| { |
| "cells": [ |
| { |
| "cell_type": "code", |
| "execution_count": 1, |
| "id": "084ad9b6", |
| "metadata": { |
| "execution": { |
| "iopub.execute_input": "2023-06-05T23:35:21.686879Z", |
| "iopub.status.busy": "2023-06-05T23:35:21.686145Z", |
| "iopub.status.idle": "2023-06-05T23:35:21.705765Z", |
| "shell.execute_reply": "2023-06-05T23:35:21.703749Z" |
| }, |
| "papermill": { |
| "duration": 0.034517, |
| "end_time": "2023-06-05T23:35:21.710915", |
| "exception": false, |
| "start_time": "2023-06-05T23:35:21.676398", |
| "status": "completed" |
| }, |
| "tags": [ |
| "parameters" |
| ] |
| }, |
| "outputs": [], |
| "source": [ |
| "file_path = \"./example.jpg\"" |
| ] |
| }, |
| { |
| "cell_type": "code", |
| "execution_count": 2, |
| "id": "50691c17", |
| "metadata": { |
| "execution": { |
| "iopub.execute_input": "2023-06-05T23:35:21.723912Z", |
| "iopub.status.busy": "2023-06-05T23:35:21.723745Z", |
| "iopub.status.idle": "2023-06-05T23:35:23.406183Z", |
| "shell.execute_reply": "2023-06-05T23:35:23.405694Z" |
| }, |
| "papermill": { |
| "duration": 1.689556, |
| "end_time": "2023-06-05T23:35:23.407237", |
| "exception": false, |
| "start_time": "2023-06-05T23:35:21.717681", |
| "status": "completed" |
| }, |
| "tags": [] |
| }, |
| "outputs": [], |
| "source": [ |
| "import os\n", |
| "import cv2\n", |
| "\n", |
| "from detectron2.config import CfgNode as CN\n", |
| "from detectron2.utils.visualizer import ColorMode, Visualizer\n", |
| "from detectron2.data import MetadataCatalog" |
| ] |
| }, |
| { |
| "attachments": {}, |
| "cell_type": "markdown", |
| "id": "062a815f", |
| "metadata": { |
| "papermill": { |
| "duration": 0.006791, |
| "end_time": "2023-06-05T23:35:23.415323", |
| "exception": false, |
| "start_time": "2023-06-05T23:35:23.408532", |
| "status": "completed" |
| }, |
| "tags": [] |
| }, |
| "source": [ |
| "### Step 1: instantiate config" |
| ] |
| }, |
| { |
| "cell_type": "code", |
| "execution_count": 3, |
| "id": "c5f1a2ba", |
| "metadata": { |
| "execution": { |
| "iopub.execute_input": "2023-06-05T23:35:23.418917Z", |
| "iopub.status.busy": "2023-06-05T23:35:23.418654Z", |
| "iopub.status.idle": "2023-06-05T23:35:23.746319Z", |
| "shell.execute_reply": "2023-06-05T23:35:23.745402Z" |
| }, |
| "papermill": { |
| "duration": 0.330876, |
| "end_time": "2023-06-05T23:35:23.747488", |
| "exception": false, |
| "start_time": "2023-06-05T23:35:23.416612", |
| "status": "completed" |
| }, |
| "tags": [] |
| }, |
| "outputs": [], |
| "source": [ |
| "from detectron2.config import get_cfg\n", |
| "from dit.ditod import add_vit_config\n", |
| "\n", |
| "cfg = get_cfg()\n", |
| "add_vit_config(cfg)\n", |
| "cfg.merge_from_file(\"publaynet_configs/cascade/cascade_dit_base.yaml\")" |
| ] |
| }, |
| { |
| "attachments": {}, |
| "cell_type": "markdown", |
| "id": "33a583f2", |
| "metadata": { |
| "papermill": { |
| "duration": 0.005449, |
| "end_time": "2023-06-05T23:35:23.754363", |
| "exception": false, |
| "start_time": "2023-06-05T23:35:23.748914", |
| "status": "completed" |
| }, |
| "tags": [] |
| }, |
| "source": [ |
| "### Step 2: add model weights URL to config" |
| ] |
| }, |
| { |
| "cell_type": "code", |
| "execution_count": 4, |
| "id": "e218a6cb", |
| "metadata": { |
| "execution": { |
| "iopub.execute_input": "2023-06-05T23:35:23.757701Z", |
| "iopub.status.busy": "2023-06-05T23:35:23.757423Z", |
| "iopub.status.idle": "2023-06-05T23:35:23.760211Z", |
| "shell.execute_reply": "2023-06-05T23:35:23.759821Z" |
| }, |
| "papermill": { |
| "duration": 0.005636, |
| "end_time": "2023-06-05T23:35:23.761117", |
| "exception": false, |
| "start_time": "2023-06-05T23:35:23.755481", |
| "status": "completed" |
| }, |
| "tags": [] |
| }, |
| "outputs": [], |
| "source": [ |
| "cfg.MODEL.WEIGHTS = \"https://layoutlm.blob.core.windows.net/dit/dit-fts/publaynet_dit-b_cascade.pth\"" |
| ] |
| }, |
| { |
| "attachments": {}, |
| "cell_type": "markdown", |
| "id": "7fa2c50c", |
| "metadata": { |
| "papermill": { |
| "duration": 0.001471, |
| "end_time": "2023-06-05T23:35:23.763846", |
| "exception": false, |
| "start_time": "2023-06-05T23:35:23.762375", |
| "status": "completed" |
| }, |
| "tags": [] |
| }, |
| "source": [ |
| "### Step 3: set device" |
| ] |
| }, |
| { |
| "cell_type": "code", |
| "execution_count": 5, |
| "id": "b4a59be1", |
| "metadata": { |
