fix crashes (#6)

- fix crashes (c276de4115b2f33f05687e7e468694f7c974ae46)

helper.py

@@ -1,65 +0,0 @@
-import streamlit as st
-import pandas as pd
-from plip_support import embed_text
-import numpy as np
-from PIL import Image
-import requests
-import tokenizers
-import os
-from io import BytesIO
-import pickle
-import base64
-
-import torch
-from transformers import (
-    VisionTextDualEncoderModel,
-    AutoFeatureExtractor,
-    AutoTokenizer,
-    CLIPModel,
-    AutoProcessor
-)
-import streamlit.components.v1 as components
-from st_clickable_images import clickable_images #pip install st-clickable-images
-
-
-@st.cache(
-    hash_funcs={
-        torch.nn.parameter.Parameter: lambda _: None,
-        tokenizers.Tokenizer: lambda _: None,
-        tokenizers.AddedToken: lambda _: None
-    }
-)
-def load_path_clip():
-    model = CLIPModel.from_pretrained("vinid/plip")
-    processor = AutoProcessor.from_pretrained("vinid/plip")
-    return model, processor
-
-@st.cache
-def init():
-    with open('data/twitter.asset', 'rb') as f:
-        data = pickle.load(f)
-    meta = data['meta'].reset_index(drop=True)
-    image_embedding = data['image_embedding']
-    text_embedding = data['text_embedding']
-    print(meta.shape, image_embedding.shape)
-    validation_subset_index = meta['source'].values == 'Val_Tweets'
-    return meta, image_embedding, text_embedding, validation_subset_index
-
-def embed_images(model, images, processor):
-    inputs = processor(images=images)
-    pixel_values = torch.tensor(np.array(inputs["pixel_values"]))
-
-    with torch.no_grad():
-        embeddings = model.get_image_features(pixel_values=pixel_values)
-    return embeddings
-
-def embed_texts(model, texts, processor):
-    inputs = processor(text=texts, padding="longest")
-    input_ids = torch.tensor(inputs["input_ids"])
-    attention_mask = torch.tensor(inputs["attention_mask"])
-
-    with torch.no_grad():
-        embeddings = model.get_text_features(
-            input_ids=input_ids, attention_mask=attention_mask
-        )
-    return embeddings

image2image.py

@@ -20,9 +20,48 @@ from transformers import (
 import streamlit.components.v1 as components
 from st_clickable_images import clickable_images #pip install st-clickable-images
 
-from helper import load_path_clip, init, embed_images
-
 
+@st.cache(
+    hash_funcs={
+        torch.nn.parameter.Parameter: lambda _: None,
+        tokenizers.Tokenizer: lambda _: None,
+        tokenizers.AddedToken: lambda _: None
+    }
+)
+def load_path_clip():
+    model = CLIPModel.from_pretrained("vinid/plip")
+    processor = AutoProcessor.from_pretrained("vinid/plip")
+    return model, processor
+
+@st.cache
+def init():
+    with open('data/twitter.asset', 'rb') as f:
+        data = pickle.load(f)
+    meta = data['meta'].reset_index(drop=True)
+    image_embedding = data['image_embedding']
+    text_embedding = data['text_embedding']
+    print(meta.shape, image_embedding.shape)
+    validation_subset_index = meta['source'].values == 'Val_Tweets'
+    return meta, image_embedding, text_embedding, validation_subset_index
+
+def embed_images(model, images, processor):
+    inputs = processor(images=images)
+    pixel_values = torch.tensor(np.array(inputs["pixel_values"]))
+
+    with torch.no_grad():
+        embeddings = model.get_image_features(pixel_values=pixel_values)
+    return embeddings
+
+def embed_texts(model, texts, processor):
+    inputs = processor(text=texts, padding="longest")
+    input_ids = torch.tensor(inputs["input_ids"])
+    attention_mask = torch.tensor(inputs["attention_mask"])
+
+    with torch.no_grad():
+        embeddings = model.get_text_features(
+            input_ids=input_ids, attention_mask=attention_mask
+        )
+    return embeddings
 def app():
     st.title('Image to Image Retrieval')
     st.markdown('#### A pathology image search engine that correlate images with images.')

text2image.py

@@ -16,8 +16,48 @@ from transformers import (
 )
 import streamlit.components.v1 as components
 
-from helper import load_path_clip, init, embed_texts
 
+@st.cache(
+    hash_funcs={
+        torch.nn.parameter.Parameter: lambda _: None,
+        tokenizers.Tokenizer: lambda _: None,
+        tokenizers.AddedToken: lambda _: None
+    }
+)
+def load_path_clip():
+    model = CLIPModel.from_pretrained("vinid/plip")
+    processor = AutoProcessor.from_pretrained("vinid/plip")
+    return model, processor
+
+@st.cache
+def init():
+    with open('data/twitter.asset', 'rb') as f:
+        data = pickle.load(f)
+    meta = data['meta'].reset_index(drop=True)
+    image_embedding = data['image_embedding']
+    text_embedding = data['text_embedding']
+    print(meta.shape, image_embedding.shape)
+    validation_subset_index = meta['source'].values == 'Val_Tweets'
+    return meta, image_embedding, text_embedding, validation_subset_index
+
+def embed_images(model, images, processor):
+    inputs = processor(images=images)
+    pixel_values = torch.tensor(np.array(inputs["pixel_values"]))
+
+    with torch.no_grad():
+        embeddings = model.get_image_features(pixel_values=pixel_values)
+    return embeddings
+
+def embed_texts(model, texts, processor):
+    inputs = processor(text=texts, padding="longest")
+    input_ids = torch.tensor(inputs["input_ids"])
+    attention_mask = torch.tensor(inputs["attention_mask"])
+
+    with torch.no_grad():
+        embeddings = model.get_text_features(
+            input_ids=input_ids, attention_mask=attention_mask
+        )
+    return embeddings
 
 
 def app():