YOLOv5-tf
YOLOv5-tf copied to clipboard
boudingbox no detect
I trained the network in 100 times and the model was generated perfectly, but during the tests the boundign boxes were not detected
sorry for the late answer, can you share your dataset sample including image and label
Hello,I also have this problem,my annotations are just like this。
<folder>head_detect_lab_data</folder>
<filename>1543.jpg</filename>
<path>F:\image_data\head_detect_lab_data\1543.jpg</path>
<source>
<database>Unknown</database>
</source>
<size>
<width>512</width>
<height>512</height>
<depth>3</depth>
</size>
<segmented>0</segmented>
<object>
<name>person</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>335</xmin>
<ymin>309</ymin>
<xmax>357</xmax>
<ymax>327</ymax>
</bndbox>
</object>
############################################################# the train.txt is just like this 0 1 10 100 11 12 13 14 15 16 17 18 19 2 20 22 23 24 26 27
I might suggest original YOLOv5 for getting a better result