| "execution": { |
| "iopub.execute_input": "2023-06-05T23:35:23.767427Z", |
| "iopub.status.busy": "2023-06-05T23:35:23.767221Z", |
| "iopub.status.idle": "2023-06-05T23:35:23.783477Z", |
| "shell.execute_reply": "2023-06-05T23:35:23.782833Z" |
| }, |
| "papermill": { |
| "duration": 0.019127, |
| "end_time": "2023-06-05T23:35:23.784489", |
| "exception": false, |
| "start_time": "2023-06-05T23:35:23.765362", |
| "status": "completed" |
| }, |
| "tags": [] |
| }, |
| "outputs": [], |
| "source": [ |
| "import torch\n", |
| "\n", |
| "cfg.MODEL.DEVICE = \"cuda\" if torch.cuda.is_available() else \"cpu\"" |
| ] |
| }, |
| { |
| "attachments": {}, |
| "cell_type": "markdown", |
| "id": "07dbb74d", |
| "metadata": { |
| "papermill": { |
| "duration": 0.001317, |
| "end_time": "2023-06-05T23:35:23.787172", |
| "exception": false, |
| "start_time": "2023-06-05T23:35:23.785855", |
| "status": "completed" |
| }, |
| "tags": [] |
| }, |
| "source": [ |
| "### Step 4: define model" |
| ] |
| }, |
| { |
| "cell_type": "code", |
| "execution_count": 6, |
| "id": "7c33676f", |
| "metadata": { |
| "execution": { |
| "iopub.execute_input": "2023-06-05T23:35:23.791150Z", |
| "iopub.status.busy": "2023-06-05T23:35:23.790903Z", |
| "iopub.status.idle": "2023-06-05T23:35:24.537777Z", |
| "shell.execute_reply": "2023-06-05T23:35:24.536919Z" |
| }, |
| "papermill": { |
| "duration": 0.247415, |
| "end_time": "2023-06-05T23:35:24.035873", |
| "exception": false, |
| "start_time": "2023-06-05T23:35:23.788458", |
| "status": "completed" |
| }, |
| "tags": [] |
| }, |
| "outputs": [ |
| { |
| "ename": "KeyboardInterrupt", |
| "evalue": "", |
| "output_type": "error", |
| "traceback": [ |
| "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", |
| "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", |
| "Cell \u001b[0;32mIn[6], line 3\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mdetectron2\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mengine\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m DefaultPredictor\n\u001b[0;32m----> 3\u001b[0m predictor \u001b[38;5;241m=\u001b[39m \u001b[43mDefaultPredictor\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcfg\u001b[49m\u001b[43m)\u001b[49m\n", |
| "File \u001b[0;32m~/detectron2_repo/detectron2/engine/defaults.py:282\u001b[0m, in \u001b[0;36mDefaultPredictor.__init__\u001b[0;34m(self, cfg)\u001b[0m\n\u001b[1;32m 280\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__init__\u001b[39m(\u001b[38;5;28mself\u001b[39m, cfg):\n\u001b[1;32m 281\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcfg \u001b[38;5;241m=\u001b[39m cfg\u001b[38;5;241m.\u001b[39mclone() \u001b[38;5;66;03m# cfg can be modified by model\u001b[39;00m\n\u001b[0;32m--> 282\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel \u001b[38;5;241m=\u001b[39m \u001b[43mbuild_model\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcfg\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 283\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel\u001b[38;5;241m.\u001b[39meval()\n\u001b[1;32m 284\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(cfg\u001b[38;5;241m.\u001b[39mDATASETS\u001b[38;5;241m.\u001b[39mTEST):\n", |
| "File \u001b[0;32m~/detectron2_repo/detectron2/modeling/meta_arch/build.py:22\u001b[0m, in \u001b[0;36mbuild_model\u001b[0;34m(cfg)\u001b[0m\n\u001b[1;32m 17\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 18\u001b[0m \u001b[38;5;124;03mBuild the whole model architecture, defined by ``cfg.MODEL.META_ARCHITECTURE``.\u001b[39;00m\n\u001b[1;32m 19\u001b[0m \u001b[38;5;124;03mNote that it does not load any weights from ``cfg``.\u001b[39;00m\n\u001b[1;32m 20\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 21\u001b[0m meta_arch \u001b[38;5;241m=\u001b[39m cfg\u001b[38;5;241m.\u001b[39mMODEL\u001b[38;5;241m.\u001b[39mMETA_ARCHITECTURE\n\u001b[0;32m---> 22\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mMETA_ARCH_REGISTRY\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmeta_arch\u001b[49m\u001b[43m)\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcfg\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 23\u001b[0m model\u001b[38;5;241m.\u001b[39mto(torch\u001b[38;5;241m.\u001b[39mdevice(cfg\u001b[38;5;241m.\u001b[39mMODEL\u001b[38;5;241m.\u001b[39mDEVICE))\n\u001b[1;32m 24\u001b[0m _log_api_usage(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodeling.meta_arch.\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m meta_arch)\n", |
