Log spectrogram constraction

layers/attention.py

@@ -74,7 +74,6 @@ class AttentionWrapper(nn.Module):
 
         # Normalize attention weight
         alignment = F.softmax(alignment, dim=-1) ## TODO: might be buggy
-        print(alignment.size())
 
         # Attention context vector
         # (batch, 1, dim)

notebooks/PlayGround.ipynb

@@ -44,7 +44,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -53,16 +53,27 @@
     "    if figures:                                                                                                         \n",
     "        visualize(alignment, spectrogram, CONFIG)                                                                       \n",
     "    IPython.display.display(Audio(waveform, rate=CONFIG.sample_rate))  \n",
-    "    return alignment"
+    "    return alignment, spectrogram"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "FileNotFoundError",
+     "evalue": "[Errno 2] No such file or directory: '../result/January-26-2018_09:10AM//config.json'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-35-e538c7c7bdac>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mCONFIG_PATH\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mROOT_PATH\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;34m'/config.json'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mOUT_FOLDER\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mROOT_PATH\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;34m'/test/'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m \u001b[0mCONFIG\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_config\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mCONFIG_PATH\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      6\u001b[0m \u001b[0muse_cuda\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/projects/TTS/utils/generic_utils.py\u001b[0m in \u001b[0;36mload_config\u001b[0;34m(config_path)\u001b[0m\n\u001b[1;32m     18\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mload_config\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mconfig_path\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     19\u001b[0m     \u001b[0mconfig\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mAttrDict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 20\u001b[0;31m     \u001b[0mconfig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mjson\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mconfig_path\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"r\"\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     21\u001b[0m     \u001b[0;32mreturn\u001b[0m  \u001b[0mconfig\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     22\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: '../result/January-26-2018_09:10AM//config.json'"
+     ]
+    }
+   ],
    "source": [
     "ROOT_PATH = '../result/January-26-2018_09:10AM/'\n",
     "MODEL_PATH = ROOT_PATH + '/checkpoint_27600.pth.tar'\n",
@@ -74,11 +85,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "TypeError",
+     "evalue": "super(type, obj): obj must be an instance or subtype of type",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-36-bde7da5375c4>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m# load the model\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m model = Tacotron(CONFIG.embedding_size, CONFIG.hidden_size,\n\u001b[0;32m----> 3\u001b[0;31m         CONFIG.num_mels, CONFIG.num_freq, CONFIG.r)\n\u001b[0m\u001b[1;32m      4\u001b[0m ap = AudioProcessor(CONFIG.sample_rate, CONFIG.num_mels, CONFIG.min_level_db,\n\u001b[1;32m      5\u001b[0m                     \u001b[0mCONFIG\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe_shift_ms\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mCONFIG\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mframe_length_ms\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mCONFIG\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpreemphasis\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/projects/TTS/models/tacotron.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, embedding_dim, linear_dim, mel_dim, freq_dim, r, padding_idx, use_memory_mask)\u001b[0m\n\u001b[1;32m     19\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0membedding\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mweight\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnormal_\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m0.3\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     20\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mencoder\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mEncoder\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0membedding_dim\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 21\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdecoder\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mDecoder\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmel_dim\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     22\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     23\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpostnet\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mCBHG\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmel_dim\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mK\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m8\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mprojections\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m256\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmel_dim\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/projects/TTS/layers/tacotron.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, memory_dim, r)\u001b[0m\n\u001b[1;32m    157\u001b[0m         self.attention_rnn = AttentionWrapper(\n\u001b[1;32m    158\u001b[0m             \u001b[0mnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mGRUCell\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m256\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;36m128\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m256\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 159\u001b[0;31m             \u001b[0mBahdanauAttention\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m256\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    160\u001b[0m         )\n\u001b[1;32m    161\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/projects/TTS/layers/attention.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, dim)\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0;32mclass\u001b[0m \u001b[0mBahdanauAttention\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mModule\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      8\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdim\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 9\u001b[0;31m         \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mBahdanauAttention\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__init__\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     10\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mquery_layer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mLinear\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdim\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdim\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbias\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     11\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtanh\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTanh\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mTypeError\u001b[0m: super(type, obj): obj must be an instance or subtype of type"
+     ]
+    }
+   ],
    "source": [
     "# load the model\n",
     "model = Tacotron(CONFIG.embedding_size, CONFIG.hidden_size,\n",
@@ -102,7 +126,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 37,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -115,7 +139,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 38,
    "metadata": {
     "collapsed": true
    },
@@ -139,7 +163,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [
     {
@@ -158,100 +182,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "torch.Size([32, 10])"
-      ]
-     },
-     "execution_count": 28,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "a = torch.randn(32, 10)\n",
-    "b = torch.nn.functional.softmax(torch.autograd.Variable(a), dim=-1)\n",
-    "b.size()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 33,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Variable containing:\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       " 1.0000\n",
-       "[torch.FloatTensor of size 32]"
-      ]
-     },
-     "execution_count": 33,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "b.sum(1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 40,
    "metadata": {
     "scrolled": false
    },
    "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "torch.Size([1, 156])\n",
-      "torch.Size([1, 156])\n"
-     ]
-    },
     {
      "data": {
       "text/html": [
        "\n",
        "                <audio controls=\"controls\" >\n",
-       "                    <source src=\"data:audio/wav;base64,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 truncated
+       "                    <source src=\"data:audio/wav;base64,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 truncated
        "                    Your browser does not support the audio element.\n",
        "                </audio>\n",
        "              "
@@ -272,9 +213,9 @@
     },
     {
      "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAABBIAAAR4CAYAAAC7N/X6AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABBIAAAR4CAYAAAC7N/X6AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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 truncated
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x7f5878081438>"
+       "<matplotlib.figure.Figure at 0x7f583fbee160>"
       ]
      },
      "metadata": {},
@@ -286,6 +227,46 @@
     "print(df.iloc[1, 1])"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "-100.0"
+      ]
+     },
+     "execution_count": 46,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ap._denormalize(aling[1]).min()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.0"
+      ]
+     },
+     "execution_count": 49,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ap._normalize(aling[1]).min()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 39,
@@ -303,7 +284,8 @@
     }
    ],
    "source": [
-    "np.unique(aling)"
+    "np.unique(a\n",
+    "          ling)"
    ]
   },
   {

