Upload gradio copy.ipynb

gradio copy.ipynb

@@ -0,0 +1,170 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "build_sam_vit_3d...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/rohith/Desktop/M3D copy/llama/lib/python3.10/site-packages/monai/utils/deprecate_utils.py:221: FutureWarning: monai.networks.blocks.patchembedding PatchEmbeddingBlock.__init__:pos_embed: Argument `pos_embed` has been deprecated since version 1.2. It will be removed in version 1.4. please use `proj_type` instead.\n",
+      "  warn_deprecated(argname, msg, warning_category)\n",
+      "/Users/rohith/Desktop/M3D copy/llama/lib/python3.10/site-packages/monai/utils/deprecate_utils.py:221: FutureWarning: monai.networks.nets.vit ViT.__init__:pos_embed: Argument `pos_embed` has been deprecated since version 1.2. It will be removed in version 1.4. please use `proj_type` instead.\n",
+      "  warn_deprecated(argname, msg, warning_category)\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "6884c5d2441e4a8a9f18b6e0595d119e",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "* Running on local URL:  http://127.0.0.1:7860\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
+      "Starting from v4.46, the `logits` model output will have the same type as the model (except at train time, where it will always be FP32)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Using existing dataset file at: .gradio/flagged/dataset1.csv\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "import torch\n",
+    "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
+    "import simple_slice_viewer as ssv\n",
+    "import SimpleITK as sikt\n",
+    "import gradio as gr\n",
+    "\n",
+    "device = torch.device('cpu')  # Set to 'cuda' if using a GPU\n",
+    "dtype = torch.float32  # Data type for model processing\n",
+    "\n",
+    "model_name_or_path = 'GoodBaiBai88/M3D-LaMed-Phi-3-4B'\n",
+    "proj_out_num = 256  # Number of projection outputs required for the image\n",
+    "\n",
+    "# Load model and tokenizer\n",
+    "model = AutoModelForCausalLM.from_pretrained(\n",
+    "    model_name_or_path,\n",
+    "    torch_dtype=torch.float32,\n",
+    "    device_map='cpu',\n",
+    "    trust_remote_code=True\n",
+    ")\n",
+    "\n",
+    "tokenizer = AutoTokenizer.from_pretrained(\n",
+    "    model_name_or_path,\n",
+    "    model_max_length=512,\n",
+    "    padding_side=\"right\",\n",
+    "    use_fast=False,\n",
+    "    trust_remote_code=True\n",
+    ")\n",
+    "\n",
+    "def process_image(image_path, question):\n",
+    "    # Load the image\n",
+    "    image_np = np.load(image_path)  # Load the .npy image\n",
+    "    image_tokens = \"<im_patch>\" * proj_out_num\n",
+    "    input_txt = image_tokens + question\n",
+    "    input_id = tokenizer(input_txt, return_tensors=\"pt\")['input_ids'].to(device=device)\n",
+    "\n",
+    "    # Prepare image for model\n",
+    "    image_pt = torch.from_numpy(image_np).unsqueeze(0).to(dtype=dtype, device=device)\n",
+    "\n",
+    "    # Generate model response\n",
+    "    generation = model.generate(image_pt, input_id, max_new_tokens=256, do_sample=True, top_p=0.9, temperature=1.0)\n",
+    "    generated_texts = tokenizer.batch_decode(generation, skip_special_tokens=True)\n",
+    "\n",
+    "    return generated_texts[0]\n",
+    "\n",
+    "# Gradio Interface\n",
+    "def gradio_interface(image, question):\n",
+    "    response = process_image(image.name, question)\n",
+    "    return response\n",
+    "\n",
+    "# Gradio App\n",
+    "gr.Interface(\n",
+    "    fn=gradio_interface,\n",
+    "    inputs=[\n",
+    "        gr.File(label=\"Upload .npy Image\", type=\"filepath\"),  # For uploading .npy image\n",
+    "        gr.Textbox(label=\"Enter your question\", placeholder=\"Ask something about the image...\"),\n",
+    "    ],\n",
+    "    outputs=gr.Textbox(label=\"Model Response\"),\n",
+    "    title=\"Medical Image Analysis\",\n",
+    "    description=\"Upload a .npy image and ask a question to analyze it using the model.\"\n",
+    ").launch()\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}