Colab

CS7643Sum21ProjTeam59.ipynb

@@ -0,0 +1 @@
+{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"CS7643Sum21ProjTeam59.ipynb","provenance":[],"collapsed_sections":["mCxFIVoQuDZQ"]},"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":"3.8.5"}},"cells":[{"cell_type":"markdown","metadata":{"id":"WkxIUDpV5CGh"},"source":["### The typical starting cell for a colab notebook"]},{"cell_type":"markdown","metadata":{"id":"RUkK19pL5fM8"},"source":["Run cell (Shift+Enter), click link, sign into Google account (or grant access), copy access code to clipboard, paste (Ctrl+V) into box below, and press Enter"]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"7OmNlqc1n2Jv","executionInfo":{"status":"ok","timestamp":1626907755278,"user_tz":240,"elapsed":34150,"user":{"displayName":"Rick Feinleib","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GjoqYHQlggzOnw7kbmibkVT3DL6W7pv4Ot4VJKd=s64","userId":"17023243058419009217"}},"outputId":"a3ddf84c-f97d-4476-b8cf-6e1ab0936895"},"source":["from google.colab import drive\n","drive.mount('/content/drive')"],"execution_count":null,"outputs":[{"output_type":"stream","text":["Mounted at /content/drive\n"],"name":"stdout"}]},{"cell_type":"markdown","metadata":{"id":"mCxFIVoQuDZQ"},"source":["#### Use the following cells for first time setup"]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"ZnX1aeNg_kOw","executionInfo":{"status":"ok","timestamp":1626916183839,"user_tz":240,"elapsed":191,"user":{"displayName":"Rick Feinleib","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GjoqYHQlggzOnw7kbmibkVT3DL6W7pv4Ot4VJKd=s64","userId":"17023243058419009217"}},"outputId":"84ac7048-6dc0-4ae7-cc5c-13d48706f89b"},"source":["%cd '/content/drive/MyDrive'"],"execution_count":25,"outputs":[{"output_type":"stream","text":["/content/drive/MyDrive\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"Uc6C2Mz7WXd1"},"source":["usr = 'rfeinleib3'\n","p = 'xxxxx'"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"RHepLguDAQL_"},"source":["!git clone https://{usr}:{p}@github.com/GaTechTeam59/representation-flow-cvpr19.git"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"H48hT44Unrhn","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1626912787193,"user_tz":240,"elapsed":613,"user":{"displayName":"Rick Feinleib","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GjoqYHQlggzOnw7kbmibkVT3DL6W7pv4Ot4VJKd=s64","userId":"17023243058419009217"}},"outputId":"f7a7e5e1-b20f-40a6-e987-2502b6618ad3"},"source":["!pwd"],"execution_count":null,"outputs":[{"output_type":"stream","text":["/content/drive/My Drive\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"p38K8YZOfqf8"},"source":["%cd 'representation-flow-cvpr19'"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"LIy3t3a1qMUq"},"source":["# This cell from https://programmersought.com/article/80741316664/\n","!git clone https://github.com/dukebw/lintel.git\n","%cd lintel\n","!python setup.py build\n","!python setup.py install"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"Zy7ob1t5yx1J","executionInfo":{"status":"ok","timestamp":1626917724950,"user_tz":240,"elapsed":630,"user":{"displayName":"Rick Feinleib","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GjoqYHQlggzOnw7kbmibkVT3DL6W7pv4Ot4VJKd=s64","userId":"17023243058419009217"}}},"source":["# This code downloads a small mp4 file from the web. No idea if this really is working\n","import requests\n","file_url = \"https://file-examples-com.github.io/uploads/2017/04/file_example_MP4_480_1_5MG.mp4\"\n","\n","r = requests.get(file_url, stream=True)\n","\n","with open(\"/content/drive/My Drive/representation-flow-cvpr19/data/sample.mp4\", \"wb\") as file:\n","  for blk in r.iter_content(chunk_size=1024):\n","    if blk:\n","      file.write(blk)"],"execution_count":33,"outputs":[]},{"cell_type":"code","metadata":{"id":"WIGP7VfszqFU"},"source":["# if not in lintel dir, then run: %cd lintel"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"yHWE8_4QkR_Y"},"source":["!lintel_test --filename ../data/sample.mp4 --width 480 --height 270"],"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"CpjEZ08tuU8_"},"source":["#### Need to run this cell to start using the Notebook"]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"YwO-IKiltc8S","executionInfo":{"status":"ok","timestamp":1626915828690,"user_tz":240,"elapsed":218,"user":{"displayName":"Rick Feinleib","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GjoqYHQlggzOnw7kbmibkVT3DL6W7pv4Ot4VJKd=s64","userId":"17023243058419009217"}},"outputId":"c0c2f77c-08b4-49f1-d6c3-92bb41899fac"},"source":["%cd '/content/drive/MyDrive/representation-flow-cvpr19'"],"execution_count":null,"outputs":[{"output_type":"stream","text":["/content/drive/MyDrive/representation-flow-cvpr19\n"],"name":"stdout"}]},{"cell_type":"markdown","metadata":{"id":"phla7FIdbC4C"},"source":["## Start code here"]},{"cell_type":"code","metadata":{"id":"OIjY-l7KbI4e"},"source":["import torch\n","from train_model_class import Model\n","\n","# for auto-reloading external modules\n","# see http://stackoverflow.com/questions/1907993/autoreload-of-modules-in-ipython\n","%load_ext autoreload\n","%autoreload 2"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"eiV_KQz7nsL3","tags":[],"executionInfo":{"status":"ok","timestamp":1626915838786,"user_tz":240,"elapsed":469,"user":{"displayName":"Rick Feinleib","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GjoqYHQlggzOnw7kbmibkVT3DL6W7pv4Ot4VJKd=s64","userId":"17023243058419009217"}},"outputId":"6d7f63a8-be83-4bc2-ac6a-1adf47dba0f0"},"source":["# Check device availability\n","device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n","print(\"You are using device: %s\" % device)"],"execution_count":null,"outputs":[{"output_type":"stream","text":["You are using device: cpu\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"JbDFZI6GjZFc"},"source":["class Args:\n","  def __init__(self, mode: str='rgb', exp_name: str=\"hmdb-test\", batch_size: int=32, length: int=32, \n","               learnable: str=\"[0,1,1,1,1]\", niter: int=20, system: str=\"hmdb\", model: str=\"3d\"):\n","    self.mode = mode\n","    self.exp_name = exp_name\n","    self.batch_size = batch_size\n","    self.length = length\n","    self.learnable = learnable\n","    self.niter = niter\n","    self.system = system\n","    self.model = model"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"q1NuorLJiGNf"},"source":["# args = Args(mode=\"rgb\", exp_name=\"hmdb-test\", batch_size=32, length=32, learnable=\"[0,1,1,1,1]\", niter=20, system=\"hmdb\", model=\"3d\")\n","args = Args()\n","model = Model(device)"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"3WhE9ng4nrhx","executionInfo":{"status":"error","timestamp":1626916034460,"user_tz":240,"elapsed":3431,"user":{"displayName":"Rick Feinleib","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GjoqYHQlggzOnw7kbmibkVT3DL6W7pv4Ot4VJKd=s64","userId":"17023243058419009217"}},"outputId":"d261ec9c-ebfb-43f2-e380-208e086706dd"},"source":["model.train(args)"],"execution_count":null,"outputs":[{"output_type":"stream","text":["/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py:481: UserWarning: This DataLoader will create 8 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.