Xingyi Yang

I implement a TensorFlow.keras version for ICML2019 Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization. Hope this would help https://github.com/Adamdad/Samesame.git

I implement a TensorFlow.keras version for ICML2019 paper Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization. Hope this would help https://github.com/Adamdad/Samesame.git

| Model name | InputSize | TrainSet | TestSet | mAP | | ----- | ------ | ------ | ------ | ----- | | [YOLOv3-Mobilenet](https://github.com/Adamdad/keras-YOLOv3-mobilenet) | 320x320 | VOC07+12 |...

Keras yolov3 mobilenet

1

I've trained yolov3 on mobilenet backend and get a good MAP(about 90M and 2 times faster than keras yolov3)。I upload my code for mobilenet-yolov3 on https://github.com/Adamdad/keras-YOLOv3-mobilenet.git use it as you...

| Model name | InputSize | TrainSet | TestSet | mAP | | ----- | ------ | ------ | ------ | ----- | | [YOLOv3-Mobilenet](https://github.com/Adamdad/keras-YOLOv3-mobilenet) | 320x320 | VOC07+12 |...

I've trained yolov3 on mobilenet backend and get a good MAP(about 90M and 2 times faster than keras yolov3)。I upload my code for mobilenet-yolov3 on https://github.com/Adamdad/keras-YOLOv3-mobilenet.git use it as you...

keras-mobilenet-yolov3

1

I've trained yolov3 on mobilenet backend and get a good MAP(about 90M and 2 times faster than keras yolov3).I upload my code for mobilenet-yolov3 on https://github.com/Adamdad/keras-YOLOv3-mobilenet.git use it as you...

Dear maintainers of latent-diffusion, a range of people and me found that, when training the latent diffusion model with `multiple gpu`, the generated image quality becomes disastrously bad. But when...

Proper Learning Rate decay for training the LDM

9

In the current repo, I see no learning rate decay in the config files. In the main paper, they are also not mentioned at all. However, when I train your...