{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "kernelspec": { "display_name": "pytorch", "language": "python", "name": "pytorch" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.6" }, "colab": { "name": "Mini-batch-logistic-regression-evaluator.ipynb", "provenance": [] }, "accelerator": "GPU", "widgets": { "application/vnd.jupyter.widget-state+json": { "bcf2585d31644e0f86569e604b2e635b": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "state": { "_view_name": "HBoxView", "_dom_classes": [], "_model_name": "HBoxModel", "_view_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_view_count": null, "_view_module_version": "1.5.0", "box_style": "", "layout": "IPY_MODEL_2612abdc916d47418dda7287807a00ce", "_model_module": "@jupyter-widgets/controls", "children": [ "IPY_MODEL_027c3ca8839846fcae9d6bb23fb10399", "IPY_MODEL_1d09572d2433498caa268567c838e640" ] } }, "2612abdc916d47418dda7287807a00ce": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "state": { "_view_name": "LayoutView", "grid_template_rows": null, "right": null, "justify_content": null, "_view_module": "@jupyter-widgets/base", "overflow": null, "_model_module_version": "1.2.0", "_view_count": null, "flex_flow": null, "width": null, "min_width": null, "border": null, "align_items": null, "bottom": null, "_model_module": "@jupyter-widgets/base", "top": null, "grid_column": null, "overflow_y": null, "overflow_x": null, "grid_auto_flow": null, "grid_area": null, "grid_template_columns": null, "flex": null, "_model_name": "LayoutModel", "justify_items": null, "grid_row": null, "max_height": null, "align_content": null, "visibility": null, "align_self": null, "height": null, "min_height": null, "padding": null, "grid_auto_rows": null, "grid_gap": null, "max_width": null, "order": null, "_view_module_version": "1.2.0", "grid_template_areas": null, "object_position": null, "object_fit": null, "grid_auto_columns": null, "margin": null, "display": null, "left": null } }, "027c3ca8839846fcae9d6bb23fb10399": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "state": { "_view_name": "ProgressView", "style": "IPY_MODEL_08cddf6f231a4e89ab8e1e026cf11796", "_dom_classes": [], "description": "", "_model_name": "FloatProgressModel", "bar_style": "info", "max": 1, "_view_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "value": 1, "_view_count": null, "_view_module_version": "1.5.0", "orientation": "horizontal", "min": 0, "description_tooltip": null, "_model_module": "@jupyter-widgets/controls", "layout": "IPY_MODEL_75267826defa4565be4bed232272434e" } }, "1d09572d2433498caa268567c838e640": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "state": { "_view_name": "HTMLView", "style": "IPY_MODEL_8c189a0cd687479dba885a9c2d47fb64", "_dom_classes": [], "description": "", "_model_name": "HTMLModel", "placeholder": "​", "_view_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "value": " 2640404480/? [01:10<00:00, 