wangxiang1230
commented
2 years ago The training recipe (GPU model, how many query videos per task, how many tasks per batch, how many iterations/tasks/batches in total, optimizer options, learning rate policy, etc.) is not available in the paper, nor is it clear in the code (the options in the YAML are mysterious, some options seem redundant, some hyperparameters are embedded in the code, etc.). It is not possible to reproduce the results from scratch without the recipe. Please, summarize all the hyperparameters, policies, and settings that have a place in the training procedure.
Hi, thanks for your attention to our HyRSM. We train our model on 4 Nvidia V100 GPUs for the default setting. The config settings can be found in our yaml file, query videos: QUERY_PER_CLASS, training task: NUM_TRAIN_TASKS, batch: BATCH_SIZE, test iterations: NUM_TEST_TASKS. For more details, you can refer to our yaml file. To make it easier to understand, I suggest you run through the code. Thanks again.
The training recipe (GPU model, how many query videos per task, how many tasks per batch, how many iterations/tasks/batches in total, optimizer options, learning rate policy, etc.) is not available in the paper, nor is it clear in the code (the options in the YAML are mysterious, some options seem redundant, some hyperparameters are embedded in the code, etc.). It is not possible to reproduce the results from scratch without the recipe. Please, summarize all the hyperparameters, policies, and settings that have a place in the training procedure.