|
|
@@ -0,0 +1,392 @@
|
|
|
+{
|
|
|
+ "cells": [
|
|
|
+ {
|
|
|
+ "cell_type": "markdown",
|
|
|
+ "id": "680ea9da",
|
|
|
+ "metadata": {},
|
|
|
+ "source": [
|
|
|
+ "# Installation\n",
|
|
|
+ "\n",
|
|
|
+ "1. Install miniconda according to the [instructions](https://docs.conda.io/en/latest/miniconda.html) for your OS\n",
|
|
|
+ "\n",
|
|
|
+ "2. Create an environment\n",
|
|
|
+ "```bash\n",
|
|
|
+ "conda create -n myenv python~=3.8.0 matplotlib jupyter opencv\n",
|
|
|
+ "conda activate myenv\n",
|
|
|
+ "```\n",
|
|
|
+ "\n",
|
|
|
+ "3. Install CUDA / cuDNN and required libraries:\n",
|
|
|
+ "```bash\n",
|
|
|
+ "conda install -c conda-forge cudatoolkit~=11.0.0 cudnn~=8.0.0\n",
|
|
|
+ "pip install chainer~=7.0 cupy_cuda110~=7.0 chainercv~=0.13.0\n",
|
|
|
+ "pip install cvmodelz pyaml tabulate tqdm\n",
|
|
|
+ "\n",
|
|
|
+ "```\n"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 1,
|
|
|
+ "id": "fb6020a1",
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "name": "stdout",
|
|
|
+ "output_type": "stream",
|
|
|
+ "text": [
|
|
|
+ "=== Chainer info ===\n",
|
|
|
+ "_will_recompute False\n",
|
|
|
+ "autotune False\n",
|
|
|
+ "compute_mode None\n",
|
|
|
+ "cudnn_deterministic False\n",
|
|
|
+ "cudnn_fast_batch_normalization False\n",
|
|
|
+ "cv_read_image_backend None\n",
|
|
|
+ "cv_resize_backend cv2\n",
|
|
|
+ "cv_rotate_backend None\n",
|
|
|
+ "debug False\n",
|
|
|
+ "dtype float32\n",
|
|
|
+ "enable_backprop True\n",
|
|
|
+ "in_recomputing False\n",
|
|
|
+ "keep_graph_on_report False\n",
|
|
|
+ "lazy_grad_sum False\n",
|
|
|
+ "schedule_func None\n",
|
|
|
+ "train True\n",
|
|
|
+ "type_check True\n",
|
|
|
+ "use_cudnn auto\n",
|
|
|
+ "use_cudnn_tensor_core auto\n",
|
|
|
+ "use_ideep never\n",
|
|
|
+ "use_static_graph True\n",
|
|
|
+ "warn_nondeterministic False\n",
|
|
|
+ "=== CuPy info ===\n",
|
|
|
+ "CuPy Version : 7.8.0\n",
|
|
|
+ "CUDA Root : None\n",
|
|
|
+ "CUDA Build Version : 11000\n",
|
|
|
+ "CUDA Driver Version : 11020\n",
|
|
|
+ "CUDA Runtime Version : 11000\n",
|
|
|
+ "cuBLAS Version : 11200\n",
|
|
|
+ "cuFFT Version : 10201\n",
|
|
|
+ "cuRAND Version : 10201\n",
|
|
|
+ "cuSOLVER Version : (10, 6, 0)\n",
|
|
|
+ "cuSPARSE Version : 11101\n",
|
|
|
+ "NVRTC Version : (11, 0)\n",
|
|
|
+ "cuDNN Build Version : 8002\n",
|
|
|
+ "cuDNN Version : 8005\n",
|
|
|
+ "NCCL Build Version : 2708\n",
|
|
|
+ "NCCL Runtime Version : 2708\n",
|
|
|
+ "CUB Version : Enabled\n",
|
|
|
+ "cuTENSOR Version : None\n"
|
|
|
+ ]
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "import chainer\n",
|
|
|
+ "import cupy\n",
|
|
|
+ "import numpy as np\n",
|
|
|
+ "import pyaml\n",
|
|
|
+ "import cv2\n",
|
|
|
+ "cv2.setNumThreads(0)\n",
|
|
|
+ "\n",
|
|
|
+ "from dataclasses import dataclass\n",
|
|
|
+ "from pathlib import Path\n",
|
|
|
+ "from typing import Callable\n",
|
|
|
+ "from tqdm.auto import tqdm\n",
|
|
|
+ "from imageio import imread\n",
|
|
|
+ "\n",
|
|
|
+ "from chainer import datasets\n",
|
