Duplicate from GV05/Marvel-Heroes-Classification-using-clip

Co-authored-by: Noam Shimshoviz <GV05@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,31 @@
+*.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
+*.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
+*.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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pb 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
+saved_model/**/* 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 +1,14 @@
+---
+title: Marvel Heroes Classification Using Clip
+emoji: 🐠
+colorFrom: purple
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.4
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: GV05/Marvel-Heroes-Classification-using-clip
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,22 @@
+from transformers import CLIPProcessor, CLIPModel
+import gradio as gr
+
+model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
+
+classes = ["Iron Man", "Captain America", "Thor", "Spider-Man", "Black Widow", "Black Panther","Hulk", "Ant-Man",
+           'Peggy Carter', "Daredevil", "Star-Lord", "Wong", "Doctor Strange","Nick Fury", "Gamora", "Jessica Jones",
+           "Nebula", "Falcon", "Winter Soldier", "Rocket", "Hawkeye"]
+text = [f"a photo of {x}" for x in classes]
+def predict(img):
+  inputs = processor(text=text, images=img, return_tensors="pt", padding=True)
+  outputs = model(**inputs)
+  logits_per_image = outputs.logits_per_image # this is the image-text similarity score
+  probs = logits_per_image.softmax(dim=1).squeeze() # we can take the softmax to get the label probabilities
+  return {classes[i] : float(probs[i]) for i in range(len(probs))}
+
+title = "Marvel Heroes Classification"
+description = "Using clip for zero-shot classification"
+examples = ["black_panter.jpg"]
+gr.Interface(fn=predict, inputs = gr.inputs.Image(shape = (512,512)), outputs= gr.outputs.Label(),
+             examples=examples, title=title, description=description).launch(inline=False)

requirements.txt

@@ -0,0 +1,3 @@
+transformers
+gradio
+torch