tensorflow-yolov3 icon indicating copy to clipboard operation
tensorflow-yolov3 copied to clipboard

🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"

Results 114 tensorflow-yolov3 issues
Sort by recently updated
recently updated
newest added

Can I transfer the CKPT file back to weights?Where is the cfg file

For I am a beginner of object detection,I don't know how to transfer coco dataset to voc format. 怎么把coco数据集转化成voc格式的呢?

help wanted

训练自己的数据集,训练集为5663张图片,测试集为1416张图片。bath_size=3。 ![2019-11-26 09-46-27屏幕截图](https://user-images.githubusercontent.com/49632230/69592684-af607e80-1031-11ea-9b67-2f70191ae75d.png) ![2019-11-26 09-45-01屏幕截图](https://user-images.githubusercontent.com/49632230/69592691-b5565f80-1031-11ea-8fcf-bb7101c421fc.png) 请问为什么test_loss一直下不去? 下面是我的tensorboard ![2019-11-26 09-50-34屏幕截图](https://user-images.githubusercontent.com/49632230/69593437-21d25e00-1034-11ea-848b-341154b9897d.png) ![2019-11-26 09-50-58屏幕截图](https://user-images.githubusercontent.com/49632230/69592887-5b09ce80-1032-11ea-9b9f-ee5edcd42f32.png) @YunYang1994 仓主以及各位大佬,能否指点一下,谢谢

如果不加载预训练模型,从头开始训练,模型收敛效果好像差很多,且存在严重过拟合,有没有好的办法解决,求大神指点!!!

Adds file to directory, instead of creating file prefix.

我在你的文档里没有找到extract_coco.py convert_tfrecord.py等文件,是已经删除了吗?

请教大家一个问题,我现在pb文件生成了,图片和视频流的检测都通过了,但是我想通过调用笔记本的摄像头来进行实时监测,请问大佬们有好的脚本吗?或者从那个视频流video_demo.py怎么修改呢?

查看了作者的代码,在stride>1的时候,是先对input进行padding,然后在tf.nn.conv2d中使用padding='VALID'的方式进行卷积。 请问为什么不直接使用tf.nn.conv2d中padding='SAME'的padding方式进行呢?似乎两种方式的效果差别不会很大,仅仅是填充的位置稍微改变。 是因为darknet作者用的前一种方式吗?

`python crop_xmin = max(0, int(max_bbox[0] - random.uniform(0, max_l_trans))) crop_ymin = max(0, int(max_bbox[1] - random.uniform(0, max_u_trans))) crop_xmax = max(w, int(max_bbox[2] + random.uniform(0, max_r_trans))) crop_ymax = max(h, int(max_bbox[3] + random.uniform(0, max_d_trans))) `...

这是Box-Clustering.ipynb聚类后得到的聚类中心值 [[0.0627878 0.09495271] [0.11484864 0.23439993] [0.86874759 0.87105803] [0.79309616 0.46284657] [0.29627503 0.71413459] [0.41545661 0.44281255] [0.30121263 0.2348154 ] [0.1761251 0.47797277] [0.52819415 0.79192799]] 这是baseline_chors.txt的值 1.25,1.625, 2.0,3.75, 4.125,2.875, 1.875,3.8125, 3.875,2.8125, 3.6875,7.4375, 3.625,2.8125, 4.875,6.1875, 11.65625,10.1875...

help wanted