Saif Hassan

@funmv @yingning @kstys @shinjayne I got same issue? Please guide Thanks in Advance.

Hello @Tian14267 I got same error Did you solve this issue? @shinjayne Please help Thanks in advance

> Hi! > I want to calculate the speed of the detected objects, but I don't know how to get the past frames from the objects with their own IDs,...

did anyone find answer? @mengxingxinqing @jinfagang

In coco_evaluation, error occurs in decode function: `Bytes-Like object is required not str`. Python 3 does not support.

To evaluate the model on validation set, run python train.py --type val.

I got same error and I resolved adding `predictor.setModelTypeAsResNet()` following line after `predictor = CustomImagePrediction()` Use following code: `predictor = CustomImagePrediction()` `predictor.setModelTypeAsResNet()` `predictor.setModelPath(model_path="action_net_ex-060_acc-0.745313.h5")` `predictor.setJsonPath(model_json="model_class.json")` `predictor.loadModel(num_objects=16)`