| "File \u001b[0;32m~/detectron2_repo/detectron2/config/config.py:189\u001b[0m, in \u001b[0;36mconfigurable.<locals>.wrapped\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 186\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mClass with @configurable must have a \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mfrom_config\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m classmethod.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 188\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m _called_with_cfg(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m--> 189\u001b[0m explicit_args \u001b[38;5;241m=\u001b[39m \u001b[43m_get_args_from_config\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfrom_config_func\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 190\u001b[0m init_func(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mexplicit_args)\n\u001b[1;32m 191\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n", |
| "File \u001b[0;32m~/detectron2_repo/detectron2/config/config.py:245\u001b[0m, in \u001b[0;36m_get_args_from_config\u001b[0;34m(from_config_func, *args, **kwargs)\u001b[0m\n\u001b[1;32m 243\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m name \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m supported_arg_names:\n\u001b[1;32m 244\u001b[0m extra_kwargs[name] \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(name)\n\u001b[0;32m--> 245\u001b[0m ret \u001b[38;5;241m=\u001b[39m \u001b[43mfrom_config_func\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 246\u001b[0m \u001b[38;5;66;03m# forward the other arguments to __init__\u001b[39;00m\n\u001b[1;32m 247\u001b[0m ret\u001b[38;5;241m.\u001b[39mupdate(extra_kwargs)\n", |
| "File \u001b[0;32m~/detectron2_repo/detectron2/modeling/meta_arch/rcnn.py:73\u001b[0m, in \u001b[0;36mGeneralizedRCNN.from_config\u001b[0;34m(cls, cfg)\u001b[0m\n\u001b[1;32m 71\u001b[0m \u001b[38;5;129m@classmethod\u001b[39m\n\u001b[1;32m 72\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mfrom_config\u001b[39m(\u001b[38;5;28mcls\u001b[39m, cfg):\n\u001b[0;32m---> 73\u001b[0m backbone \u001b[38;5;241m=\u001b[39m \u001b[43mbuild_backbone\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcfg\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 74\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m {\n\u001b[1;32m 75\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbackbone\u001b[39m\u001b[38;5;124m\"\u001b[39m: backbone,\n\u001b[1;32m 76\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mproposal_generator\u001b[39m\u001b[38;5;124m\"\u001b[39m: build_proposal_generator(cfg, backbone\u001b[38;5;241m.\u001b[39moutput_shape()),\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 81\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpixel_std\u001b[39m\u001b[38;5;124m\"\u001b[39m: cfg\u001b[38;5;241m.\u001b[39mMODEL\u001b[38;5;241m.\u001b[39mPIXEL_STD,\n\u001b[1;32m 82\u001b[0m }\n", |
| "File \u001b[0;32m~/detectron2_repo/detectron2/modeling/backbone/build.py:31\u001b[0m, in \u001b[0;36mbuild_backbone\u001b[0;34m(cfg, input_shape)\u001b[0m\n\u001b[1;32m 28\u001b[0m input_shape \u001b[38;5;241m=\u001b[39m ShapeSpec(channels\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mlen\u001b[39m(cfg\u001b[38;5;241m.\u001b[39mMODEL\u001b[38;5;241m.\u001b[39mPIXEL_MEAN))\n\u001b[1;32m 30\u001b[0m backbone_name \u001b[38;5;241m=\u001b[39m cfg\u001b[38;5;241m.\u001b[39mMODEL\u001b[38;5;241m.\u001b[39mBACKBONE\u001b[38;5;241m.\u001b[39mNAME\n\u001b[0;32m---> 31\u001b[0m backbone \u001b[38;5;241m=\u001b[39m \u001b[43mBACKBONE_REGISTRY\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbackbone_name\u001b[49m\u001b[43m)\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcfg\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minput_shape\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 32\u001b[0m \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(backbone, Backbone)\n\u001b[1;32m 33\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m backbone\n", |
