Duplicate from dawahealth/medsiglip-diagnosis

.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 +1,40 @@
+---
+language: en
+library_name: transformers
+pipeline_tag: image-classification
+tags:
+- vision
+- cervical-cancer
+- diagnosis
+license: apache-2.0
+---
+
+# 🩺 MedSigLip Diagnosis Model
+
+This repository contains **MedSigLip**, a deep learning model for cervical cancer image diagnosis.  
+It takes colposcopy images as input and predicts the most likely stage/class of the condition.  
+
+---
+
+## 📊 Model Details
+- **Task:** Image Classification  
+- **Domain:** Healthcare – Cervical Cancer Diagnosis  
+- **Framework:** Hugging Face Transformers / PyTorch  
+- **Author:** Khanyi Tapiwa Magagula (AI Eswatini)  
+
+---
+
+## 🚀 Inference API
+
+Once the **Inference API** is enabled, you can run predictions without any setup. Example:
+
+```python
+from huggingface_hub import InferenceClient
+
+# Replace with your repo name
+client = InferenceClient("KhanyiTapiwa00/medsiglip-diagnosis")
+
+# Run image classification
+result = client.image_classification("1_10.jpg")
+
+print(result)

app.py

@@ -0,0 +1,33 @@
+import gradio as gr
+from transformers import CLIPProcessor, CLIPModel
+from PIL import Image
+import torch
+
+MODEL_ID = "KhanyiTapiwa00/medsiglip-diagnosis"
+
+processor = CLIPProcessor.from_pretrained(MODEL_ID)
+model = CLIPModel.from_pretrained(MODEL_ID)
+model.eval()
+
+def predict(image: Image.Image, text: str):
+    if image is None or text.strip() == "":
+        return "Please provide both an image and a text description."
+    
+    inputs = processor(images=image, text=text, return_tensors="pt", padding=True)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    
+    logits = outputs.logits_per_image
+    probs = torch.softmax(logits, dim=1)
+    return str(probs.cpu().numpy())
+
+demo = gr.Interface(
+    fn=predict,
+    inputs=[gr.Image(type="pil", label="Upload Medical Image"),
+            gr.Textbox(label="Enter Description")],
+    outputs=gr.Textbox(label="Similarity Score"),
+    title="MedSigLIP AI Demo",
+    description="Upload a medical image and compare it with a text description."
+)
+
+demo.launch()

classifier.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b64668df46049b5d29e27315e99d34ccb86768780b25fbac0046deb45236bb3
+size 595387

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "SiglipModel"
+  ],
+  "dtype": "float32",
+  "initializer_factor": 1.0,
+  "model_type": "siglip",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "max_position_embeddings": 64,
+    "model_type": "siglip_text_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "projection_size": 1152,
+    "vocab_size": 32000
+  },
+  "transformers_version": "4.56.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 448,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d2e0293b9b1fb3a8978b50dc1dc25e7af502abde6f277d62404d8880ee0929
+size 3513309984

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862,
+  "size": {
+    "height": 448,
+    "width": 448
+  }
+}

requirements.txt

@@ -0,0 +1,5 @@
+torch
+transformers
+gradio
+Pillow
+

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e5036bed065526c3c212dfbe288752391797c4bb1a284aa18c9a0b23fcaf8ec
+size 798330

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "added_tokens_decoder": {
+    "1": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids"
+  ],
+  "model_max_length": 64,
+  "pad_token": "</s>",
+  "processor_class": "SiglipProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "SiglipTokenizer",
+  "unk_token": "<unk>"
+}