Fix #97

clean/18_CAM.ipynb

@@ -47,10 +47,10 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <td>0</td>\n",
-       "      <td>0.181760</td>\n",
-       "      <td>0.032238</td>\n",
-       "      <td>0.009472</td>\n",
-       "      <td>00:14</td>\n",
+       "      <td>0.141987</td>\n",
+       "      <td>0.018823</td>\n",
+       "      <td>0.007442</td>\n",
+       "      <td>00:16</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>"
@@ -78,10 +78,10 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <td>0</td>\n",
-       "      <td>0.059119</td>\n",
-       "      <td>0.014090</td>\n",
-       "      <td>0.002706</td>\n",
-       "      <td>00:18</td>\n",
+       "      <td>0.050934</td>\n",
+       "      <td>0.015366</td>\n",
+       "      <td>0.006766</td>\n",
+       "      <td>00:21</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>"
@@ -98,7 +98,7 @@
     "path = untar_data(URLs.PETS)/'images'\n",
     "def is_cat(x): return x[0].isupper()\n",
     "dls = ImageDataLoaders.from_name_func(\n",
-    "    path, get_image_files(path), valid_pct=0.2, seed=42,\n",
+    "    path, get_image_files(path), valid_pct=0.2, seed=21,\n",
     "    label_func=is_cat, item_tfms=Resize(224))\n",
     "learn = cnn_learner(dls, resnet34, metrics=error_rate)\n",
     "learn.fine_tune(1)"
@@ -160,7 +160,7 @@
     {
      "data": {
       "text/plain": [
-       "tensor([[2.7374e-09, 1.0000e+00]], device='cuda:5')"
+       "tensor([[7.3566e-07, 1.0000e+00]], device='cuda:0')"
       ]
      },
      "execution_count": null,
@@ -240,7 +240,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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 truncated
+      "image/png": "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 truncated
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -255,7 +255,7 @@
     "x_dec = TensorImage(dls.train.decode((x,))[0][0])\n",
     "_,ax = plt.subplots()\n",
     "x_dec.show(ctx=ax)\n",
-    "ax.imshow(cam_map[0].detach().cpu(), alpha=0.6, extent=(0,224,224,0),\n",
+    "ax.imshow(cam_map[1].detach().cpu(), alpha=0.6, extent=(0,224,224,0),\n",
     "              interpolation='bilinear', cmap='magma');"
    ]
   },