|
|
+ "from chainer import iterators\n",
|
|
|
+ "from chainer.dataset import concat_examples\n",
|
|
|
+ "from chainercv import transforms as tr\n",
|
|
|
+ "from cvmodelz.models import ModelFactory\n",
|
|
|
+ "from cvmodelz.models import BaseModel\n",
|
|
|
+ "\n",
|
|
|
+ "\n",
|
|
|
+ "chainer.config.cv_resize_backend = \"cv2\"\n",
|
|
|
+ "print(\"=== Chainer info ===\")\n",
|
|
|
+ "chainer.config.show()\n",
|
|
|
+ "print(\"=== CuPy info ===\")\n",
|
|
|
+ "cupy.show_config()"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 2,
|
|
|
+ "id": "97b3ca53",
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "@dataclass\n",
|
|
|
+ "class Arguments(object):\n",
|
|
|
+ " \n",
|
|
|
+ " def __str__(self):\n",
|
|
|
+ " return pyaml.dump(dict(Arguments=self.__dict__), sort_dicts=False)\n",
|
|
|
+ " \n",
|
|
|
+ " dataset: str = \"eu_moths\"\n",
|
|
|
+ " weights: str = \"clf_final.npz\"\n",
|
|
|
+ " \n",
|
|
|
+ " split_id: int = 0\n",
|
|
|
+ " \n",
|
|
|
+ " device_id: int = 0\n",
|
|
|
+ " batch_size: int = 32\n",
|
|
|
+ " n_jobs: int = 4\n",
|
|
|
+ " "
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 3,
|
|
|
+ "id": "287b1fa1",
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "class Dataset(chainer.dataset.DatasetMixin):\n",
|
|
|
+ " \n",
|
|
|
+ " def __init__(self, root: str, split_id: int, is_train: bool = True):\n",
|
|
|
+ " super().__init__()\n",
|
|
|
+ " \n",
|
|
|
+ " root = Path(root)\n",
|
|
|
+ " self._root = root\n",
|
|
|
+ " self.class_names = np.loadtxt(root / \"class_names.txt\", dtype=\"U255\")\n",
|
|
|
+ " \n",
|
|
|
+ " _images = np.loadtxt(root / \"images.txt\", dtype=[(\"id\", np.int32), (\"fname\", \"U255\")])\n",
|
|
|
+ " _labels = np.loadtxt(root / \"labels.txt\", dtype=np.int32)\n",
|
|
|
+ " _split_ids = np.loadtxt(root / \"tr_ID.txt\", dtype=np.int32)\n",
|
|
|
+ " \n",
|
|
|
+ " if is_train:\n",
|
|
|
+ " # select all other splits\n",
|
|
|
+ " split_mask = _split_ids != split_id\n",
|
|
|
+ " \n",
|
|
|
+ " else:\n",
|
|
|
+ " # select only images for a given split ID\n",
|
|
|
+ " split_mask = _split_ids == split_id \n",
|
|
|
+ " \n",
|
|
|
+ " self.images = _images[\"fname\"][split_mask]\n",
|
|
|
+ " self.labels = _labels[split_mask]\n",
|
|
|
+ " \n",
|
|
|
+ " \n",
|
|
|
+ " def __len__(self):\n",
|
|
|
+ " return len(self.images)\n",
|
|
|
+ " \n",
|
|
|
+ " def get_example(self, i):\n",
|
|
|
+ " im_path = self._root / \"images\" / self.images[i]\n",
|
|
|
+ " label = self.labels[i]\n",
|
|
|
+ " return imread(im_path, pilmode=\"RGB\"), label\n",
|
|
|
+ "\n",
|
|
|
+ "class DataTransformer(object):\n",
|
|
|
+ " \n",
|
|
|
+ " def __init__(self, prepare: Callable, size: int):\n",
|
|
|
+ " super().__init__()\n",
|
|
|
+ " self.prepare = prepare\n",
|
|
|
+ " self.size = size\n",
|
|
|
+ " \n",
|
|
|
+ " def __call__(self, data):\n",
|
|
|
+ " image, label = data\n",
|
|
|
+ " new_image = self.prepare(image, self.size)\n",
|
|
|
+ " \n",
|
|
|
+ " new_image = tr.center_crop(new_image, size=(self.size, self.size))\n",
