zhishao
zhishao
毕竟不是所有模型都是像您代码里提供的nin一样这么简单的网络结构
when I run conver_weight and use the pretrained ckpt to evaluate, raise the error below : tensorflow.python.framework.errors_impl.NotFoundError: Key conv52/batch_normalization/beta/ExponentialMovingAverage not found in checkpoint [[node save/RestoreV2 (defined at /Project/tensorflow-yolov3-master/evaluate.py:50) ]]
i want to get the position of each head on heatmap , is there some way to get the val ?
In network.py you using maxpooling in branches, not avgpooling in the paper, why ?
input a image 1920*1080 , cost 0.11~0.14s , on 2070S .
我看到安全帽识别中使用的数据集基本只有头,那么分类的前一阶段需要使用一个人头检测模型吗?还是说人体检测模型也可以?请问paddle有人头检测相关预训练模型吗?
Network: DBnet Env: torch1.9.1 Training with DDP mode on four GPUs.  Code got error and break in here : 
flow, mask, merged = self.flownet(imgs, scale_list) flow must be the flow between two images. it's shape (bs, 4, H, W) , how to visualize it ? like this:  and...
 I Try match LeakyRelu_LeakyRelu_171:out0 I Match r_leakrelu [['LeakyRelu_LeakyRelu_171']] [['LeakyRelu']] to [['leakyrelu']] I Try match LeakyRelu_LeakyRelu_153:out0 I Match r_leakrelu [['LeakyRelu_LeakyRelu_153']] [['LeakyRelu']] to [['leakyrelu']] I Try match Conv_Conv_161:out0 I Match r_conv...