dexter2406

> @CaptainEven , I wanna train the network to track person and car at the same time and I used gen_labels_mot16_car.py to generate the car label, should I need to...

I wait for about 20min and notice that there are following files are generated: ``` graph.pbtxt events.out.tfevents.1606226671.DESKTOP-AVNMGK4 ``` even though there's still no progress shown - maybe because your code...

Thanks for the reply. I'm using (mainly): ``` python=3.6.12 tensorflow==1.2.0 scipy==1.1.0 numpy==1.19.4 matplotlib==3.3.3 opencv-python==4.4.0 pillow==8.0.1 ``` I know it's stated that this code is only tested in `python==2.7` and `tf==1.1`,...

> Hi, > Is it possible to replace the feature extractor ? Because, better person re-identification models can improve the accuracy (in a person reid specific scenario). [For example](https://github.com/KaiyangZhou/deep-person-reid/blob/master/docs/MODEL_ZOO.md) Have...

> Hi, First of all very nice implementation. In the deep sort paper, they mention that they trained encoder on mars dataset, which is essentially people discriminator, are you using...

Found a solution. Works for me:) @OrkhanHI @Eurus-Holmes @Feynman1999 ``` def bilinear_sampler(img, coords): H = tf.shape(img)[1] W = tf.shape(img)[2] max_y = tf.cast(H - 1, 'int32') max_x = tf.cast(W - 1,...

> No practise, but I think it better to train 2 models for pedstrain and vehicles separately, because these 2 classes is unsimilar at all. > > You can train...