squeezeDet

squeezeDet copied to clipboard

How to do hard negative mining

1

Hi, I wonder how it would be possible to run hard negative mining as in SSD paper? " Instead of using all the negative examples, we sort them using the...

cygerts

The memory of the runtime model?

4

hi, when I retrain the squeezeDet net on kitti dataset. I set the batch_size to 1 or 10, and I found that the usage of the GPU are just same...

chenfsjz

Will random initialization parameters have no precision?

1

When no pre-training model is used, the random initialization parameter is used to train the squeezeDet, and another GPU is verified at the same time, but the training does not...

JUSTDODoDo

Hi, This PR request is to add a config setting for the flip probability.

hoonkai

Hello, I'm trying to run this model on a RPI using tensorflow 1.9.0. The execution is good but gives an bus error when entering the session.run function. Issue is similar...

cedricve

Hi, is it possible to include online hard example mining in squeezedet?

pribadihcr

Training it from scratch

1

Has anyone tried to train SqueezeDet from scratch? If yes how long does it take to converge? I have some multimodal features I am using hence cannot use the ImageNet...

aditya1709

Why is the IoU layer associated with a batch size? Is there a way to make it independent of the batch size? It prevents us from analyzing the learned model...

aditya1709

Hi all, first of all thanks for sharing this much content on your model. I want to do inference with squeezeDet inside a C++ project (roscpp). For this I need...

AlexejD

Is there some way to calculate anchor boxes for my own dataset?

4

I try to train this model on my own dataset. I created the structure of folder similar to kitti. I have the same size of image as KITTI. But my...

mrlzla