'Can we add another model in pretrained object detection?
pipeline_config.model.ssd.num_classes = 2 pipeline_config.train_config.batch_size = 2 pipeline_config.train_config.fine_tune_checkpoint = PRETRAINED_MODEL_PATH+'/ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8/checkpoint/ckpt-0' pipeline_config.train_config.fine_tune_checkpoint_type = "detection" pipeline_config.train_input_reader.label_map_path= ANNOTATION_PATH + '/label_map.pbtxt' pipeline_config.train_input_reader.tf_record_input_reader.input_path[:] = [ANNOTATION_PATH + '/train.record'] pipeline_config.eval_input_reader[0].label_map_path = ANNOTATION_PATH + '/label_map.pbtxt' pipeline_config.eval_input_reader[0].tf_record_input_reader.input_path[:] = [ANNOTATION_PATH + '/test.record']
This is the pipeline and I want to add VGG and inception model in this pipeline.
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|