{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "4764eedc",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/chzhang/anaconda3/envs/ldm/lib/python3.8/site-packages/tqdm/auto.py:22: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "import torch "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "664bf7de",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'1.11.0'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "torch.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "1a845e6b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "torch.cuda.is_available()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "1749f11f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from torchvision import models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "b6fd37e4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_keys(['__name__', '__doc__', '__package__', '__loader__', '__spec__', '__path__', '__file__', '__cached__', '__builtins__', 'alexnet', 'AlexNet', 'convnext', 'ConvNeXt', 'convnext_tiny', 'convnext_small', 'convnext_base', 'convnext_large', 'resnet', 'ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152', 'resnext50_32x4d', 'resnext101_32x8d', 'wide_resnet50_2', 'wide_resnet101_2', 'vgg', 'VGG', 'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn', 'vgg19_bn', 'vgg19', 'squeezenet', 'SqueezeNet', 'squeezenet1_0', 'squeezenet1_1', 'inception', 'Inception3', 'inception_v3', 'InceptionOutputs', '_InceptionOutputs', 'densenet', 'DenseNet', 'densenet121', 'densenet169', 'densenet201', 'densenet161', 'googlenet', 'GoogLeNet', 'GoogLeNetOutputs', '_GoogLeNetOutputs', '_utils', 'mobilenetv2', 'mobilenetv3', 'mobilenet', 'MobileNetV2', 'mobilenet_v2', 'MobileNetV3', 'mobilenet_v3_large', 'mobilenet_v3_small', 'mnasnet', 'MNASNet', 'mnasnet0_5', 'mnasnet0_75', 'mnasnet1_0', 'mnasnet1_3', 'shufflenetv2', 'ShuffleNetV2', 'shufflenet_v2_x0_5', 'shufflenet_v2_x1_0', 'shufflenet_v2_x1_5', 'shufflenet_v2_x2_0', 'efficientnet', 'EfficientNet', 'efficientnet_b0', 'efficientnet_b1', 'efficientnet_b2', 'efficientnet_b3', 'efficientnet_b4', 'efficientnet_b5', 'efficientnet_b6', 'efficientnet_b7', 'regnet', 'RegNet', 'regnet_y_400mf', 'regnet_y_800mf', 'regnet_y_1_6gf', 'regnet_y_3_2gf', 'regnet_y_8gf', 'regnet_y_16gf', 'regnet_y_32gf', 'regnet_y_128gf', 'regnet_x_400mf', 'regnet_x_800mf', 'regnet_x_1_6gf', 'regnet_x_3_2gf', 'regnet_x_8gf', 'regnet_x_16gf', 'regnet_x_32gf', 'vision_transformer', 'VisionTransformer', 'vit_b_16', 'vit_b_32', 'vit_l_16', 'vit_l_32', 'detection', 'feature_extraction', 'optical_flow', 'quantization', 'segmentation', 'video'])"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "models.__dict__.keys()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "aec9cafa",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = models.__dict__['resnet152']()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "29409f63",
   "metadata": {},
   "outputs": [],
   "source": [
    "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "b11e424b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "device(type='cuda')"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "device"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "252ac26f",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = models.__dict__['resnet152']().to(device)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "65262e8e",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}