notebooks/TestModelOnLJSpeech.ipynb

@@ -116,6 +116,28 @@
     "spec, w = compute_spectrogram(file_name)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABAUAAAI4CAYAAAASzVA9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4wLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvpW3flQAAIABJREFUeJzsvVmsrVtW3/ebzdesfu3+9Ofec/sq\nqqHupaCKQBk3AdsJJEh5QIqESCLyEktRHiLLL+QhkaLkjUROQImDHSm27BhFGGELjCmqgKIoqnA1\nt6pue+7pz9n92qv5utnkYXxr7X0vVWWMoejWX9rae3/r++Y3mzHHHOM/xpxLxRhZY4011lhjjTXW\nWGONNdZYY401/uJB/0lXYI011lhjjTXWWGONNdZYY4011viTwZoUWGONNdZYY4011lhjjTXWWGON\nv6BYkwJrrLHGGmusscYaa6yxxhprrPEXFGtSYI011lhjjTXWWGONNdZYY401/oJiTQqsscYaa6yx\nxhprrLHGGmusscZfUKxJgTXWWGONNdZYY4011lhjjTXW+AuKbyspoJT6e0qpfaXUVy5c21RK/YpS\n6o3290Z7XSmlflop9aZS6ktKqY9ceObH2/vfUEr9+IXrLyulvtw+89NKKfXtbN8aa6yxxhprrLHG\nGmusscYaa/xx4Rv51O/5/Jv60d8M3+5MgZ8Dfug91/428KsxxueAX23/B/jrwHPtz08C/xsIiQD8\nFPDdwEeBn1oSCe09P3nhufe+a4011lhjjTXWWGONNdZYY401/qzi5/jWfu439KO/Fb6tpECM8VPA\n8Xsu/wjw99u//z7wH124/g+i4LeBsVLqMvCDwK/EGI9jjCfArwA/1H42jDF+JsYYgX9woaw11lhj\njTXWWGONNdZYY4011vgzjW/iU1/EN/OjvynsH2UF/5DYizE+AogxPlJK7bbXrwL3Ltx3v732ra7f\n/wbXvyGUUj+JMCcALwNkZozGAhFHQ+PPyMwYg0W3/InHAwqDQaGASAR0+59RikQrrAKtIETw7U8g\nolFYTfukXHchYpRCK1Dq/LPYfuZiRKHIjcK0z4YoP6mJUq+gqAPkJmLbct6LJijmLtK1CqOk3k2Q\nG2OUZzTyO0apwxKR8/9jhIkv2UlyFJGAkvbFZXsjmVn2gdRH+knJPUDl5W+zrKc6Z6iW/VL7iCeg\nUETk74aSxs9QKsHqHEtKRoLV5++PRAKRvjWrvpr4mrFNyfV5qwLgo4ybVhGjkPZEhYu09Zb75J72\n/whNVBQu0rcQUCwu9Ktp+8+fN40QFYmObUukv5ZtDRfqAOCiwgf5zCowOmIu1LkJitLH9vNWbtoX\nxQguRmKEVMtny3JUK6ugCBcG1iN9nRm5f3nNBwgxYrQixIht5XoJhZSJkjo1Ia7qE4HKR5K2Du9+\nhrbOUh8XFS6I3CzlPhDbeSTPa6QfljLio/T5MDnvtxAVnvNxi62sxbadS/lbzg0f23KXzyPjbtqx\nWPXrhXFy7bjJHJN+Pm+PyEXtoQgy+qnW5Fq9az7GVh8sZd+1deroiFZxNf9DFHlazsdwQW7O9cf5\n3DMXdEdo71uOhQ+QGUj0sq+WekkR3zMmy1Yvx3b5vhBFx4QIiZb7L8775fsuYtnfttWFF+e5j7Dw\nnlRrYoQ6BrrGkLQ3LOdAoqX9VYi4AFafy33g3XKqOJ8DwEoXB87rqRWkWvo5IG2qfaSfqLb90uKl\nrlIX2uIjHDQP2bCXSbWSPlfnY1q3+jq5MOBNlHmRakWql9Ik41a2c+RiX+kL4xYv6NSklaPlu7SS\nvlmtF20ZMYLRYNrxC+0YG87lfDUPLqxPSxmwbf+7CzoIztcmmUmsdMmynhFpj1ayDsa23nkrmDFC\n0yqejokrGV8WtpzHPipSHbHtGlUHhY+KrJVdT7tOcT5PQXTQtIFBwrkeXvZJu4rI/FQrmdRKdIqL\nkLXzL6LIjEfrgFIQgiIEhY+