Nirvan Anjirbag

Results 5 issues of Nirvan Anjirbag

Is it possible to adapt this model for video-based person re-identification? Could we attach an LSTM layer towards the end in order to aggregate the tensors over all the video...

Can you please add pre-trained model weights to this? It will be a lot easier for everyone to test this code with the weights are already provided.

I don't understand how `retrain_yolo.py` expects the training data. How do I feed my images and my annotation files into retrain_yolo ? Should the images and annotation xml files be...

![output1](https://user-images.githubusercontent.com/23417993/51552197-10f61080-1e96-11e9-9966-d7a75e801dd1.png) ![output2](https://user-images.githubusercontent.com/23417993/51552198-10f61080-1e96-11e9-8bb3-73c8a11d64e6.png) ![output3](https://user-images.githubusercontent.com/23417993/51552199-118ea700-1e96-11e9-970d-cf61089068f0.png) ![output4](https://user-images.githubusercontent.com/23417993/51552200-118ea700-1e96-11e9-84e5-a6b51d0614d0.png)

![train](https://user-images.githubusercontent.com/23417993/51500611-a8a32280-1df4-11e9-833a-840960aa4b49.jpg) ![test](https://user-images.githubusercontent.com/23417993/51500628-b658a800-1df4-11e9-94d3-b62f07567712.jpg) ![autoencoder1](https://user-images.githubusercontent.com/23417993/51500741-354de080-1df5-11e9-8a17-965c165b4dad.jpg) ![autoencoder2](https://user-images.githubusercontent.com/23417993/51500746-3979fe00-1df5-11e9-8bf2-ca586f4ecf83.jpg) ![autoencoder3](https://user-images.githubusercontent.com/23417993/51500748-3b43c180-1df5-11e9-99c4-9bf70d118134.jpg) ![out1](https://user-images.githubusercontent.com/23417993/51500750-3ed74880-1df5-11e9-9013-d5b8187dbb2a.jpeg) ![out2](https://user-images.githubusercontent.com/23417993/51500755-426acf80-1df5-11e9-8b02-3ff7afdad287.jpeg) ![out3](https://user-images.githubusercontent.com/23417993/51500758-472f8380-1df5-11e9-8ddf-4ef26b55c305.jpeg) ![out4](https://user-images.githubusercontent.com/23417993/51500763-4ac30a80-1df5-11e9-9943-c576b7a34122.jpeg)