_masks]** but I don't know how to...

why I got the negative loss ?

4

I got the nagetive loss use the unet ,I don't know what's the wrong in my code. I use the gt (maks) of 2 class,background and foregroud,with the mask pixels...

Could you list the differents between you codes and official faster rcnn?

2

Hi ,your project is cool. I plan to write a faster rcnn project with gluon. I want to use your code for reference,could you list the differents between you codes...

an issues about your ocr data iteration

5

Hi,your project is cool ,but your OCR_LSTM_CTC's data iteration is very slow? Could you update it? Thank you very much

Could you share the training log of your faster rcnn(vgg16)?

2

Hi ,I'm training gluon-cv's faster rcnn(vgg16 and VOC). But,the 7 epoch mAP is 0.52 ,I think it is lower than I expected. Could you share the training log of your...