Object_Detection Not working in tensorflow

Question

I am new to tensor flow and I trained face mask model and tried it on web cam but it shows something like this.

Can anyone help me with this, I used around 100+ images and 2-3 hrs for training, where i am doing mistake can anyone help me out.

Last 2 cmd used

python train.py --train_dir=training/ --pipeline_config_path=training/ssd_mobilenet_v1_pets.config --logtostderr


python export_inference_graph.py --input_type image_tensor --pipeline_config_path training/ssd_mobilenet_v1_pets.config --trained_checkpoint_prefix training/model.ckpt-0 --output_directory new_graph

Answer 1

您使用的training/model.ckpt-0是模型开始训练后的第一个检查点，您需要使用保存在training文件夹中的最后一个检查点。