|
|
|
+ "\n",
|
|
|
+ " # transform the pixel range from 0..1 to -1..1\n",
|
|
|
+ " new_image = new_image * 2 - 1\n",
|
|
|
+ " return new_image, label"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 4,
|
|
|
+ "id": "6f988e87",
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "def load_model(weights: str):\n",
|
|
|
+ " \n",
|
|
|
+ " model = ModelFactory.new(\"cvmodelz.InceptionV3\", n_classes=200)\n",
|
|
|
+ " model.load(weights, path=\"model/\")\n",
|
|
|
+ " return model\n",
|
|
|
+ "\n",
|
|
|
+ "def load_datasets(root: Path, model_input_size: int, prepare: Callable, split_id: int):\n",
|
|
|
+ " \n",
|
|
|
+ " train_ds = Dataset(root, split_id=split_id, is_train=True)\n",
|
|
|
+ " val_ds = Dataset(root, split_id=split_id, is_train=False)\n",
|
|
|
+ " \n",
|
|
|
+ " transformer = DataTransformer(prepare, model_input_size)\n",
|
|
|
+ " train_ds = datasets.TransformDataset(train_ds, transformer)\n",
|
|
|
+ " val_ds = datasets.TransformDataset(val_ds, transformer)\n",
|
|
|
+ " \n",
|
|
|
+ " return train_ds, val_ds\n",
|
|
|
+ "\n",
|
|
|
+ "def new_iterator(dataset, n_jobs: int = -1, **kwargs):\n",
|
|
|
+ " it_cls = iterators.SerialIterator\n",
|
|
|
+ " \n",
|
|
|
+ " if n_jobs >= 1:\n",
|
|
|
+ " kwargs[\"n_processes\"] = n_jobs\n",
|
|
|
+ " it_cls = iterators.MultiprocessIterator\n",
|
|
|
+ " \n",
|
|
|
+ " return it_cls(dataset, **kwargs)\n",
|
|
|
+ " "
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 5,
|
|
|
+ "id": "6cffafe9",
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "def evaluate(model: chainer.Chain, iterator, device_id: int = -1) -> float:\n",
|
|
|
+ " if device_id >= 0:\n",
|
|
|
+ " device = chainer.backends.cuda.get_device_from_id(device_id)\n",
|
|
|
+ " device.use()\n",
|
|
|
+ " else:\n",
|
|
|
+ " # for CPU mode\n",
|
|
|
+ " device = device_id\n",
|
|
|
+ " \n",
|
|
|
+ " model.to_device(device)\n",
|
|
|
+ " \n",
|
|
|
+ " n_batches = int(np.ceil(len(iterator.dataset) / iterator.batch_size))\n",
|
|
|
+ " \n",
|
|
|
+ " preds = []\n",
|
|
|
+ " labels = []\n",
|
|
|
+ " \n",
|
|
|
+ " iterator.reset()\n",
|
|
|
+ " for batch in tqdm(iterator, total=n_batches):\n",
|
|
|
+ " X, y = concat_examples(batch, device=device)\n",
|
|
|
+ " \n",
|
|
|
+ " # shape is (batch_size, #classes)\n",
|
|
|
+ " logits = model(X)\n",
|
|
|
+ " \n",
|
|
|
+ " logits.to_cpu()\n",
|
|
|
+ "\n",
|
|
|
+ " # get the class ID with the highest score\n",
|
|
|
+ " preds.extend(logits.array.argmax(axis=-1))\n",
|
|
|
+ " labels.extend(chainer.cuda.to_cpu(y))\n",
|
|
|
+ " \n",
|
|
|
+ " return np.mean(np.array(preds) == np.array(labels))\n"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 6,
|
|
|
+ "id": "191b8ce2",
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "def main(args: Arguments):\n",
|
|
|
+ " model = load_model(args.weights)\n",
|
|
|
+ "\n",
|
|
|
+ " print(f\"Created {model.meta.name} model with weights from \\\"{args.weights}\\\"\")\n",
|
|
|
+ "\n",
|
|
|