| "File \u001b[0;32m/appuser/app/unilm/dit/ditod/backbone.py:145\u001b[0m, in \u001b[0;36mbuild_vit_fpn_backbone\u001b[0;34m(cfg, input_shape)\u001b[0m\n\u001b[1;32m 134\u001b[0m \u001b[38;5;129m@BACKBONE_REGISTRY\u001b[39m\u001b[38;5;241m.\u001b[39mregister()\n\u001b[1;32m 135\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mbuild_vit_fpn_backbone\u001b[39m(cfg, input_shape: ShapeSpec):\n\u001b[1;32m 136\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 137\u001b[0m \u001b[38;5;124;03m Create a VIT w/ FPN backbone.\u001b[39;00m\n\u001b[1;32m 138\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 143\u001b[0m \u001b[38;5;124;03m backbone (Backbone): backbone module, must be a subclass of :class:`Backbone`.\u001b[39;00m\n\u001b[1;32m 144\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 145\u001b[0m bottom_up \u001b[38;5;241m=\u001b[39m \u001b[43mbuild_VIT_backbone\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcfg\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 146\u001b[0m in_features \u001b[38;5;241m=\u001b[39m cfg\u001b[38;5;241m.\u001b[39mMODEL\u001b[38;5;241m.\u001b[39mFPN\u001b[38;5;241m.\u001b[39mIN_FEATURES\n\u001b[1;32m 147\u001b[0m out_channels \u001b[38;5;241m=\u001b[39m cfg\u001b[38;5;241m.\u001b[39mMODEL\u001b[38;5;241m.\u001b[39mFPN\u001b[38;5;241m.\u001b[39mOUT_CHANNELS\n", |
| "File \u001b[0;32m/appuser/app/unilm/dit/ditod/backbone.py:131\u001b[0m, in \u001b[0;36mbuild_VIT_backbone\u001b[0;34m(cfg)\u001b[0m\n\u001b[1;32m 127\u001b[0m pos_type \u001b[38;5;241m=\u001b[39m cfg\u001b[38;5;241m.\u001b[39mMODEL\u001b[38;5;241m.\u001b[39mVIT\u001b[38;5;241m.\u001b[39mPOS_TYPE\n\u001b[1;32m 129\u001b[0m model_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28meval\u001b[39m(\u001b[38;5;28mstr\u001b[39m(cfg\u001b[38;5;241m.\u001b[39mMODEL\u001b[38;5;241m.\u001b[39mVIT\u001b[38;5;241m.\u001b[39mMODEL_KWARGS)\u001b[38;5;241m.\u001b[39mreplace(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m))\n\u001b[0;32m--> 131\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mVIT_Backbone\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mout_features\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdrop_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mimg_size\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpos_type\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel_kwargs\u001b[49m\u001b[43m)\u001b[49m\n", |
| "File \u001b[0;32m/appuser/app/unilm/dit/ditod/backbone.py:67\u001b[0m, in \u001b[0;36mVIT_Backbone.__init__\u001b[0;34m(self, name, out_features, drop_path, img_size, pos_type, model_kwargs)\u001b[0m\n\u001b[1;32m 65\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mbeit\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;129;01min\u001b[39;00m name \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdit\u001b[39m\u001b[38;5;124m'\u001b[39m \u001b[38;5;129;01min\u001b[39;00m name:\n\u001b[1;32m 66\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m pos_type \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mabs\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[0;32m---> 67\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbackbone \u001b[38;5;241m=\u001b[39m \u001b[43mmodel_func\u001b[49m\u001b[43m(\u001b[49m\u001b[43mimg_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mimg_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 68\u001b[0m \u001b[43m \u001b[49m\u001b[43mout_features\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mout_features\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 69\u001b[0m \u001b[43m \u001b[49m\u001b[43mdrop_path_rate\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdrop_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 70\u001b[0m \u001b[43m \u001b[49m\u001b[43muse_abs_pos_emb\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 71\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 72\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m pos_type \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mshared_rel\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 73\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbackbone \u001b[38;5;241m=\u001b[39m model_func(img_size\u001b[38;5;241m=\u001b[39mimg_size,\n\u001b[1;32m 74\u001b[0m out_features\u001b[38;5;241m=\u001b[39mout_features,\n\u001b[1;32m 75\u001b[0m drop_path_rate\u001b[38;5;241m=\u001b[39mdrop_path,\n\u001b[1;32m 76\u001b[0m use_shared_rel_pos_bias\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[1;32m 77\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mmodel_kwargs)\n", |
