last min cleanup

conv3d.py

@@ -104,7 +104,6 @@ class Bottleneck(nn.Module):
 
 
 class ResNet(nn.Module):
-
     def __init__(self,
                  block,
                  layers,

dev4.ipynb → dev/dev4.ipynb

@@ -21,7 +21,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 102,
+   "execution_count": 114,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -34,135 +34,53 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 106,
+   "execution_count": 115,
    "metadata": {},
    "outputs": [],
    "source": [
-    "ex = ExperimentRunner(params.experiments, n_jobs=1)"
+    "ex = ExperimentRunner(params.experiment_test, n_jobs=1)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 104,
+   "execution_count": 116,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Running param set: {'data_path_base': 'vtest_new2', 'conv_model_name': 'resnet', 'num_epochs': 20, 'feature_extract': True, 'batch_size': 64, 'lr': 0.001, 'use_vggish': True, 'momentum': 0.9}\n"
+      "Running param set: {'data_path_base': 'vtest_new2', 'conv_model_name': 'resnet', 'num_epochs': 10, 'feature_extract': False, 'batch_size': 64, 'lr': 0.001, 'use_vggish': True, 'momentum': 0.9}\n",
+      "Running uuid c6cd69a63c6b7670802afa33af35b13d6c687340f71bf7e299e5711c\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Params to update\n",
-      "* combined.weight\n",
-      "* combined.bias\n",
-      "Epoch 0/19\n",
-      "----------\n",
-      "train Loss: 0.6817 F1: 0.5897 Acc: 0.5949\n",
-      "val Loss: 0.7901 F1: 0.4043 Acc: 0.3412\n",
-      "\n",
-      "Epoch 1/19\n",
-      "----------\n",
-      "train Loss: 0.6104 F1: 0.7294 Acc: 0.7089\n",
-      "val Loss: 0.6452 F1: 0.8125 Acc: 0.7176\n",
-      "\n",
-      "Epoch 2/19\n",
-      "----------\n",
-      "train Loss: 0.6116 F1: 0.7222 Acc: 0.6203\n",
-      "val Loss: 0.6177 F1: 0.8217 Acc: 0.7294\n",
-      "\n",
-      "Epoch 3/19\n",
-      "----------\n",
-      "train Loss: 0.5695 F1: 0.7692 Acc: 0.6962\n",
-      "val Loss: 0.6339 F1: 0.8095 Acc: 0.7176\n",
-      "\n",
-      "Epoch 4/19\n",
-      "----------\n",
-      "train Loss: 0.5504 F1: 0.7816 Acc: 0.7595\n",
-      "val Loss: 0.6923 F1: 0.5743 Acc: 0.4941\n",
-      "\n",
-      "Epoch 5/19\n",
-      "----------\n",
-      "train Loss: 0.4833 F1: 0.8148 Acc: 0.8101\n",
-      "val Loss: 0.6607 F1: 0.6789 Acc: 0.5882\n",
-      "\n",
-      "Epoch 6/19\n",
-      "----------\n",
-      "train Loss: 0.4592 F1: 0.8293 Acc: 0.8228\n",
-      "val Loss: 0.6051 F1: 0.8130 Acc: 0.7294\n",
-      "\n",
-      "Epoch 7/19\n",
-      "----------\n",
-      "train Loss: 0.4290 F1: 0.8706 Acc: 0.8608\n",
-      "val Loss: 0.5585 F1: 0.8722 Acc: 0.8000\n",
-      "\n",
-      "Epoch 8/19\n",
-      "----------\n",
-      "train Loss: 0.4170 F1: 0.8696 Acc: 0.8481\n",
-      "val Loss: 0.5424 F1: 0.8722 Acc: 0.8000\n",
-      "\n",
-      "Epoch 9/19\n",
-      "----------\n",
-      "train Loss: 0.4004 F1: 0.8696 Acc: 0.8481\n",
-      "val Loss: 0.5398 F1: 0.8788 Acc: 0.8118\n",
-      "\n",
-      "Epoch 10/19\n",
-      "----------\n",
-      "train Loss: 0.3825 F1: 0.9011 Acc: 0.8861\n",
-      "val Loss: 0.5567 F1: 0.8594 Acc: 0.7882\n",
-      "\n",
-      "Epoch 11/19\n",
-      "----------\n",
-      "train Loss: 0.3598 F1: 0.9213 Acc: 0.9114\n",
-      "val Loss: 0.5710 F1: 0.8571 Acc: 0.7882\n",
-      "\n",
-      "Epoch 12/19\n",
-      "----------\n",
-      "train Loss: 0.3281 F1: 0.9412 Acc: 0.9367\n",
-      "val Loss: 0.5708 F1: 0.8480 Acc: 0.7765\n",
-      "\n",
-      "Epoch 13/19\n",
-      "----------\n",
-      "train Loss: 0.3187 F1: 0.9302 Acc: 0.9241\n",
-      "val Loss: 0.5715 F1: 0.8226 Acc: 0.7412\n",
-      "\n",
-      "Epoch 14/19\n",
-      "----------\n",
-      "train Loss: 0.3049 F1: 0.9647 Acc: 0.9620\n",
-      "val Loss: 0.5688 F1: 0.8033 Acc: 0.7176\n",
-      "\n",
-      "Epoch 15/19\n",
-      "----------\n",
-      "train Loss: 0.2929 F1: 0.9535 Acc: 0.9494\n",
-      "val Loss: 0.5558 F1: 0.8320 Acc: 0.7529\n",
-      "\n",
-      "Epoch 16/19\n",
-      "----------\n",
-      "train Loss: 0.2833 F1: 0.9425 Acc: 0.9367\n",
-      "val Loss: 0.5366 F1: 0.8504 Acc: 0.7765\n",
-      "\n",
-      "Epoch 17/19\n",
-      "----------\n",
-      "train Loss: 0.2662 F1: 0.9647 Acc: 0.9620\n",
-      "val Loss: 0.5275 F1: 0.8594 Acc: 0.7882\n",
-      "\n",
-      "Epoch 18/19\n",
-      "----------\n",
-      "train Loss: 0.2576 F1: 0.9535 Acc: 0.9494\n",
-      "val Loss: 0.5512 F1: 0.8293 Acc: 0.7529\n",
-      "\n",
-      "Epoch 19/19\n",
-      "----------\n",
-      "train Loss: 0.2463 F1: 0.9535 Acc: 0.9494\n",
-      "val Loss: 0.5820 F1: 0.7863 Acc: 0.7059\n",
-      "\n",
-      "Training complete in 2m 51s\n",
-      "Best val F1  : 0.878788\n",
-      "Best val Acc : 0.811765\n"
+      "Updating ALL params\n"
+     ]
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-116-106ea74a54b1>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mex\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun\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[0;32m~/Dropbox/github/cs231n-project/experiments.py\u001b[0m in \u001b[0;36mrun\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m     61\u001b[0m             \u001b[0mrun_output\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mParallel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn_jobs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mn_jobs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdelayed\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_param_run\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mparam\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mparam\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mparam_grid\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     62\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[0;32m---> 63\u001b[0;31m             \u001b[0mrun_output\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_param_run\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mparam\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mparam\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mparam_grid\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     64\u001b[0m         results_enriched = [\n\u001b[1;32m     65\u001b[0m             merge_dicts(self._get_dict_from_results(result), param_set,\n",
+      "\u001b[0;32m~/Dropbox/github/cs231n-project/experiments.py\u001b[0m in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m     61\u001b[0m             \u001b[0mrun_output\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mParallel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn_jobs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mn_jobs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdelayed\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_param_run\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mparam\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mparam\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mparam_grid\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     62\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[0;32m---> 63\u001b[0;31m             \u001b[0mrun_output\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_param_run\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mparam\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mparam\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mparam_grid\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     64\u001b[0m         results_enriched = [\n\u001b[1;32m     65\u001b[0m             merge_dicts(self._get_dict_from_results(result), param_set,\n",
