initial_commit

app.py

@@ -0,0 +1,54 @@
+import streamlit as st
+import torch
+from PIL import Image
+from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer
+model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+feature_extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+#pickle.load(open('energy_model.pkl', 'rb'))
+#vocab = np.load('w2i.p', allow_pickle=True)
+print("="*150)
+print("MODEL LOADED")
+st.title("img_captioning_app")
+#st.text("Build with Streamlit and OpenCV")
+if "photo" not in st.session_state:
+	st.session_state["photo"]="not done"
+
+c2, c3 = st.columns([2,1])
+def change_photo_state():
+	st.session_state["photo"]="done"
+print("="*150)
+print("RESNET MODEL LOADED")
+
+@st.cache
+def load_image(img):
+	im = Image.open(img)
+	return im
+activities = ["Detection","About"]
+choice = st.sidebar.selectbox("Select Activty",activities)
+uploaded_photo = c2.file_uploader("Upload Image",type=['jpg','png','jpeg'], on_change=change_photo_state)
+camera_photo = c2.camera_input("Take a photo", on_change=change_photo_state)
+if choice == 'Detection':
+    st.subheader("Face Detection") 
+    if st.session_state["photo"]=="done":
+        if uploaded_photo:
+            our_image= load_image(uploaded_photo)
+        elif camera_photo:
+            our_image= load_image(camera_photo)
+        elif uploaded_photo==None and camera_photo==None:
+            our_image= load_image('image.jpg')
+        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        model.to(device)
+        max_length = 16
+        num_beams = 4
+        gen_kwargs = {"max_length": max_length, "num_beams": num_beams}
+        def predict_step(our_image):
+            if our_image.mode != "RGB":
+                our_image = our_image.convert(mode="RGB")
+            pixel_values = feature_extractor(images=our_image, return_tensors="pt").pixel_values
+            pixel_values = pixel_values.to(device)
+            output_ids = model.generate(pixel_values, **gen_kwargs)
+            preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
+            preds = [pred.strip() for pred in preds]
+            return preds
+        predict_step(our_image)

requirements.txt

@@ -0,0 +1,12 @@
+# -f https://download.pytorch.org/whl/torch_stable.html
+# torchvision==0.7.0+cpu
+# torch==1.6.0+cpu
+torch
+torchvision
+pandas==1.0.3
+wget==3.2
+streamlit==0.71.0
+spacy==2.3.2
+https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.2.0/en_core_web_sm-2.2.0.tar.gz
+requests==2.22.0
+Pillow>=8.1.1