| "File \u001b[0;32m/appuser/app/unilm/dit/ditod/beit.py:635\u001b[0m, in \u001b[0;36mdit_base_patch16\u001b[0;34m(pretrained, **kwargs)\u001b[0m\n\u001b[1;32m 634\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdit_base_patch16\u001b[39m(pretrained\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m--> 635\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mBEiT\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 636\u001b[0m \u001b[43m \u001b[49m\u001b[43mpatch_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m16\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 637\u001b[0m \u001b[43m \u001b[49m\u001b[43membed_dim\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m768\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 638\u001b[0m \u001b[43m \u001b[49m\u001b[43mdepth\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m12\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 639\u001b[0m \u001b[43m \u001b[49m\u001b[43mnum_heads\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m12\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 640\u001b[0m \u001b[43m \u001b[49m\u001b[43mmlp_ratio\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m4\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 641\u001b[0m \u001b[43m \u001b[49m\u001b[43mqkv_bias\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 642\u001b[0m \u001b[43m \u001b[49m\u001b[43mnorm_layer\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpartial\u001b[49m\u001b[43m(\u001b[49m\u001b[43mnn\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mLayerNorm\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43meps\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m1e-6\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 643\u001b[0m \u001b[43m \u001b[49m\u001b[43minit_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 644\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 645\u001b[0m model\u001b[38;5;241m.\u001b[39mdefault_cfg \u001b[38;5;241m=\u001b[39m _cfg()\n\u001b[1;32m 646\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m model\n", |
| "File \u001b[0;32m/appuser/app/unilm/dit/ditod/beit.py:460\u001b[0m, in \u001b[0;36mBEiT.__init__\u001b[0;34m(self, img_size, patch_size, in_chans, num_classes, embed_dim, depth, num_heads, mlp_ratio, qkv_bias, qk_scale, drop_rate, attn_drop_rate, drop_path_rate, hybrid_backbone, norm_layer, init_values, use_abs_pos_emb, use_rel_pos_bias, use_shared_rel_pos_bias, use_checkpoint, pretrained, out_features)\u001b[0m\n\u001b[1;32m 458\u001b[0m dpr \u001b[38;5;241m=\u001b[39m [x\u001b[38;5;241m.\u001b[39mitem() \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mlinspace(\u001b[38;5;241m0\u001b[39m, drop_path_rate, depth)] \u001b[38;5;66;03m# stochastic depth decay rule\u001b[39;00m\n\u001b[1;32m 459\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39muse_rel_pos_bias \u001b[38;5;241m=\u001b[39m use_rel_pos_bias\n\u001b[0;32m--> 460\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mblocks \u001b[38;5;241m=\u001b[39m nn\u001b[38;5;241m.\u001b[39mModuleList([\n\u001b[1;32m 461\u001b[0m Block(\n\u001b[1;32m 462\u001b[0m dim\u001b[38;5;241m=\u001b[39membed_dim, num_heads\u001b[38;5;241m=\u001b[39mnum_heads, mlp_ratio\u001b[38;5;241m=\u001b[39mmlp_ratio, qkv_bias\u001b[38;5;241m=\u001b[39mqkv_bias, qk_scale\u001b[38;5;241m=\u001b[39mqk_scale,\n\u001b[1;32m 463\u001b[0m drop\u001b[38;5;241m=\u001b[39mdrop_rate, attn_drop\u001b[38;5;241m=\u001b[39mattn_drop_rate, drop_path\u001b[38;5;241m=\u001b[39mdpr[i], norm_layer\u001b[38;5;241m=\u001b[39mnorm_layer,\n\u001b[1;32m 464\u001b[0m init_values\u001b[38;5;241m=\u001b[39minit_values, window_size\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpatch_embed\u001b[38;5;241m.\u001b[39mpatch_shape \u001b[38;5;28;01mif\u001b[39;00m use_rel_pos_bias \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[1;32m 465\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(depth)])\n\u001b[1;32m 467\u001b[0m \u001b[38;5;66;03m# trunc_normal_(self.mask_token, std=.02)\u001b[39;00m\n\u001b[1;32m 469\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m patch_size \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m16\u001b[39m:\n", |