+      "\u001b[0;32m~/Dropbox/github/cs231n-project/experiments.py\u001b[0m in \u001b[0;36m_param_run\u001b[0;34m(self, param_set)\u001b[0m\n\u001b[1;32m     46\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     47\u001b[0m             \u001b[0mlog\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf'Running uuid {uuid}'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 48\u001b[0;31m             \u001b[0mexperiment_results\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrain_kd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mparam_set\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     49\u001b[0m             \u001b[0mpickle_object\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexperiment_results\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_file_path_experiment_results\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0muuid\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     50\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/Dropbox/github/cs231n-project/train.py\u001b[0m in \u001b[0;36mtrain_kd\u001b[0;34m(data_path_base, conv_model_name, num_epochs, feature_extract, batch_size, use_vggish, num_workers, shuffle, lr, momentum, use_3d)\u001b[0m\n\u001b[1;32m     67\u001b[0m     return train_model(kd,\n\u001b[1;32m     68\u001b[0m                        \u001b[0mdataloaders_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcriterion\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moptimizer_ft\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnum_epochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mnum_epochs\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 69\u001b[0;31m                        is_inception=(conv_model_name == \"inception\"))\n\u001b[0m\u001b[1;32m     70\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     71\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/Dropbox/github/cs231n-project/train.py\u001b[0m in \u001b[0;36mtrain_model\u001b[0;34m(model, dataloaders, criterion, optimizer, num_epochs, is_inception)\u001b[0m\n\u001b[1;32m     76\u001b[0m     \u001b[0mval_f1_history\u001b[0m \u001b[0;34m=\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     77\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 78\u001b[0;31m     \u001b[0mbest_model_wts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcopy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdeepcopy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstate_dict\u001b[0m\u001b[0;34m(\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     79\u001b[0m     \u001b[0mbest_acc\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m0.0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     80\u001b[0m     \u001b[0mbest_f1\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m0.0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/anaconda3/lib/python3.7/copy.py\u001b[0m in \u001b[0;36mdeepcopy\u001b[0;34m(x, memo, _nil)\u001b[0m\n\u001b[1;32m    178\u001b[0m                     \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    179\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[0;32m--> 180\u001b[0;31m                     \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_reconstruct\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmemo\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0mrv\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    181\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    182\u001b[0m     \u001b[0;31m# If is its own copy, don't memoize.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/anaconda3/lib/python3.7/copy.py\u001b[0m in \u001b[0;36m_reconstruct\u001b[0;34m(x, memo, func, args, state, listiter, dictiter, deepcopy)\u001b[0m\n\u001b[1;32m    304\u001b[0m             \u001b[0;32mfor\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdictiter\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    305\u001b[0m                 \u001b[0mkey\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdeepcopy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmemo\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 306\u001b[0;31m                 \u001b[0mvalue\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdeepcopy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmemo\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    307\u001b[0m                 \u001b[0my\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    308\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[0;32m/anaconda3/lib/python3.7/copy.py\u001b[0m in \u001b[0;36mdeepcopy\u001b[0;34m(x, memo, _nil)\u001b[0m\n\u001b[1;32m    159\u001b[0m             \u001b[0mcopier\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"__deepcopy__\"\u001b[0m\u001b[0;34m,\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    160\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mcopier\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 161\u001b[0;31m                 \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcopier\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmemo\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    162\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    163\u001b[0m                 \u001b[0mreductor\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdispatch_table\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcls\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/anaconda3/lib/python3.7/site-packages/torch/tensor.py\u001b[0m in \u001b[0;36m__deepcopy__\u001b[0;34m(self, memo)\u001b[0m\n\u001b[1;32m     29\u001b[0m                 \u001b[0mnew_tensor\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclone\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     30\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[0;32m---> 31\u001b[0;31m                 \u001b[0mnew_storage\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstorage\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__deepcopy__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmemo\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     32\u001b[0m                 \u001b[0mnew_tensor\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnew\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     33\u001b[0m                 \u001b[0mnew_tensor\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mset_\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnew_storage\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstorage_offset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstride\u001b[0m\u001b[0;34m(\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/anaconda3/lib/python3.7/site-packages/torch/storage.py\u001b[0m in \u001b[0;36m__deepcopy__\u001b[0;34m(self, memo)\u001b[0m\n\u001b[1;32m     26\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_cdata\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mmemo\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     27\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mmemo\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_cdata\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 28\u001b[0;31m         \u001b[0mnew_storage\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclone\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     29\u001b[0m         \u001b[0mmemo\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_cdata\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnew_storage\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     30\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mnew_storage\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/anaconda3/lib/python3.7/site-packages/torch/storage.py\u001b[0m in \u001b[0;36mclone\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m     42\u001b[0m         \u001b[0mdevice\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_device\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mis_cuda\u001b[0m \u001b[0;32melse\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     43\u001b[0m         \u001b[0;32mwith\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcuda\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdevice\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---> 44\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcopy_\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[0m\n\u001b[0m\u001b[1;32m     45\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     46\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mtolist\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;31mKeyboardInterrupt\u001b[0m: "
      ]
     }
    ],

