I am using Tensorflow's object detection api to train ssd model. I am using for that Tensorflow 1.15 in google colab and google drive for storage. As the training went the oldest checkpoints gets deleted but my problem is that google drive has deleted .data file of the latest checkpoint and I only have .meta and .index files. I do have though older checkpoints with the completed .data, .meta and .index files. I tried changing the fine_tune_checkpoint to "/content/drive/MyDrive/dataset/models/research/object_detection/training/model_16838.ckpt" where 16838 is the checkpoint with the three files but it didn't work. Is there any other solution to restart training from that checkpoint and not the final checkpoint or do I have to restart training?