98486594.59it/s]", "_view_count": null, "_view_module_version": "1.5.0", "description_tooltip": null, "_model_module": "@jupyter-widgets/controls", "layout": "IPY_MODEL_b6528931de654b3c85b94bec14f4891b" } }, "08cddf6f231a4e89ab8e1e026cf11796": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "state": { "_view_name": "StyleView", "_model_name": "ProgressStyleModel", "description_width": "initial", "_view_module": "@jupyter-widgets/base", "_model_module_version": "1.5.0", "_view_count": null, "_view_module_version": "1.2.0", "bar_color": null, "_model_module": "@jupyter-widgets/controls" } }, "75267826defa4565be4bed232272434e": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "state": { "_view_name": "LayoutView", "grid_template_rows": null, "right": null, "justify_content": null, "_view_module": "@jupyter-widgets/base", "overflow": null, "_model_module_version": "1.2.0", "_view_count": null, "flex_flow": null, "width": null, "min_width": null, "border": null, "align_items": null, "bottom": null, "_model_module": "@jupyter-widgets/base", "top": null, "grid_column": null, "overflow_y": null, "overflow_x": null, "grid_auto_flow": null, "grid_area": null, "grid_template_columns": null, "flex": null, "_model_name": "LayoutModel", "justify_items": null, "grid_row": null, "max_height": null, "align_content": null, "visibility": null, "align_self": null, "height": null, "min_height": null, "padding": null, "grid_auto_rows": null, "grid_gap": null, "max_width": null, "order": null, "_view_module_version": "1.2.0", "grid_template_areas": null, "object_position": null, "object_fit": null, "grid_auto_columns": null, "margin": null, "display": null, "left": null } }, "8c189a0cd687479dba885a9c2d47fb64": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "state": { "_view_name": "StyleView", "_model_name": "DescriptionStyleModel", "description_width": "", "_view_module": "@jupyter-widgets/base", "_model_module_version": "1.5.0", "_view_count": null, "_view_module_version": "1.2.0", "_model_module": "@jupyter-widgets/controls" } }, "b6528931de654b3c85b94bec14f4891b": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "state": { "_view_name": "LayoutView", "grid_template_rows": null, "right": null, "justify_content": null, "_view_module": "@jupyter-widgets/base", "overflow": null, "_model_module_version": "1.2.0", "_view_count": null, "flex_flow": null, "width": null, "min_width": null, "border": null, "align_items": null, "bottom": null, "_model_module": "@jupyter-widgets/base", "top": null, "grid_column": null, "overflow_y": null, "overflow_x": null, "grid_auto_flow": null, "grid_area": null, "grid_template_columns": null, "flex": null, "_model_name": "LayoutModel", "justify_items": null, "grid_row": null, "max_height": null, "align_content": null, "visibility": null, "align_self": null, "height": null, "min_height": null, "padding": null, "grid_auto_rows": null, "grid_gap": null, "max_width": null, "order": null, "_view_module_version": "1.2.0", "grid_template_areas": null, "object_position": null, "object_fit": null, "grid_auto_columns": null, "margin": null, "display": null, "left": null } } } } }, "cells": [ { "cell_type": "code", "metadata": { "id": "YUemQib7ZE4D" }, "source": [ "import torch\n", "import sys\n", "import numpy as np\n", "import os\n", "from sklearn.neighbors import KNeighborsClassifier\n", "import yaml\n", "import matplotlib.pyplot as plt\n", "from sklearn.decomposition import PCA\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn import preprocessing\n", "import importlib.util\n", "import torchvision" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "WSgRE1CcLqdS", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "e44ac358-6480-4a5f-a358-6eb6ace26c8b" }, "source": [ "!pip install gdown" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "Requirement already satisfied: gdown in /usr/local/lib/python3.6/dist-packages (3.6.4)\n", "Requirement already satisfied: six in /usr/local/lib/python3.6/dist-packages (from gdown) (1.15.0)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.6/dist-packages (from gdown) (2.23.0)\n", "Requirement already satisfied: tqdm in /usr/local/lib/python3.6/dist-packages (from gdown) (4.41.1)\n", "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests->gdown) (1.24.3)\n", "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests->gdown) (3.0.4)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests->gdown) (2020.12.5)\n", "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests->gdown) (2.10)\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "id": "NOIJEui1ZziV" }, "source": [ "def get_file_id_by_model(folder_name):\n", " file_id = {'resnet18_100-epochs_stl10': '14_nH2FkyKbt61cieQDiSbBVNP8-gtwgF',\n", " 'resnet18_100-epochs_cifar10': '1lc2aoVtrAetGn0PnTkOyFzPCIucOJq7C'}\n", " return file_id.get(folder_name, \"Model not found.\")" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "G7YMxsvEZMrX", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "36932a7d-c7e5-492a-f37d-8be6b18f787a" }, "source": [ "folder_name = 'resnet18_100-epochs_stl10'\n", "file_id = get_file_id_by_model(folder_name)\n", "print(folder_name, file_id)" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "resnet18_100-epochs_stl10 14_nH2FkyKbt61cieQDiSbBVNP8-gtwgF\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "id": "PWZ8fet_YoJm", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "8d52756d-707b-4a3f-9e8c-0d191408deab" }, "source": [ "# download and extract model files\n", "os.system('gdown https://drive.google.com/uc?id={}'.format(file_id))\n", "os.system('unzip {}'.format(folder_name))\n", "!ls" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "checkpoint_0100.pth.tar\n", "config.yml\n", "events.out.tfevents.1610901470.4cb2c837708d.2683858.0\n", "resnet18_100-epochs_stl10.zip\n", "sample_data\n", "training.log\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "id": "ooyhd8piZ1w1", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "6ffb73aa-35c5-4df2-bd1f-6de6a235a9e5" }, "source": [ "!unzip resnet18_100-epochs_stl10" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "Archive: resnet18_100-epochs_stl10.zip\n", "replace checkpoint_0100.pth.tar? [y]es, [n]o, [A]ll, [N]one, [r]ename: A\n", " inflating: checkpoint_0100.pth.tar \n", " inflating: config.yml \n", " inflating: events.out.tfevents.1610901470.4cb2c837708d.2683858.0 \n", " inflating: training.log \n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "id": "3_nypQVEv-hn" }, "source": [ "from torch.utils.data import DataLoader\n", "import torchvision.transforms as transforms\n", "from torchvision import datasets" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "lDfbL3w_Z0Od", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "5f58bd9b-4428-4b8c-e271-b47ca6694f34" }, "source": [ "device = 'cuda' if torch.cuda.is_available() else 'cpu'\n", "print(\"Using device:\", device)" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "Using device: cuda\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "id": "BfIPl0G6_RrT" }, "source": [ "def get_stl10_data_loaders(download, shuffle=False, batch_size=128):\n", " train_dataset = datasets.STL10('./data', split='train', download=download,\n", " transform=transforms.ToTensor())\n", "\n", " train_loader = DataLoader(train_dataset, batch_size=batch_size,\n", " num_workers=0, drop_last=False, shuffle=shuffle)\n", " \n", " test_dataset = datasets.STL10('./data', split='test', download=download,\n", " transform=transforms.ToTensor())\n", "\n", " test_loader = DataLoader(test_dataset, batch_size=2*batch_size,\n", " num_workers=10, drop_last=False, shuffle=shuffle)\n", " return train_loader, test_loader\n", "\n", "def get_cifar10_data_loaders(download, shuffle=False, batch_size=128):\n", " train_dataset = datasets.CIFAR10('./data', train=True, download=download,\n", " transform=transforms.ToTensor())\n", "\n", " train_loader = DataLoader(train_dataset, batch_size=batch_size,\n", " num_workers=0, drop_last=False, shuffle=shuffle)\n", " \n", " test_dataset = datasets.CIFAR10('./data', train=False, download=download,\n", " transform=transforms.ToTensor())\n", "\n", " test_loader = DataLoader(test_dataset, batch_size=2*batch_size,\n", " num_workers=10, drop_last=False, shuffle=shuffle)\n", " return train_loader, test_loader" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "6N8lYkbmDTaK" }, "source": [ "with open(os.path.join('./config.yml')) as file:\n", " config = yaml.load(file)" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "a18lPD-tIle6" }, "source": [ "if config.arch == 'resnet18':\n", " model = torchvision.models.resnet18(pretrained=False, num_classes=10).to(device)\n", "elif config.arch == 'resnet50':\n", " model = torchvision.models.resnet50(pretrained=False, num_classes=10).to(device)" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "4AIfgq41GuTT" }, "source": [ "checkpoint = torch.load('checkpoint_0100.pth.tar', map_location=device)\n", "state_dict = checkpoint['state_dict']\n", "\n", "for k in list(state_dict.keys()):\n", "\n", " if k.startswith('backbone.'):\n", " if k.startswith('backbone') and not k.startswith('backbone.fc'):\n", " # remove prefix\n", " state_dict[k[len(\"backbone.\"):]] = state_dict[k]\n", " del state_dict[k]" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "VVjA83PPJYWl" }, "source": [ "log = model.load_state_dict(state_dict, strict=False)\n", "assert log.missing_keys == ['fc.weight', 'fc.bias']" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "_GC0a14uWRr6", "colab": { "base_uri": "https://localhost:8080/", "height": 117, "referenced_widgets": [ "bcf2585d31644e0f86569e604b2e635b", "2612abdc916d47418dda7287807a00ce", "027c3ca8839846fcae9d6bb23fb10399", "1d09572d2433498caa268567c838e640", "08cddf6f231a4e89ab8e1e026cf11796", "75267826defa4565be4bed232272434e", "8c189a0cd687479dba885a9c2d47fb64", "b6528931de654b3c85b94bec14f4891b" ] }, "outputId": "56db3fac-10cc-4985-932d-878375ccd18f" }, "source": [ "if config.dataset_name == 'cifar10':\n", " train_loader, test_loader = get_cifar10_data_loaders(download=True)\n", "elif config.dataset_name == 'stl10':\n", " train_loader, test_loader = get_stl10_data_loaders(download=True)\n", "print(\"Dataset:\", config.dataset_name)" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "Downloading http://ai.stanford.edu/~acoates/stl10/stl10_binary.tar.gz to ./data/stl10_binary.tar.gz\n" ], "name": "stdout" }, { "output_type": "display_data", "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "bcf2585d31644e0f86569e604b2e635b", "version_minor": 0, "version_major": 2 }, "text/plain": [ "HBox(children=(FloatProgress(value=1.0, bar_style='info', max=1.0), HTML(value='')))" ] }, "metadata": { "tags": [] } }, { "output_type": "stream", "text": [ "Extracting ./data/stl10_binary.tar.gz to ./data\n", "Files already downloaded and verified\n", "Dataset: stl10\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "id": "pYT_KsM0Mnnr" }, "source": [ "# freeze all layers but the last fc\n", "for name, param in model.named_parameters():\n", " if name not in ['fc.weight', 'fc.bias']:\n", " param.requires_grad = False\n", "\n", "parameters = list(filter(lambda p: p.requires_grad, model.parameters()))\n", "assert len(parameters) == 2 # fc.weight, fc.bias" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "aPVh1S_eMRDU" }, "source": [ "optimizer = torch.optim.Adam(model.parameters(), lr=3e-4, weight_decay=0.0008)\n", "criterion = torch.nn.CrossEntropyLoss().to(device)" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "edr6RhP2PdVq" }, "source": [ "def accuracy(output, target, topk=(1,)):\n", " \"\"\"Computes the accuracy over the k top predictions for the specified values of k\"\"\"\n", " with torch.no_grad():\n", " maxk = max(topk)\n", " batch_size = target.size(0)\n", "\n", " _, pred = output.topk(maxk, 1, True, True)\n", " pred = pred.t()\n", " correct = pred.eq(target.view(1, -1).expand_as(pred))\n", "\n", " res = []\n", " for k in topk:\n", " correct_k = correct[:k].reshape(-1).float().sum(0, keepdim=True)\n", " res.append(correct_k.mul_(100.0 / batch_size))\n", " return res" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "qOder0dAMI7X", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "95b285c8-2b26-4d2c-ccc3-bb9111871c8d" }, "source": [ "epochs = 100\n", "for epoch in range(epochs):\n", " top1_train_accuracy = 0\n", " for counter, (x_batch, y_batch) in enumerate(train_loader):\n", " x_batch = x_batch.to(device)\n", " y_batch = y_batch.to(device)\n", "\n", " logits = model(x_batch)\n", " loss = criterion(logits, y_batch)\n", " top1 = accuracy(logits, y_batch, topk=(1,))\n", " top1_train_accuracy += top1[0]\n", "\n", " optimizer.zero_grad()\n", " loss.backward()\n", " optimizer.step()\n", "\n", " top1_train_accuracy /= (counter + 1)\n", " top1_accuracy = 0\n", " top5_accuracy = 0\n", " for counter, (x_batch, y_batch) in enumerate(test_loader):\n", " x_batch = x_batch.to(device)\n", " y_batch = y_batch.to(device)\n", "\n", " logits = model(x_batch)\n", " \n", " top1, top5 = accuracy(logits, y_batch, topk=(1,5))\n", " top1_accuracy += top1[0]\n", " top5_accuracy += top5[0]\n", " \n", " top1_accuracy /= (counter + 1)\n", " top5_accuracy /= (counter + 1)\n", " print(f\"Epoch {epoch}\\tTop1 Train accuracy {top1_train_accuracy.item()}\\tTop1 Test accuracy: {top1_accuracy.item()}\\tTop5 test acc: {top5_accuracy.item()}\")" ], "execution_count": null, "outputs": [ { "output_type": "stream", "text": [ "Top1 Train accuracy 29.47265625\tTop1 Test accuracy: 42.4560546875\tTop5 test acc: 92.41943359375\n", "Top1 Train accuracy 49.47265625\tTop1 Test accuracy: 53.662109375\tTop5 test acc: 96.15478515625\n", "Top1 Train accuracy 56.85546875\tTop1 Test accuracy: 