TensorFlow2.0-Examples
TensorFlow2.0-Examples copied to clipboard
YunYang1994
🙄 Difficult algorithm, Simple code.
Hello, ResNet' network is different from the paper. https://arxiv.org/abs/1512.03385
I am a newbie to YOLOv3. Recently, I am working on training my dataset by YOLOv3 and want to run on my TX2. So, It is my fortune to follow...
hi your network is very good and I want to thank you for this network i want to implement angle to bounding box and change yolo formats to (x,y,w,h,a) can...
env: tensorflow-gpu== 2.0.0 opencv-python== 4.1.1.26 numpy==1.16.4 Pillow==6.1.0 scipy==1.2.1 wget==3.2 seaborn==0.9.0 easydict==1.9 cv2 读取视频是没有问题的，已测试 但是在tensorflow2.0 videodemo中，读取视频提示 raise ValueError("No image!") 请核查一下问题所在
首先，非常感谢前辈分享的工作。 我是个大三的新手，使用了wget的那套权重，image_demo.py的代码没动，用了一块GPU，yolov3测试样例图片大概花了十多秒吧，感觉没法做到实时检测。 1.GPU不够多吗？ 2.改变一下image_demo.py，用GPU来做预测？ 3.自己训练一套类别少的权重来做预测？（我任务是安全帽检测）
Hi,大佬，我看见你resnet系列中res34和res50最后都return ResNet(Bottleneck, [3,4,6,3])，res50不是应该return ResNet(Bottleneck, [3,4,14,3])吗？
我不知道每张图片的坐标轴是什么样子的？x轴与y轴到底是怎么分布的？具体来说，您将图片放在了坐标轴的那个象限去描述真实框的位置呢？
运行时显示：WARNING:tensorflow:Gradients does not exist for variables ['disp_net/conv2d_3/kernel:0', 'disp_net/conv2d_3/bias:0', 'disp_net/conv2d_4/kernel:0', 'disp_net/conv2d_4/bias:0', 'disp_net/conv2d_5/kernel:0', 'disp_net/conv2d_5/bias:0'] when minimizing the loss.
thank you for your share, I ask if the model saved by tensorflow2.0 can be used on 1.x?