+ " train_ds, val_ds = load_datasets(args.dataset, model.meta.input_size, model.prepare, split_id=args.split_id)\n",
|
|
|
+ " print(f\"Found {len(train_ds)} training and {len(val_ds)} validation images\")\n",
|
|
|
+ "\n",
|
|
|
+ " val_it = new_iterator(val_ds, \n",
|
|
|
+ " n_jobs=args.n_jobs, \n",
|
|
|
+ " batch_size=args.batch_size,\n",
|
|
|
+ " repeat=False,\n",
|
|
|
+ " shuffle=False\n",
|
|
|
+ " )\n",
|
|
|
+ "\n",
|
|
|
+ " with chainer.using_config(\"train\", False), chainer.no_backprop_mode():\n",
|
|
|
+ " accu = evaluate(model, val_it, device_id=args.device_id)\n",
|
|
|
+ " print(f\"Accuracy: {accu:.2%}\")"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 7,
|
|
|
+ "id": "08b15e42",
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "name": "stdout",
|
|
|
+ "output_type": "stream",
|
|
|
+ "text": [
|
|
|
+ "Arguments:\n",
|
|
|
+ " dataset: data/datasets/eu_moths\n",
|
|
|
+ " weights: data/models/clf_final_2021-03-16-15.12.12.019294678.npz\n",
|
|
|
+ " split_id: 0\n",
|
|
|
+ " device_id: 0\n",
|
|
|
+ " batch_size: 32\n",
|
|
|
+ " n_jobs: 4\n",
|
|
|
+ "\n",
|
|
|
+ "Created InceptionV3 model with weights from \"data/models/clf_final_2021-03-16-15.12.12.019294678.npz\"\n",
|
|
|
+ "Found 1653 training and 552 validation images\n"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "data": {
|
|
|
+ "application/vnd.jupyter.widget-view+json": {
|
|
|
+ "model_id": "d6db493c995e40679bdc1341c8bb1291",
|
|
|
+ "version_major": 2,
|
|
|
+ "version_minor": 0
|
|
|
+ },
|
|
|
+ "text/plain": [
|
|
|
+ " 0%| | 0/18 [00:00<?, ?it/s]"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ "metadata": {},
|
|
|
+ "output_type": "display_data"
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "name": "stderr",
|
|
|
+ "output_type": "stream",
|
|
|
+ "text": [
|
|
|
+ "/home/korsch/.miniconda3/envs/ba_king/lib/python3.8/site-packages/chainer/functions/connection/convolution_2d.py:295: PerformanceWarning: The best algo of conv fwd might not be selected due to lack of workspace size (8388608)\n",
|
|
|
+ " cuda.cudnn.convolution_forward(\n"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "name": "stdout",
|
|
|
+ "output_type": "stream",
|
|
|
+ "text": [
|
|
|
+ "Accuracy: 92.21%\n"
|
|
|
+ ]
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "args = Arguments(\n",
|
|
|
+ " dataset=\"data/eu_moths\",\n",
|
|
|
+ " weights=\"data/clf_final_2021-03-16-15.12.12.019294678.npz\",\n",
|
|
|
+ ")\n",
|
|
|
+ "print(args)\n",
|
|
|
+ "\n",
|
|
|
+ "main(args)"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": null,
|
|
|
+ "id": "08e8f17b",
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": []
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": null,
|
|
|
+ "id": "8bad02a4",
|
|
|
+ "metadata": {},
|
|
|
+ "outputs": [],
|
|
|
+ "source": []
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "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": "3.8.10"
|
|
|
+ }
|
|
|
+ },
|
|
|
+ "nbformat": 4,
|
|
|
+ "nbformat_minor": 5
|
|
|
+}
|