57.92236328125\tTop5 test acc: 96.74072265625\n", "Top1 Train accuracy 59.3359375\tTop1 Test accuracy: 59.9365234375\tTop5 test acc: 97.021484375\n", "Top1 Train accuracy 60.8984375\tTop1 Test accuracy: 61.1572265625\tTop5 test acc: 97.15576171875\n", "Top1 Train accuracy 61.89453125\tTop1 Test accuracy: 61.8408203125\tTop5 test acc: 97.2900390625\n", "Top1 Train accuracy 62.48046875\tTop1 Test accuracy: 62.5244140625\tTop5 test acc: 97.3388671875\n", "Top1 Train accuracy 63.125\tTop1 Test accuracy: 63.037109375\tTop5 test acc: 97.44873046875\n", "Top1 Train accuracy 64.4140625\tTop1 Test accuracy: 63.39111328125\tTop5 test acc: 97.54638671875\n", "Top1 Train accuracy 64.86328125\tTop1 Test accuracy: 63.85498046875\tTop5 test acc: 97.5830078125\n", "Top1 Train accuracy 65.15625\tTop1 Test accuracy: 64.0869140625\tTop5 test acc: 97.65625\n", "Top1 Train accuracy 65.56640625\tTop1 Test accuracy: 64.34326171875\tTop5 test acc: 97.69287109375\n", "Top1 Train accuracy 65.859375\tTop1 Test accuracy: 64.48974609375\tTop5 test acc: 97.7294921875\n", "Top1 Train accuracy 66.03515625\tTop1 Test accuracy: 64.83154296875\tTop5 test acc: 97.75390625\n", "Top1 Train accuracy 66.171875\tTop1 Test accuracy: 65.02685546875\tTop5 test acc: 97.79052734375\n", "Top1 Train accuracy 66.484375\tTop1 Test accuracy: 65.46630859375\tTop5 test acc: 97.7783203125\n", "Top1 Train accuracy 66.953125\tTop1 Test accuracy: 65.66162109375\tTop5 test acc: 97.8515625\n", "Top1 Train accuracy 67.2265625\tTop1 Test accuracy: 65.91796875\tTop5 test acc: 97.93701171875\n", "Top1 Train accuracy 67.48046875\tTop1 Test accuracy: 65.97900390625\tTop5 test acc: 97.91259765625\n", "Top1 Train accuracy 67.8125\tTop1 Test accuracy: 66.11328125\tTop5 test acc: 97.93701171875\n", "Top1 Train accuracy 68.046875\tTop1 Test accuracy: 66.3330078125\tTop5 test acc: 97.9736328125\n", "Top1 Train accuracy 68.45703125\tTop1 Test accuracy: 66.5283203125\tTop5 test acc: 97.94921875\n", "Top1 Train accuracy 68.59375\tTop1 Test accuracy: 66.63818359375\tTop5 test acc: 97.94921875\n", "Top1 Train accuracy 68.7890625\tTop1 Test accuracy: 66.748046875\tTop5 test acc: 97.93701171875\n", "Top1 Train accuracy 69.00390625\tTop1 Test accuracy: 66.90673828125\tTop5 test acc: 97.9248046875\n", "Top1 Train accuracy 69.21875\tTop1 Test accuracy: 67.0654296875\tTop5 test acc: 97.9736328125\n", "Top1 Train accuracy 69.35546875\tTop1 Test accuracy: 67.0654296875\tTop5 test acc: 97.9736328125\n", "Top1 Train accuracy 69.66796875\tTop1 Test accuracy: 67.2119140625\tTop5 test acc: 97.93701171875\n", "Top1 Train accuracy 69.765625\tTop1 Test accuracy: 67.24853515625\tTop5 test acc: 97.9736328125\n", "Top1 Train accuracy 69.82421875\tTop1 Test accuracy: 67.4072265625\tTop5 test acc: 97.98583984375\n", "Top1 Train accuracy 69.9609375\tTop1 Test accuracy: 67.431640625\tTop5 test acc: 97.98583984375\n", "Top1 Train accuracy 70.09765625\tTop1 Test accuracy: 67.4560546875\tTop5 test acc: 97.998046875\n", "Top1 Train accuracy 70.15625\tTop1 Test accuracy: 67.44384765625\tTop5 test acc: 98.01025390625\n", "Top1 Train accuracy 70.29296875\tTop1 Test accuracy: 67.54150390625\tTop5 test acc: 98.0224609375\n", "Top1 Train accuracy 70.41015625\tTop1 Test accuracy: 67.61474609375\tTop5 test acc: 98.05908203125\n", "Top1 Train accuracy 70.5078125\tTop1 Test accuracy: 