| "File \u001b[0;32m/appuser/app/unilm/dit/ditod/beit.py:461\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 458\u001b[0m dpr \u001b[38;5;241m=\u001b[39m [x\u001b[38;5;241m.\u001b[39mitem() \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mlinspace(\u001b[38;5;241m0\u001b[39m, drop_path_rate, depth)] \u001b[38;5;66;03m# stochastic depth decay rule\u001b[39;00m\n\u001b[1;32m 459\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39muse_rel_pos_bias \u001b[38;5;241m=\u001b[39m use_rel_pos_bias\n\u001b[1;32m 460\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mblocks \u001b[38;5;241m=\u001b[39m nn\u001b[38;5;241m.\u001b[39mModuleList([\n\u001b[0;32m--> 461\u001b[0m \u001b[43mBlock\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 462\u001b[0m \u001b[43m \u001b[49m\u001b[43mdim\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43membed_dim\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnum_heads\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnum_heads\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmlp_ratio\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmlp_ratio\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mqkv_bias\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mqkv_bias\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mqk_scale\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mqk_scale\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 463\u001b[0m \u001b[43m \u001b[49m\u001b[43mdrop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdrop_rate\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mattn_drop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattn_drop_rate\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdrop_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdpr\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnorm_layer\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnorm_layer\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 464\u001b[0m \u001b[43m \u001b[49m\u001b[43minit_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minit_values\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mwindow_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpatch_embed\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpatch_shape\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43muse_rel_pos_bias\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[1;32m 465\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(depth)])\n\u001b[1;32m 467\u001b[0m \u001b[38;5;66;03m# trunc_normal_(self.mask_token, std=.02)\u001b[39;00m\n\u001b[1;32m 469\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m patch_size \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m16\u001b[39m:\n", |
| "File \u001b[0;32m/appuser/app/unilm/dit/ditod/beit.py:223\u001b[0m, in \u001b[0;36mBlock.__init__\u001b[0;34m(self, dim, num_heads, mlp_ratio, qkv_bias, qk_scale, drop, attn_drop, drop_path, init_values, act_layer, norm_layer, window_size, attn_head_dim)\u001b[0m\n\u001b[1;32m 221\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnorm2 \u001b[38;5;241m=\u001b[39m norm_layer(dim)\n\u001b[1;32m 222\u001b[0m mlp_hidden_dim \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mint\u001b[39m(dim \u001b[38;5;241m*\u001b[39m mlp_ratio)\n\u001b[0;32m--> 223\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmlp \u001b[38;5;241m=\u001b[39m \u001b[43mMlp\u001b[49m\u001b[43m(\u001b[49m\u001b[43min_features\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdim\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mhidden_features\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmlp_hidden_dim\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mact_layer\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mact_layer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdrop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdrop\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 225\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m init_values \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 226\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mgamma_1 \u001b[38;5;241m=\u001b[39m nn\u001b[38;5;241m.\u001b[39mParameter(init_values \u001b[38;5;241m*\u001b[39m torch\u001b[38;5;241m.\u001b[39mones((dim)), requires_grad\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n", |
