From fc531a19156fb1853b84d3a537967251252e094a Mon Sep 17 00:00:00 2001 From: Debanjum Singh Solanky Date: Sat, 28 Aug 2021 22:26:12 -0700 Subject: [PATCH] Resolve relative file paths to model embeddings in all search types --- src/search_type/asymmetric.py | 6 +++--- src/search_type/image_search.py | 2 +- src/search_type/symmetric_ledger.py | 6 +++--- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/src/search_type/asymmetric.py b/src/search_type/asymmetric.py index d9320524..656d1fb3 100644 --- a/src/search_type/asymmetric.py +++ b/src/search_type/asymmetric.py @@ -15,7 +15,7 @@ import torch from sentence_transformers import SentenceTransformer, CrossEncoder, util # Internal Packages -from utils.helpers import get_absolute_path +from utils.helpers import get_absolute_path, resolve_absolute_path from processor.org_mode.org_to_jsonl import org_to_jsonl @@ -50,7 +50,7 @@ def extract_entries(notesfile, verbose=0): def compute_embeddings(entries, bi_encoder, embeddings_file, regenerate=False, verbose=0): "Compute (and Save) Embeddings or Load Pre-Computed Embeddings" # Load pre-computed embeddings from file if exists - if embeddings_file.exists() and not regenerate: + if resolve_absolute_path(embeddings_file).exists() and not regenerate: corpus_embeddings = torch.load(get_absolute_path(embeddings_file)) if verbose > 0: print(f"Loaded embeddings from {embeddings_file}") @@ -152,7 +152,7 @@ def setup(input_files, input_filter, compressed_jsonl, embeddings, regenerate=Fa bi_encoder, cross_encoder, top_k = initialize_model() # Map notes in Org-Mode files to (compressed) JSONL formatted file - if not compressed_jsonl.exists() or regenerate: + if not resolve_absolute_path(compressed_jsonl).exists() or regenerate: org_to_jsonl(input_files, input_filter, compressed_jsonl, verbose) # Extract Entries diff --git a/src/search_type/image_search.py b/src/search_type/image_search.py index 88b69f83..7cad8624 100644 --- a/src/search_type/image_search.py +++ b/src/search_type/image_search.py @@ -32,7 +32,7 @@ def compute_embeddings(image_names, model, embeddings_file, regenerate=False, ve image_embeddings = None # Load pre-computed embeddings from file if exists - if embeddings_file.exists() and not regenerate: + if resolve_absolute_path(embeddings_file).exists() and not regenerate: image_embeddings = torch.load(embeddings_file) if verbose: print(f"Loaded pre-computed embeddings from {embeddings_file}") diff --git a/src/search_type/symmetric_ledger.py b/src/search_type/symmetric_ledger.py index 6c0bc4c1..d19f82eb 100644 --- a/src/search_type/symmetric_ledger.py +++ b/src/search_type/symmetric_ledger.py @@ -13,7 +13,7 @@ import torch from sentence_transformers import SentenceTransformer, CrossEncoder, util # Internal Packages -from utils.helpers import get_absolute_path +from utils.helpers import get_absolute_path, resolve_absolute_path from processor.ledger.beancount_to_jsonl import beancount_to_jsonl @@ -44,7 +44,7 @@ def extract_entries(notesfile, verbose=0): def compute_embeddings(entries, bi_encoder, embeddings_file, regenerate=False, verbose=0): "Compute (and Save) Embeddings or Load Pre-Computed Embeddings" # Load pre-computed embeddings from file if exists - if embeddings_file.exists() and not regenerate: + if resolve_absolute_path(embeddings_file).exists() and not regenerate: corpus_embeddings = torch.load(get_absolute_path(embeddings_file)) if verbose > 0: print(f"Loaded embeddings from {embeddings_file}") @@ -146,7 +146,7 @@ def setup(input_files, input_filter, compressed_jsonl, embeddings, regenerate=Fa bi_encoder, cross_encoder, top_k = initialize_model() # Map notes in Org-Mode files to (compressed) JSONL formatted file - if not compressed_jsonl.exists() or regenerate: + if not resolve_absolute_path(compressed_jsonl).exists() or regenerate: beancount_to_jsonl(input_files, input_filter, compressed_jsonl, verbose) # Extract Entries