KeyError: "The name 'image_tensor:0' refers to a Tensor which does not exist. The operation, 'image_tensor', does not exist in the graph." about auto_annotate HOT 4 CLOSED

Hello @prism5426, I just finished the new version of auto annotation for TF 2.x. To try to use it, please, run the detection_img_tf2.py file inside scripts. To run this file you need this command:

python3 scripts/detection_img_tf2.py --saved_model /path-saved-model --labelmap /path-label-map.pbtxt --imgs /path-of-the-imgs

Please, let me know if everything worked as expected!

from auto_annotate.

Hello @AlvaroCavalcante I tried to run this command "python3 scripts/detection_img_tf2.py --saved_model /path-saved-model --labelmap /path-label-map.pbtxt --imgs /path-of-the-imgs" but I found this issue

from auto_annotate.

Hello @shabbir9916, as mentioned in the auto annotation tutorial here, you need to replace the content of the visualization_utils.py to add the lines of code needed to the project work correctly. This file is inside the TF garden repo, in models/research/object_detection/utils. An easy way to do this is to copy all the content in the "visualization_utils_v2.py" in this repo and paste it into the visualization_utils.py of the TF repo. Let me know if you have any doubt, I recommend checking the mentioned tutorial to get a cleaner idea.

from auto_annotate.

@shabbir9916 I'll close this issue due to inactivity. Please, feel free to reopen if you have some news!

from auto_annotate.