ssds.pytorch

ssds.pytorch copied to clipboard

when I run this command: python -m ssds.utils.visualize -cfg experiments/cfgs/tests/test.yml, it occurred an error like this: Traceback (most recent call last): File "/home/zhang/anaconda3/envs/ssds/lib/python3.7/runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File...

Deerzh

The dataloder seems to have some problems. When I run the script, many images turn to all zero after the data loader.

BentengMa

yml problem

3

Hello, I would like to replace FEATURE_LAYER yml, how to determine the FEATURE_LAYER profile, such as yolov3 and mobilenetv3

QZ-cmd

Loss is not decreasing

19

I have trained ssd with mobilenetv2 on VOC but after almost 500 epochs, the loss is still like this: ``` 517/518 in 0.154s [##########] | loc_loss: 1.4773 cls_loss: 2.3165 ==>Train:...

lucasjinreal

This is the roadmap for ssds.pytorch v1.5. The development for ssds.pytorch v1.5 is fully reconstruct and almost done. The main features are listed at here: ### [Documentations](https://foreveryounggithub.github.io/ssds.doc/): - [x] install;...

foreverYoungGitHub

How to set the parameters of the pre-training model

5

i want to use pre-training model > TRAINABLE_SCOPE: 'base,norm,extras,loc,conf' RESUME_SCOPE: 'base,norm,extras,loc,conf' TRAINABLE_SCOPE and RESUME_SCOPE , How should I modify or Which parameters should I remove? thanks

Damon2019

All the ssds method are based on 300, can it changed into 500 or 512?

12

Can the input image size be changed into another?

lucasjinreal

Training result is too sparse

5

@ShuangXieIrene Hi, I use this proj to train my own dataset(a small and simple scene). I found that the trainning result is so sparse, it means lots channels of weights...

xingyueye

(1). My pytorch version is 1.4.0, and my data class is 1, when I train this model ,I encountered this problem: RuntimeError: Error(s) in loading state_dict for FSSDLite: size mismatch...

WesterL

Follow this https://github.com/chuanqi305/MobileNet-SSD，mobilenet-ssd only get mAP 68% without MS-COCO pretraining。Even if the structure changes from ssd to ssdlite,why can it improve so much? I trained mobilenet-ssdlite only on VOC with...

luoduo21