\n","  cpuset_checked))\n"],"name":"stderr"},{"output_type":"stream","text":["193\n","179 22\n"],"name":"stdout"},{"output_type":"stream","text":["/usr/local/lib/python3.7/dist-packages/torch/optim/sgd.py:69: UserWarning: optimizer contains a parameter group with duplicate parameters; in future, this will cause an error; see github.com/pytorch/pytorch/issues/40967 for more information\n","  super(SGD, self).__init__(params, defaults)\n"],"name":"stderr"},{"output_type":"error","ename":"FileNotFoundError","evalue":"ignored","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)","\u001b[0;32m<ipython-input-24-0251a84d6b3a>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m","\u001b[0;32m/content/drive/MyDrive/representation-flow-cvpr19/train_model_class.py\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(self, args)\u001b[0m\n\u001b[1;32m    155\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    156\u001b[0m                 \u001b[0;32mwith\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_grad_enabled\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 157\u001b[0;31m                     \u001b[0;32mfor\u001b[0m \u001b[0mvid\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcls\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdataloader\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mphase\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    158\u001b[0m                         \u001b[0;32mif\u001b[0m \u001b[0mc\u001b[0m\u001b[0;34m%\u001b[0m\u001b[0;36m200\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    159\u001b[0m                             \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'epoch'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mepoch\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'iter'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mc\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py\u001b[0m in \u001b[0;36m__next__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    519\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_sampler_iter\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    520\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_reset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 521\u001b[0;31m             \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_next_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    522\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_num_yielded\u001b[0m \u001b[0;34m+=\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    523\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_dataset_kind\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0m_DatasetKind\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mIterable\u001b[0m \u001b[0;32mand\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m\\\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py\u001b[0m in \u001b[0;36m_next_data\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1201\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1202\u001b[0m                 \u001b[0;32mdel\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_task_info\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0midx\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1203\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_process_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1204\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1205\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_try_put_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py\u001b[0m in \u001b[0;36m_process_data\u001b[0;34m(self, data)\u001b[0m\n\u001b[1;32m   1227\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_try_put_index\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1228\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mExceptionWrapper\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1229\u001b[0;31m             \u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreraise\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1230\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1231\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.7/dist-packages/torch/_utils.py\u001b[0m in \u001b[0;36mreraise\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    423\u001b[0m             \u001b[0;31m# have message field\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    424\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexc_type\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmessage\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmsg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 425\u001b[0;31m         \u001b[0;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexc_type\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmsg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    426\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    427\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mFileNotFoundError\u001b[0m: Caught FileNotFoundError in DataLoader worker process 0.\nOriginal Traceback (most recent call last):\n  File \"/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/worker.py\", line 287, in _worker_loop\n    data = fetcher.fetch(index)\n  File \"/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py\", line 44, in fetch\n    data = [self.dataset[idx] for idx in possibly_batched_index]\n  File \"/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py\", line 44, in <listcomp>\n    data = [self.dataset[idx] for idx in possibly_batched_index]\n  File \"/content/drive/My Drive/representation-flow-cvpr19/hmdb_dataset.py\", line 59, in __getitem__\n    with open(vid, 'rb') as f:\nFileNotFoundError: [Errno 2] No such file or directory: '/ssd/hmdb/rgb_YouTube_smiles!_smile_h_nm_np1_fr_med_8.mp4'\n"]}]},{"cell_type":"code","metadata":{"id":"j4e806VECt8D"},"source":["#!python train_model.py -mode rgb -exp_name \"hmdb-test\" -batch_size 32 -length 32 -learnable \"[0,1,1,1,1]\" -niter 20 -system hmdb -model \"3d\""],"execution_count":null,"outputs":[]}]}

