done

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* 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
+*.sav filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,33 @@
+import streamlit as st
+from PIL import Image
+from transformers import AutoImageProcessor
+import torch
+import joblib
+
+with st.sidebar:
+    st.subheader('Image Classifier using ResNet50')
+    st.divider()
+    st.write('This is a image classification app using ResNet50. It is a state of the art model for image classification. It is a pretrained model which is trained on a large dataset of images. It can be used for classifying any image. It is a very powerful model and is very fast. It is also very accurate.')
+    image = Image.open('resnet_architecture.png')
+    st.image(image, caption='Bert Model')
+    st.code('App Built by Ambuj Raj',language='python')
+
+
+st.title('Image Classifier using ResNet50')
+
+uploaded_file = st.file_uploader("Choose a image", type=['png', 'jpeg', 'jpg'])
+if uploaded_file is not None:
+    st.image(uploaded_file, width=300)
+    raw_image = Image.open(uploaded_file).convert('RGB')
+
+if st.button('Classify Image'):
+    with st.spinner('Classifying Image...'):
+        processor = AutoImageProcessor.from_pretrained("microsoft/resnet-50")
+        loaded_model = joblib.load("model.sav")
+        inputs = processor(raw_image, return_tensors="pt")
+        with torch.no_grad():
+            logits = loaded_model(**inputs).logits
+        # model predicts one of the 1000 ImageNet classes
+        predicted_label = logits.argmax(-1).item()
+    st.success('Image Classified!')
+    st.write('Predicted Label is: ',loaded_model.config.id2label[predicted_label])

main.py

@@ -0,0 +1,20 @@
+from transformers import AutoImageProcessor, ResNetForImageClassification
+import torch
+from datasets import load_dataset
+import joblib
+
+dataset = load_dataset("huggingface/cats-image")
+image = dataset["test"]["image"][0]
+print(image)
+
+processor = AutoImageProcessor.from_pretrained("microsoft/resnet-50")
+
+loaded_model = joblib.load("model.sav")
+inputs = processor(image, return_tensors="pt")
+
+with torch.no_grad():
+    logits = loaded_model(**inputs).logits
+
+# model predicts one of the 1000 ImageNet classes
+predicted_label = logits.argmax(-1).item()
+print(loaded_model.config.id2label[predicted_label])

model.sav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b213354ad1d09fe2385e2b4f720cd2e28a1449258f966d5d7e27da72891eaa
+size 102632052

requirements.txt

@@ -0,0 +1,4 @@
+torch
+transformers
+joblib
+streamlit