Duplicate from amarsaikhan/document-classifier

Co-authored-by: Aamarsaikhan Batjargal <amarsaikhan@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Document Classifier
+emoji: ⚡
+colorFrom: green
+colorTo: purple
+sdk: streamlit
+sdk_version: 1.21.0
+app_file: app.py
+pinned: false
+duplicated_from: amarsaikhan/document-classifier
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,34 @@
+
+import streamlit as st
+from transformers import pipeline
+from PIL import Image
+checkpoint = "openai/clip-vit-large-patch14"
+classifier = pipeline(model=checkpoint, task="zero-shot-image-classification")
+def get_best_label(predictions):
+    max_score = 0
+    label = ""
+    for p in predictions:
+        if p['score'] > max_score:
+            max_score = p['score']
+            label = p['label']
+    return label, max_score
+
+st.markdown('<h1 style="color:black;">Document Classifier</h1>', unsafe_allow_html=True)
+st.markdown('<h2 style="color:gray;">This model can classify input image to the following categories:</h2>', unsafe_allow_html=True)
+st.markdown('<h3 style="color:gray;"> <ul> <li>Invoice</li> <li>Bank statement</li> <li>Credit bureau</li> </ul> </h3>', unsafe_allow_html=True)
+
+
+
+upload= st.file_uploader('Insert image for classification', type=['png','jpg'])
+c1, c2= st.columns(2)
+if upload is not None:
+  image = Image.open(upload)
+  c1.header('Input Image')
+  c1.image(image)
+  print("c1", c1)
+  print("c2", c2)
+  c2.header('Output')
+  c2.subheader('Predicted class :')
+  predictions = classifier(image, candidate_labels=["invoice, receipt", "bank statement, financial statement", "credit report"])
+  c2.subheader('Predicted class :' + str(get_best_label(predictions)))
+  c2.write(str(predictions))

requirements.txt

@@ -0,0 +1,6 @@
+altair
+pandas
+streamlit
+transformers
+Pillow
+torch