README.md

@@ -17,13 +17,13 @@ If you find the code useful for your research, please cite our paper:
 
 
 # Representation Flow Layer
-![tsf](/examples/flow-layer.png?raw=true "repflow")
+![tsf](./examples/flow-layer.png?raw=true "repflow")
 
 We introduce the representation flow layer, which can be found in [rep_flow_layer.py](rep_flow_layer.py). This layer iteratively estimates the flow, can be applied to CNN feature maps, and is fully learnable to maximize classification performance.
 
 
 # Activity Recognition Experiments
-![model overview](/examples/flow-in-network.png?raw=true "model overview")
+![model overview](./examples/flow-in-network.png?raw=true "model overview")
 
 We include our pretrained models for HMDB and Kinetics in [models/](models).
 

project.py

@@ -0,0 +1,25 @@
+import torch
+from train_model_class import Model
+
+# Check device availability
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+print("You are using device: %s" % device)
+
+class Args:
+  def __init__(self, mode: str='rgb', exp_name: str="hmdb-test", batch_size: int=32, length: int=32, 
+               learnable: str="[0,1,1,1,1]", niter: int=20, system: str="hmdb", model: str="3d"):
+    self.mode = mode
+    self.exp_name = exp_name
+    self.batch_size = batch_size
+    self.length = length
+    self.learnable = learnable
+    self.niter = niter
+    self.system = system
+    self.model = model
+
+
+# args = Args(mode="rgb", exp_name="hmdb-test", batch_size=32, length=32, learnable="[0,1,1,1,1]", niter=20, system="hmdb", model="3d")
+args = Args()
+model = Model(device)
+
+model.train(args)