{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "08fe0c59",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path\n",
    "\n",
    "import torch\n",
    "from timesformer.models.vit import TimeSformer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "10239d32",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_file = Path.home()/'TimeSformer/models/TimeSformer_divST_8x32_224_K600.pyth'\n",
    "model_file.exists()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "652fb03e",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = TimeSformer(img_size=224, num_classes=600, num_frames=8, attention_type='divided_space_time',  pretrained_model=str(model_file))\n",
    "\n",
    "dummy_video = torch.randn(2, 3, 8, 224, 224) # (batch x channels x frames x height x width)\n",
    "\n",
    "pred = model(dummy_video,) # (2, 600)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "83de13c5-791c-4db7-aba4-6d29ce88584e",
   "metadata": {},
   "outputs": [],
   "source": [
    "assert pred.shape == (2,600)"
   ]
  }
 ],
 "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": "3.9.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}