need info to build config and samples json
djangid opened this issue · comments
can anyone explain "train_env": "TID2013",
"s3_bucket": "ds-hotel-image-assessment",
"docker_image": "idealo/nima-gpu",
"base_model_name": "MobileNet",
"existing_weights": null,
"n_classes": 10,
"batch_size": 64,
"epochs_train_dense": 25,
"learning_rate_dense": 0.001,
"decay_dense": 0,
"epochs_train_all": 25,
"learning_rate_all": 0.0000003,
"decay_all": 0,
"dropout_rate": 0.75,
"multiprocessing_data_load": true,
"num_workers_data_load": 8,
"img_format": "bmp"
This config file lists all the parameters needed to train the technical model on AWS. Let us know if you have more specific questions on any of the parameters
could you please let me know how to know what field is what and more information so i can understand how to make my own filed i nfromtion
Hi, most field names are quite descriptive and should be clear if you deal with neural nets. If you have specific questions to a field please reopen this issue, but I am not going to run through all of them, closing this for now