montensorrt

test score_label Inconsistent when test images Inconsistent in Same image

2

First of all, thank you for presenting your work as open source. When I tested model, I found test score_label changed when test same one image,When the batch_size is not...

First of all, I would like to thank the author for his contribution to open source. I have a question. Can the algorithm be directly transferred to onnx, or trt?

Partial realization is missing（Bottleneck_last，SPP_super）

1

Why i not found in ddrnet_39.py about Bottleneck_last，SPP_super, So now only use Bottleneck and PPAM replace?

训练时有足够内存，依然得到out of memory问题

1

您好，首先感谢您分享了您的稠密目标定位算法，最近我对您得算法进行实现得时候出现了问题，如下： 首先我是在windows10平台上运行得训练过程，前面数据和模型处理好了以后，开始训练出现问题如下： 不论运行那个模型，当模型开始正向执行，总是在第一个conv出爆出问题： VGG16_FPN.py: def forward(self, x): f = [] x = self.layer1(x) seg_hrnet.py: def forward(self, x): residual = x out = self.conv1(x) 总是爆出内存不足问题， RuntimeError: CUDA out of memory. Tried...

First of all, I would like to thank the author for his contribution to open source. I have a question. Can the algorithm be directly transferred to onnx, or trt?

where find infer script file?

3

Dear Anuj, I am very impressed from your work and I would like to try and replicate your training to understand how your method works. I have completed the training...