yushe
yushe
请教大佬: 我的model原本时tensorflow的,通过tf2onnx成功转成了onnx模型,且结果已校验是对的, 转换命令为“python -m tf2onnx.convert --graphdef ./deeplab.pb --output depplab.onnx --fold_const --opset 11 --inputs ImageTensor:0 --outputs SemanticPredictions:0" 通过tengine的convert_tool转onnx的命令为: "./convert_tool -f onnx -m ./deeplab.onnx -o deeplab.tmfile" 报错信息如下: ----- Tengine Convert Tool ----...
**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] **Describe the solution you'd...
您好,感谢大佬优秀的代码分享,我想请教一下这个代码中的人脸识别(特征提取)模型的输入,是直接把人脸检测得到的box,crop成图像嘛,对于检测得到的box有没有什么移动/缩放的操作,另外是否需要根据landmark的位置做人脸姿态矫正,然后再输入特征提取网络进行特征提取?
感谢楼主这么优秀的工具,请问是否有计划支持多目标跟踪标注?是否计划添加deepsort跟踪算法
Hi, can you describe the mothods how you get your 60k train data from https://github.com/lizhengwei1992/Fast_Portrait_Segmentation/tree/master/dataset#dataset. Thank you very much for your work .
Hi, can you tell me your ideal about how to calculate the confidence map of optical flow,?
在cnnModel.py中: 问题1: line 143: keep_prop=tf.Variable(initial_value=0.5,name="keep_prop") line 144: self.fc_result=create_CNN(input_data=self.data_tensor,num_classes=gConfig['num_dataset_classes'],keep_prop=gConfig['keeps'] keep_prop变量并没有被用到,且在144行,参数keep_prop=gConfig['keeps']不能这样写,因为后面要根据forward_only的值,传不同的参数给keep_prop变量。 我认为应该讲keep_prop定义为place_holder,以下为参考: self.keep_prop=tf.placeholder(tf.float32,name="keep_prop") self.fc_result=create_CNN(input_data=self.data_tensor,num_classes=gConfig['num_dataset_classes'],keep_prop=self.keep_prop)、 -------------------------------------- 问题2: line 200: accuracy = correct.size/(self.percent*gConfig['dataset_size']/100) 这里求accuracy的分母,要改为shuffled_data.shape[0] ------------------------------------- 问题3: cnnModel: step函数中,if forward_only:这一部分应该也需要更改或者重写,请核实
Thank you for your great work,sir! I have a question, thant when I use this code to parse SSD caffe model, some error happens: ............................. init plugin proto: ./models/vehDetector/vehDetector.prototxt caffemodel:...
Hi, can you tell me your ideal about how to calculate the confidence map of optical flow,?
I think your instruction about how to run the code may be lack one important step,which may be plugged after "train models", because after trained models, when I go into...