67.67578125\tTop5 test acc: 98.0712890625\n", "Top1 Train accuracy 70.64453125\tTop1 Test accuracy: 67.73681640625\tTop5 test acc: 98.08349609375\n", "Top1 Train accuracy 70.859375\tTop1 Test accuracy: 67.76123046875\tTop5 test acc: 98.0712890625\n", "Top1 Train accuracy 70.8984375\tTop1 Test accuracy: 67.88330078125\tTop5 test acc: 98.08349609375\n", "Top1 Train accuracy 71.07421875\tTop1 Test accuracy: 67.95654296875\tTop5 test acc: 98.095703125\n", "Top1 Train accuracy 71.11328125\tTop1 Test accuracy: 67.93212890625\tTop5 test acc: 98.1201171875\n", "Top1 Train accuracy 71.2890625\tTop1 Test accuracy: 68.0419921875\tTop5 test acc: 98.10791015625\n", "Top1 Train accuracy 71.3671875\tTop1 Test accuracy: 68.10302734375\tTop5 test acc: 98.13232421875\n", "Top1 Train accuracy 71.42578125\tTop1 Test accuracy: 68.1396484375\tTop5 test acc: 98.13232421875\n", "Top1 Train accuracy 71.4453125\tTop1 Test accuracy: 68.1396484375\tTop5 test acc: 98.13232421875\n", "Top1 Train accuracy 71.50390625\tTop1 Test accuracy: 68.1640625\tTop5 test acc: 98.1201171875\n", "Top1 Train accuracy 71.484375\tTop1 Test accuracy: 68.2373046875\tTop5 test acc: 98.14453125\n", "Top1 Train accuracy 71.6015625\tTop1 Test accuracy: 68.34716796875\tTop5 test acc: 98.15673828125\n", "Top1 Train accuracy 71.7578125\tTop1 Test accuracy: 68.39599609375\tTop5 test acc: 98.15673828125\n", "Top1 Train accuracy 71.89453125\tTop1 Test accuracy: 68.37158203125\tTop5 test acc: 98.20556640625\n", "Top1 Train accuracy 72.01171875\tTop1 Test accuracy: 68.4326171875\tTop5 test acc: 98.20556640625\n", "Top1 Train accuracy 72.1484375\tTop1 Test accuracy: 68.44482421875\tTop5 test acc: 98.2177734375\n", "Top1 Train accuracy 72.1875\tTop1 Test accuracy: 68.51806640625\tTop5 test acc: 98.25439453125\n", "Top1 Train accuracy 72.28515625\tTop1 Test accuracy: 68.603515625\tTop5 test acc: 98.2421875\n", "Top1 Train accuracy 72.36328125\tTop1 Test accuracy: 68.5791015625\tTop5 test acc: 98.2666015625\n", "Top1 Train accuracy 72.5390625\tTop1 Test accuracy: 68.61572265625\tTop5 test acc: 98.2666015625\n", "Top1 Train accuracy 72.59765625\tTop1 Test accuracy: 68.64013671875\tTop5 test acc: 98.2666015625\n", "Top1 Train accuracy 73.02734375\tTop1 Test accuracy: 68.7255859375\tTop5 test acc: 98.25439453125\n", "Top1 Train accuracy 73.18359375\tTop1 Test accuracy: 68.76220703125\tTop5 test acc: 98.2666015625\n", "Top1 Train accuracy 73.26171875\tTop1 Test accuracy: 68.8232421875\tTop5 test acc: 98.291015625\n", "Top1 Train accuracy 73.359375\tTop1 Test accuracy: 68.85986328125\tTop5 test acc: 98.27880859375\n", "Top1 Train accuracy 73.45703125\tTop1 Test accuracy: 68.8720703125\tTop5 test acc: 98.32763671875\n", "Top1 Train accuracy 73.49609375\tTop1 Test accuracy: 68.9208984375\tTop5 test acc: 98.33984375\n", "Top1 Train accuracy 73.53515625\tTop1 Test accuracy: 68.8720703125\tTop5 test acc: 98.33984375\n", "Top1 Train accuracy 73.53515625\tTop1 Test accuracy: 68.9208984375\tTop5 test acc: 98.3642578125\n", "Top1 Train accuracy 73.65234375\tTop1 Test accuracy: 69.00634765625\tTop5 test acc: 98.33984375\n", "Top1 Train accuracy 73.76953125\tTop1 Test accuracy: 69.0185546875\tTop5 test acc: 98.33984375\n", "Top1 Train accuracy 73.9453125\tTop1 Test accuracy: 69.0673828125\tTop5 test acc: 98.35205078125\n", "Top1 Train accuracy 74.00390625\tTop1 