lyuweiwang

> I managed to do it by > > 1. pip install tensorflowjs==0.8.6 > 2. tensorflowjs_converter --input_format=tf_saved_model --output_json=true --output_node_names='Postprocessor/ExpandDims_1,Postprocessor/Slice' --saved_model_tages=serve graph/saved_model web_model > 3. 0 is reserved for 'unknow' class...

I have tried this, the author's method is better. Although I thought you are right.

> I believe you did not generate the segmentation results. Before tracking, please generate the segmentation first. As we can see in 'datasets.KittiMOTSDataset.MOTSTrackCarsValOffset', at Line 198, segmentation results should be...

> I believe you did not generate the segmentation results. Before tracking, please generate the segmentation first. As we can see in 'datasets.KittiMOTSDataset.MOTSTrackCarsValOffset', at Line 198, segmentation results should be...

@RandomFool123 However, I only use one GPU.

Finally, I realized that "./pointTrack_weights/PointTrack.pthCar" should be copied to "./car_finetune_tracking/checkpoint.pth" before I run "test_tracking.py". So, the problem is caused because the model has no parameters.

@RandomFool123 My result is similar to yours. Maybe we should visualize the result of 0013.

> I modified this bug. > Because my GCC let me implement all the virtual functions of the parent class. Hi, I have the same problem. Could you please tell...

maybe a simple restart will solve your problem

I tried all NAS-FPN config files and only 640 worked. I use both COCO dataset and my dataset. My hardware and software is listed bellow: GPU: 4 * P40 CUDA...