ZOUYIyi
ZOUYIyi
> Modified, with gpu_nms supports > I ran it on windows successfully (Python 3.6.6, VS2015 compiler, CUDA 9.0 with CUDNN v7), just modify some code. > Tested both cpu_nms and...
@qhgz2013 really need your help , please....
@qhgz2013 I see. ... I have already done all the things you said , but I really need to run the project in windows, thanks for your advice anyway. I...
应该按照作者的图例放置weights,但是用inference.py去预测，具体可见代码。
yes，I have done that.it works perfectly.thank you. ---Original--- From: "Wslsdx" Date: Tue, Jun 4, 2019 13:55 PM To: "Wslsdx/Deep-Learning-Approach-for-Surface-Defect-Detection"; Cc: "ZOUYIyi";"Author"; Subject: Re: [Wslsdx/Deep-Learning-Approach-for-Surface-Defect-Detection] how to save pbfile (#3) sorry...
主要是确定输入输出节点的名字，然后按照网上的例子先做个简单的网络freeze，就可以了。 ------------------ 原始邮件 ------------------ 发件人: "gulingfengze"; 发送时间: 2019年6月11日(星期二) 上午9:19 收件人: "Wslsdx/Deep-Learning-Approach-for-Surface-Defect-Detection"; 抄送: "邹易";"Mention"; 主题: Re: [Wslsdx/Deep-Learning-Approach-for-Surface-Defect-Detection] howto save pbfile (#3) @ZOUYIyi Can you tell me how to implement model freeze?...
input_name = "Image" output_name = "segment/Sigmoid" ------------------ 原始邮件 ------------------ 发件人: "gulingfengze"; 发送时间: 2019年6月11日(星期二) 下午5:13 收件人: "Wslsdx/Deep-Learning-Approach-for-Surface-Defect-Detection"; 抄送: "邹易"; "Mention"; 主题: Re: [Wslsdx/Deep-Learning-Approach-for-Surface-Defect-Detection] howto save pbfile (#3) @ZOUYIyi What are the...
here is my script for saving pb file: //// def save_PbModel(self): input_name = "Image" output_name = "segment/Sigmoid" output_node_names = [input_name,output_name] print("模型保存为pb格式，输入节点name：{}输出节点name: {}".format(input_name,output_name)) output_graph_def = tf.graph_util.convert_variables_to_constants( self.__session, self.__session.graph_def, output_node_names, ) with...
> What about changing: self.keras_model.metrics_tensors.append(loss) > to: self.keras_model.add_metric(loss, name) > > it is work! 非常感谢 我应该在哪里修改这一句呢？
> All the cameras are triggered at the same time when the laser faces forward. > > When projecting lidar points to the cameras, you need to unwarp the LiDAR...