experiments.py

@@ -44,6 +44,7 @@ class ExperimentRunner:
             log(uuid)
             experiment_results = unpickle(self._file_path_experiment_results(uuid))
         else:
+            log(f'Running uuid {uuid}')
             experiment_results = train_kd(**param_set)
             pickle_object(experiment_results, self._file_path_experiment_results(uuid))
 

params.py

@@ -13,8 +13,8 @@ vggish_frame_rate = 0.96
 experiment_test = {
     'data_path_base': {data_path_base},
     'conv_model_name': {'resnet'},
-    'num_epochs': {20},
-    'feature_extract': {True},
+    'num_epochs': {10},
+    'feature_extract': {False},
     'batch_size': {64},
     'lr': {0.001},
     'use_vggish': {True},

segmentor.py

@@ -124,17 +124,22 @@ class Segmentor:
                 self.show_images_horizontally(segment_images[-n_to_show:])
                 print('=' * 10)
 
-    def visualize_segments_youtube(self,
-                                   youtube_id: str,
-                                   n_to_show: int = 10,
-                                   show_title: bool = True,
-                                   remove_file: bool = True):
+    @staticmethod
+    def _download_youtube_video(youtube_id: str, show_title: bool = True) -> str:
         yt = YouTube(f'http://youtube.com/watch?v={youtube_id}')
         if show_title:
             print(f'Title: {yt.title}')
         yt_stream = yt.streams.first()
         path = f'{yt_stream.default_filename}'
         yt_stream.download()
+        return path
+
+    def visualize_segments_youtube(self,
+                                   youtube_id: str,
+                                   n_to_show: int = 10,
+                                   show_title: bool = True,
+                                   remove_file: bool = True):
+        path = self._download_youtube_video(youtube_id, show_title)
         self.visualize_segments(path, n_to_show)
         if remove_file:
             os.remove(path)