| "File \u001b[0;32m/appuser/app/unilm/dit/ditod/beit.py:65\u001b[0m, in \u001b[0;36mMlp.__init__\u001b[0;34m(self, in_features, hidden_features, out_features, act_layer, drop)\u001b[0m\n\u001b[1;32m 63\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfc1 \u001b[38;5;241m=\u001b[39m nn\u001b[38;5;241m.\u001b[39mLinear(in_features, hidden_features)\n\u001b[1;32m 64\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mact \u001b[38;5;241m=\u001b[39m act_layer()\n\u001b[0;32m---> 65\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfc2 \u001b[38;5;241m=\u001b[39m \u001b[43mnn\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mLinear\u001b[49m\u001b[43m(\u001b[49m\u001b[43mhidden_features\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mout_features\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 66\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdrop \u001b[38;5;241m=\u001b[39m nn\u001b[38;5;241m.\u001b[39mDropout(drop)\n", |
| "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torch/nn/modules/linear.py:101\u001b[0m, in \u001b[0;36mLinear.__init__\u001b[0;34m(self, in_features, out_features, bias, device, dtype)\u001b[0m\n\u001b[1;32m 99\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 100\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mregister_parameter(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mbias\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[0;32m--> 101\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mreset_parameters\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n", |
| "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torch/nn/modules/linear.py:107\u001b[0m, in \u001b[0;36mLinear.reset_parameters\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 103\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mreset_parameters\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 104\u001b[0m \u001b[38;5;66;03m# Setting a=sqrt(5) in kaiming_uniform is the same as initializing with\u001b[39;00m\n\u001b[1;32m 105\u001b[0m \u001b[38;5;66;03m# uniform(-1/sqrt(in_features), 1/sqrt(in_features)). For details, see\u001b[39;00m\n\u001b[1;32m 106\u001b[0m \u001b[38;5;66;03m# https://github.com/pytorch/pytorch/issues/57109\u001b[39;00m\n\u001b[0;32m--> 107\u001b[0m \u001b[43minit\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mkaiming_uniform_\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43ma\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmath\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msqrt\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m5\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 108\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbias \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 109\u001b[0m fan_in, _ \u001b[38;5;241m=\u001b[39m init\u001b[38;5;241m.\u001b[39m_calculate_fan_in_and_fan_out(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mweight)\n", |
| "File \u001b[0;32m~/.local/lib/python3.10/site-packages/torch/nn/init.py:412\u001b[0m, in \u001b[0;36mkaiming_uniform_\u001b[0;34m(tensor, a, mode, nonlinearity)\u001b[0m\n\u001b[1;32m 410\u001b[0m bound \u001b[38;5;241m=\u001b[39m math\u001b[38;5;241m.\u001b[39msqrt(\u001b[38;5;241m3.0\u001b[39m) \u001b[38;5;241m*\u001b[39m std \u001b[38;5;66;03m# Calculate uniform bounds from standard deviation\u001b[39;00m\n\u001b[1;32m 411\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mno_grad():\n\u001b[0;32m--> 412\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mtensor\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43muniform_\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[43mbound\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbound\u001b[49m\u001b[43m)\u001b[49m\n", |
| "\u001b[0;31mKeyboardInterrupt\u001b[0m: " |
| ] |
| } |
| ], |
| "source": [ |
| "from detectron2.engine import DefaultPredictor\n", |
| "\n", |
| "predictor = DefaultPredictor(cfg)" |
| ] |
| } |
| ], |
| "metadata": { |
| "kernelspec": { |
| "display_name": "Python 3", |
| "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": "3.10.6" |
| }, |
| "papermill": { |
| "default_parameters": {}, |
| "duration": 4.258575, |
| "end_time": "2023-06-05T23:35:24.901751", |
| "environment_variables": {}, |
| "exception": null, |
| "input_path": "inference.ipynb", |
| "output_path": "output", |
| "parameters": {}, |
| "start_time": "2023-06-05T23:35:20.643176", |
| "version": "2.4.0" |
| } |
| }, |
| "nbformat": 4, |
| "nbformat_minor": 5 |
| } |