6fV9EqQurY2xlJap2tZJeuThvYzsGLijqqLDtPJe+Ou9PF9RKHygg\nURF7Yd1Yzs4YoQwyUEvdLrKmqIPIZdLqDhfFPnARmhBJtaJnQ9tHcaWbmqBFH8RzXaBX+kdRBZlL\nVgVZN5f6K7Rrm5K1c/n8cuzqsLSNwKr4+9bT8zl3PqbLsnVbBxQ4r1l4g1EiG6qti8iMZu41uQ6r\n+arb8V32nego1X7WjnVc6lBF08qZaXUDrZwt16iVvLWfuXiuf3XbNtPqGteu0blZ2lrq3euNkmcr\nL7bfchz1e+5djp+BVb1cUO/WS0DhArnRqzlNKz9LOyozIhMuntubSzu0WelUmdsRGUPaogLQtG1Z\nzqelnlri3H5693OxnRvLPlraxDMXGCWKiKz9LkaqEOkaLbLznndY/e7ylzbYwi1tzVb+g6IOYquk\n+lynxHacfFzqoYgnkmn9Lnv8ov0bEH2+XGt8gGmoyFW6uraEXY17K+fv0ctLyZO1CQofVv3UW7a5\nfd7FSIhiwyZKi50eA5FAil3pBukfRSC2Ou6Cb8BSv8hYNnhSjLQNaKJHo4lEHJ5IQGMIeJpYoNAo\npdu+80QiWlliDPjYtO83LCWGGNpxWVq9Kyk4jDHu8OcMP/iDH41HR5M/1nd8/vOvvwqUFy79bIzx\nZ/8ti/lm/vKjb/bAnwZS4JtBfYNr8Q9x/Rui7dyfBVBKRbDsDF5hQ10nizmNqpnwmEDgZniRvspQ\nKOpW6HNtMUqxCI7P+1/miv3gquwPJ09xc2AYJpG5UzwpAieVp58Ydjvi3CsihYe7M884NZzVgYX3\nPD9K6Bi4PY08PVCMEpn8TYCuieRGFqWlc3jRiSi9GCU9E+jbwMJr9ktNE+FqJzBK/GrxmznNmVM8\nWEBuxIhTwCiNpBqmDZw1kBsx0PZLOC4DveS8m58bKhINdYCjCo5KMVybECl9ZJhqjIKtDLYyqfdx\nrfgnB3f58cs3qD0c1/D2maOXaF4YiRJa9tlR6Tj2Cx6YO+xXX+dW+goGSyDQDwMshkY17OkRz49S\nMi0LnVGRpFXSZw2c1rCVKXaySKojdxfShmf6gVRH+jYwsI5Ex3ah1pw2lsJLPx1UioGNvG9Yk+hA\nEzRTZziuNbmJdI0YHnOveXtmeG7gCRHmXlN6WQhzHbnZbUh1IAILb0hUJNUyTqeN5XGpaYKMR+EV\nd2eBF0aKax3PXl6LoRE0x7Xce1TJIndaRXyMXO5quvaCQ9fKiI/QtfL/fgFnTeCVrXMHY4kqKE5r\nRRUiG6nUYylrIEamUTKGmYGBFaOy9IonpSYzrdESFU2AwkXemtbs5AlP9RWDRMoInJfrguL1M7g9\nK9hKM5QSA2fhHV/ic/xw//t4egBbaWAzdas2Lbym9JpERxIl4zZ1Uo/cRHaySG7CSt61ilRBMXeK\nTIuR4aOi9DKvlgZEExRdE0l0xEU4qAxzB1c6gUmjeVLCWS3y/TevBnIdCEDpNZPGMPfSh/tlxAcx\npC53ZaE+qeG3T074yHCDy13omiWJJ4Nwe2640ZW5K208J298lHEdJ56NxK/Ga+4MEydy1gR4uICT\nyvPC2DJMpFyjxLhWStrqIxzXmi8ee3yE7dzwdF/GE0T2Fl4M+keLQM8qtnMYJudGdBOh8vDGWeBx\nWfHsoMMwEcNTK2lXqlk5+I8LxUktOqCXiLKeO7g3q9nILD2r6Vip6+8cT/nIeMDlLvSMyMudueLO\n1PFp9yleVt/Ldpbyc4//e35s5++wkRlsSxx84eyEDd3lRi+jlwgxlptI5RWPi0ATIi+NNLu59PHU\nKY4qxUEZGCaKfiLE6a+fPub7R5cInJM3J1XksGwYJpbUiB5fvlfWkXNHRwOZEXekCVKPro3kBpLW\nEQzIPDmtFTMn9xkl8nWpK4TYwkWOqkDPalJzbrQKsaGYNpGDwvPM0NK1st4YBbt5INex1TVCuuQt\ngVx6kXurZQyWDtOsifzy2dv8p7u3sPrckO+ZyCgJFF7xuNTYtvyFV3z2IPLBTU3HRE5rRd8K4WIu\nrMYbqccqMVMXTnNQG3Id2ckcfetXZGkTNGXrmC51Y7Oav5BpcWTfnueUXrGReuZOc6XTcLM3pwma\nuUs4rBJKr3lpNMVFzUmVMmksl/KKrnUsnKX0BqvFmJ40lr71DBJHzzak1jPoVKSpQymoKsvBtMe8\nsex2Cwa9kix3mCTgao1rDN4rnDeUVYJSkU7WUDeGh9M+h1XKB7ePiVHRBE3RJBTO8qXTHi8MCnY6\nJZl1xKiYNwnvzHoAzJyEIm72Cq6PpqSt/vNesyhTbp8NALhfpISouNGtWHjDV8/EhrjVq+ma0K5V\nljMna/zARi7nDW/OU14alNwcTsmt46ToUDgrDlfQ5MZzZTjDmKXBL4PaNIbSWWZ1wtwlAAyTGq0i\npbe4Vt8+KTOOaksT5J2bqUOpyNyZFRmycLJujJOG3HhSE8iNo5M4EuNJEo+1gRAUj04G3J71uFck\nPNevuNZdsDOaYUxc9X/wisN5l9IbBklDN23QKvK5/S1GiSc3niZo+okTgiZoJo3lt48SrndhmIid\nZC44maXX3CsMqYbNNJC0a4lvSdJ35ordHK53HFbDw8JybwEvDgM9E5h7zeNS82gBZ3Wgn2q+YxzJ\ntJTzqNC8eeb4rm2zKr8Mijtzw82eZ5QEUh3Qrc5/Z5G063HruHpYeCFm0lbfThtxjrcyyNprpYff\nOWx4fiTPP1rIuN7smxVZ7FsiugmK+/PAg6LkmX6H3EDXqpVTn5tIZmDhYFLDbg6XO56+Dcyc5qSW\n+ZUoaKLob6sUvaUO1ELCNQHKljTqW7HPQjxf74Q4VvRtZGDDat3LtOiH0msWXnNUKLine truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7fcd254a4c88>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "spec2 = np.concatenate([spec, spec], axis=1)\n",
+    "hop_length=hop_length*2\n",
+    "plot_spectrogram(spec2)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 47,

train.py

@@ -182,6 +182,7 @@ def main(args):
                           current_step)
             tb.add_scalar('Time/StepTime', step_time, current_step)
 
+
             if current_step % c.save_step == 0:
                 checkpoint_path = 'checkpoint_{}.pth.tar'.format(current_step)
                 checkpoint_path = os.path.join(OUT_PATH, checkpoint_path)
@@ -194,6 +195,13 @@ def main(args):
                                  'date': datetime.date.today().strftime("%B %d, %Y")},
                                 checkpoint_path)
                 print("\n | > Checkpoint is saved : {}".format(checkpoint_path))
+
+                # Log spectrogram reconstruction
+                const_spec = linear_output[0].data.cpu()[None, :]
+                gt_spec = linear_spec_var[0].data.cpu()[None, :]
+                tb.add_image('Spec/Reconstruction', const_spec, current_step)
+                tb.add_image('Spec/GroundTruth', gt_spec, current_step)
+
         lr_scheduler.step(loss.data[0])
         tb.add_scalar('Time/EpochTime', epoch_time, epoch)
         epoch_time = 0