Support Ultralytics YOLO models and TIMM models

.gitignore

@@ -1,3 +1,8 @@
+# pytorch related
+*.pt
+*.pth
+
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

nbs/timm.ipynb

@@ -0,0 +1,159 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-style: italic\">                                Available Models                                </span>\n",
+       "┏━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\"> Backend </span>┃<span style=\"font-weight: bold\"> Model ID                                        </span>┃<span style=\"font-weight: bold\"> Input --&gt; Output </span>┃\n",
+       "┡━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━┩\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\"> timm    </span>│<span style=\"color: #800080; text-decoration-color: #800080\"> vit_huge_patch14_clip_336.laion2b_ft_in12k_in1k </span>│<span style=\"color: #008000; text-decoration-color: #008000\"> image --&gt; class  </span>│\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\"> timm    </span>│<span style=\"color: #800080; text-decoration-color: #800080\"> maxvit_xlarge_tf_512.in21k_ft_in1k              </span>│<span style=\"color: #008000; text-decoration-color: #008000\"> image --&gt; class  </span>│\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\"> timm    </span>│<span style=\"color: #800080; text-decoration-color: #800080\"> maxvit_xlarge_tf_384.in21k_ft_in1k              </span>│<span style=\"color: #008000; text-decoration-color: #008000\"> image --&gt; class  </span>│\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\"> ...     </span>│<span style=\"color: #800080; text-decoration-color: #800080\"> ...                                             </span>│<span style=\"color: #008000; text-decoration-color: #008000\"> ...              </span>│\n",
+       "│<span style=\"color: #008080; text-decoration-color: #008080\"> ...     </span>│<span style=\"color: #800080; text-decoration-color: #800080\"> ...                                             </span>│<span style=\"color: #008000; text-decoration-color: #008000\"> ...              </span>│\n",
+       "└─────────┴─────────────────────────────────────────────────┴──────────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[3m                                Available Models                                \u001b[0m\n",
+       "┏━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1mBackend\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mModel ID                                       \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mInput --> Output\u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━┩\n",
+       "│\u001b[36m \u001b[0m\u001b[36mtimm   \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35mvit_huge_patch14_clip_336.laion2b_ft_in12k_in1k\u001b[0m\u001b[35m \u001b[0m│\u001b[32m \u001b[0m\u001b[32mimage --> class \u001b[0m\u001b[32m \u001b[0m│\n",
+       "│\u001b[36m \u001b[0m\u001b[36mtimm   \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35mmaxvit_xlarge_tf_512.in21k_ft_in1k             \u001b[0m\u001b[35m \u001b[0m│\u001b[32m \u001b[0m\u001b[32mimage --> class \u001b[0m\u001b[32m \u001b[0m│\n",
+       "│\u001b[36m \u001b[0m\u001b[36mtimm   \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35mmaxvit_xlarge_tf_384.in21k_ft_in1k             \u001b[0m\u001b[35m \u001b[0m│\u001b[32m \u001b[0m\u001b[32mimage --> class \u001b[0m\u001b[32m \u001b[0m│\n",
+       "│\u001b[36m \u001b[0m\u001b[36m...    \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m...                                            \u001b[0m\u001b[35m \u001b[0m│\u001b[32m \u001b[0m\u001b[32m...             \u001b[0m\u001b[32m \u001b[0m│\n",
+       "│\u001b[36m \u001b[0m\u001b[36m...    \u001b[0m\u001b[36m \u001b[0m│\u001b[35m \u001b[0m\u001b[35m...                                            \u001b[0m\u001b[35m \u001b[0m│\u001b[32m \u001b[0m\u001b[32m...             \u001b[0m\u001b[32m \u001b[0m│\n",
+       "└─────────┴─────────────────────────────────────────────────┴──────────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import xinfer\n",
+    "\n",
+    "xinfer.list_models(\"vit\", limit=3)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32m2024-10-11 23:43:39.344\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mxinfer.timm.timm_model\u001b[0m:\u001b[36m__init__\u001b[0m:\u001b[36m17\u001b[0m - \u001b[1mLoading model: mobilenetv2_050.lamb_in1k\u001b[0m\n",
+      "\u001b[32m2024-10-11 23:43:39.345\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mxinfer.timm.timm_model\u001b[0m:\u001b[36mload_model\u001b[0m:\u001b[36m21\u001b[0m - \u001b[1mLoading model: mobilenetv2_050.lamb_in1k\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "128884c6909b4ebb9a4f3881fdaff671",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model.safetensors:   0%|          | 0.00/7.98M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32m2024-10-11 23:43:40.408\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36mxinfer.timm.timm_model\u001b[0m:\u001b[36minference\u001b[0m:\u001b[36m27\u001b[0m - \u001b[1mRunning inference on https://ultralytics.com/images/bus.jpg\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "model = xinfer.create_model(\"mobilenetv2_050.lamb_in1k\", \"timm\")\n",
+    "\n",
+    "result = model.inference(\"https://ultralytics.com/images/bus.jpg\", top_k=10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'class': 'minibus', 'id': 654, 'confidence': 62.94279098510742},\n",
+       " {'class': 'police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria',\n",
+       "  'id': 734,\n",
+       "  'confidence': 8.970001220703125},\n",
+       " {'class': 'trolleybus, trolley coach, trackless trolley',\n",
+       "  'id': 874,\n",
+       "  'confidence': 4.9347052574157715},\n",
+       " {'class': 'ambulance', 'id': 407, 'confidence': 2.7388036251068115},\n",
+       " {'class': 'streetcar, tram, tramcar, trolley, trolley car',\n",
+       "  'id': 829,\n",
+       "  'confidence': 1.687123417854309},\n",
+       " {'class': 'jinrikisha, ricksha, rickshaw',\n",
+       "  'id': 612,\n",
+       "  'confidence': 1.6692038774490356},\n",
+       " {'class': 'passenger car, coach, carriage',\n",
+       "  'id': 705,\n",
+       "  'confidence': 1.348435401916504},\n",
+       " {'class': 'recreational vehicle, RV, R.V.',\n",
+       "  'id': 757,\n",
+       "  'confidence': 1.2413547039031982},\n",
+       " {'class': 'minivan', 'id': 656, 'confidence': 0.5516668558120728},\n",
+       " {'class': 'amphibian, amphibious vehicle',\n",
+       "  'id': 408,\n",
+       "  'confidence': 0.4996110796928406}]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "xinfer",
+   "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
+}