Test accuracy: 69.1162109375\tTop5 test acc: 98.35205078125\n", "Top1 Train accuracy 74.0625\tTop1 Test accuracy: 69.140625\tTop5 test acc: 98.3642578125\n", "Top1 Train accuracy 74.12109375\tTop1 Test accuracy: 69.17724609375\tTop5 test acc: 98.3642578125\n", "Top1 Train accuracy 74.21875\tTop1 Test accuracy: 69.20166015625\tTop5 test acc: 98.35205078125\n", "Top1 Train accuracy 74.21875\tTop1 Test accuracy: 69.2626953125\tTop5 test acc: 98.33984375\n", "Top1 Train accuracy 74.23828125\tTop1 Test accuracy: 69.3359375\tTop5 test acc: 98.33984375\n", "Top1 Train accuracy 74.23828125\tTop1 Test accuracy: 69.37255859375\tTop5 test acc: 98.3154296875\n", "Top1 Train accuracy 74.2578125\tTop1 Test accuracy: 69.42138671875\tTop5 test acc: 98.3154296875\n", "Top1 Train accuracy 74.27734375\tTop1 Test accuracy: 69.482421875\tTop5 test acc: 98.3154296875\n", "Top1 Train accuracy 74.375\tTop1 Test accuracy: 69.51904296875\tTop5 test acc: 98.30322265625\n", "Top1 Train accuracy 74.39453125\tTop1 Test accuracy: 69.6044921875\tTop5 test acc: 98.30322265625\n", "Top1 Train accuracy 74.43359375\tTop1 Test accuracy: 69.6044921875\tTop5 test acc: 98.30322265625\n", "Top1 Train accuracy 74.43359375\tTop1 Test accuracy: 69.6044921875\tTop5 test acc: 98.30322265625\n", "Top1 Train accuracy 74.4921875\tTop1 Test accuracy: 69.64111328125\tTop5 test acc: 98.3154296875\n", "Top1 Train accuracy 74.5703125\tTop1 Test accuracy: 69.7021484375\tTop5 test acc: 98.3154296875\n", "Top1 Train accuracy 74.66796875\tTop1 Test accuracy: 69.775390625\tTop5 test acc: 98.3154296875\n", "Top1 Train accuracy 74.6875\tTop1 Test accuracy: 69.775390625\tTop5 test acc: 98.3154296875\n", "Top1 Train accuracy 74.74609375\tTop1 Test accuracy: 69.76318359375\tTop5 test acc: 98.30322265625\n", "Top1 Train accuracy 74.74609375\tTop1 Test accuracy: 69.78759765625\tTop5 test acc: 98.30322265625\n", "Top1 Train accuracy 74.84375\tTop1 Test accuracy: 69.81201171875\tTop5 test acc: 98.3154296875\n", "Top1 Train accuracy 74.94140625\tTop1 Test accuracy: 69.88525390625\tTop5 test acc: 98.32763671875\n", "Top1 Train accuracy 75.0390625\tTop1 Test accuracy: 69.8974609375\tTop5 test acc: 98.32763671875\n", "Top1 Train accuracy 75.05859375\tTop1 Test accuracy: 69.921875\tTop5 test acc: 98.3154296875\n", "Top1 Train accuracy 75.078125\tTop1 Test accuracy: 69.95849609375\tTop5 test acc: 98.30322265625\n", "Top1 Train accuracy 75.15625\tTop1 Test accuracy: 69.921875\tTop5 test acc: 98.30322265625\n", "Top1 Train accuracy 75.21484375\tTop1 Test accuracy: 69.9462890625\tTop5 test acc: 98.30322265625\n", "Top1 Train accuracy 75.17578125\tTop1 Test accuracy: 69.93408203125\tTop5 test acc: 98.30322265625\n", "Top1 Train accuracy 75.17578125\tTop1 Test accuracy: 69.98291015625\tTop5 test acc: 98.291015625\n", "Top1 Train accuracy 75.234375\tTop1 Test accuracy: 69.95849609375\tTop5 test acc: 98.3154296875\n", "Top1 Train accuracy 75.234375\tTop1 Test accuracy: 69.98291015625\tTop5 test acc: 98.3154296875\n", "Top1 Train accuracy 75.2734375\tTop1 Test accuracy: 70.00732421875\tTop5 test acc: 98.3154296875\n", "Top1 Train accuracy 75.37109375\tTop1 Test accuracy: 70.01953125\tTop5 test acc: 98.3154296875\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "id": "dtYqHZirMNZk" }, "source": [ "" ], "execution_count": null, "outputs": [] } ] }