Detect queries in test items
1 2 3 4 5 6 7 8 9 10 11 12 | qbe_std(
queries_loc,
references_loc,
names_fetcher = fetch_npz_names,
features_fetcher = fetch_npz_item,
search_mf_maker = create_allcomb_df,
post_processor = create_qbestd_df,
nndtw_func = sousrir_1nndtw,
ssdtw_func = sousrir_ssdtw,
progress_bar = TRUE,
use_multisession = TRUE
)
|
queries_loc |
Location of queries (default: an npz file containing a named dictionary of NumPy feature matrices of shape TxF) |
references_loc |
Location of references (default: an npz file containing a named dictionary of NumPy feature matrices of shape TxF) |
names_fetcher |
A function that takes queries_loc/references_loc and returns the items contained in them (default: fetch_npz_names) |
features_fetcher |
A function that takes queries_loc/references_loc and an item name, and returns the features associated with that item (default: fetch_npz_item) |
search_mf_maker |
A function that takes the list of query and reference names and returns a two-column data frame with pairs of queries and references (default: create_allcomb_df) |
post_processor |
A function to process the search results (default: create_qbestd_df) |
nndtw_func |
A function to shortlist starting indices (default: sousrir_1nndtw) |
ssdtw_func |
A function to calculate a score of how likely a query occurs in a reference, given starting indices (default: sousrir_ssdtw) |
progress_bar |
Show progress bar while running search |
use_multisession |
Use future::multisession to run search using multiple R sessions in parallel |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.