Image Rendering problem resolved (#1178)

amanpro30 · web-flow · commit dcaa8808a8a7 · 2020-02-20T16:28:59.000+01:00
diff --git a/notebooks/chapter19/Learners.ipynb b/notebooks/chapter19/Learners.ipynb
@@ -318,7 +318,7 @@
     "\n",
     "By default we use dense networks with two hidden layers, which has the architecture as the following:\n",
     "\n",
-    "<img src=\"images/nn.png\" width=500/>\n",
+    "<img src=\"images/nn.png\" width=\"500\"/>\n",
     "\n",
     "In our code, we implemented it as:"
    ]
@@ -500,7 +500,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.2"
+   "version": "3.6.9"
   }
  },
  "nbformat": 4,
diff --git a/notebooks/chapter19/Loss Functions and Layers.ipynb b/notebooks/chapter19/Loss Functions and Layers.ipynb
@@ -40,7 +40,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<img src= images/mse_plot.png width=500/>"
+    "<img src=\"images/mse_plot.png\" width=\"500\"/>"
    ]
   },
   {
@@ -88,7 +88,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<img src= images/corss_entropy_plot.png width=500/>"
+    "<img src=\"images/corss_entropy_plot.png\" width=\"500\"/>"
    ]
   },
   {
@@ -390,7 +390,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.2"
+   "version": "3.6.9"
   }
  },
  "nbformat": 4,
diff --git a/notebooks/chapter19/Optimizer and Backpropagation.ipynb b/notebooks/chapter19/Optimizer and Backpropagation.ipynb
@@ -251,7 +251,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<img src=\"images/backprop.png\" width=500/>"
+    "<img src=\"images/backprop.png\" width=\"500\"/>"
    ]
   },
   {
@@ -260,7 +260,7 @@
    "source": [
     "Applying optimizers and back-propagation algorithm together, we can update the weights of a neural network to minimize the loss function with alternatively doing forward and back-propagation process. Here is a figure form [here](https://medium.com/datathings/neural-networks-and-backpropagation-explained-in-a-simple-way-f540a3611f5e) describing how a neural network updates its weights:\n",
     "\n",
-    "<img src=\"images/nn_steps.png\" width=700></img>"
+    "<img src=\"images/nn_steps.png\" width=\"700\"></img>"
    ]
   },
   {
@@ -303,7 +303,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.2"
+   "version": "3.6.9"
   }
  },
  "nbformat": 4,
diff --git a/notebooks/chapter19/RNN.ipynb b/notebooks/chapter19/RNN.ipynb
@@ -12,7 +12,7 @@
     "\n",
     "Recurrent neural networks address this issue. They are networks with loops in them, allowing information to persist.\n",
     "\n",
-    "<img src=\"images/rnn_unit.png\" width=500/>"
+    "<img src=\"images/rnn_unit.png\" width=\"500\"/>"
    ]
   },
   {
@@ -21,7 +21,7 @@
    "source": [
     "A recurrent neural network can be thought of as multiple copies of the same network, each passing a message to a successor. Consider what happens if we unroll the above loop:\n",
     " \n",
-    "<img src=\"images/rnn_units.png\" width=500/>"
+    "<img src=\"images/rnn_units.png\" width=\"500\"/>"
    ]
   },
   {
@@ -30,7 +30,7 @@
    "source": [
     "As demonstrated in the book, recurrent neural networks may be connected in many different ways: sequences in the input, the output, or in the most general case both.\n",
     "\n",
-    "<img src=\"images/rnn_connections.png\" width=700/>"
+    "<img src=\"images/rnn_connections.png\" width=\"700\"/>"
    ]
   },
   {
@@ -303,7 +303,7 @@
     "\n",
     "Autoencoders are an unsupervised learning technique in which we leverage neural networks for the task of representation learning. It works by compressing the input into a latent-space representation, to do transformations on the data. \n",
     "\n",
-    "<img src=\"images/autoencoder.png\" width=800/>"
+    "<img src=\"images/autoencoder.png\" width=\"800\"/>"
    ]
   },
   {
@@ -314,7 +314,7 @@
     "\n",
     "Autoencoders have different architectures for different kinds of data. Here we only provide a simple example of a vanilla encoder, which means they're only one hidden layer in the network:\n",
     "\n",
-    "<img src=\"images/vanilla.png\" width=500/>\n",
+    "<img src=\"images/vanilla.png\" width=\"500\"/>\n",
     "\n",
     "You can view the source code by:"
    ]
@@ -479,7 +479,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.8"
+   "version": "3.6.9"
   }
  },
  "nbformat": 4,
diff --git a/notebooks/chapter24/Image Edge Detection.ipynb b/notebooks/chapter24/Image Edge Detection.ipynb
@@ -69,7 +69,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<img src=\"images/gradients.png\" width=700/>"
+    "<img src=\"images/gradients.png\" width=\"700\"/>"
    ]
   },
   {
@@ -105,7 +105,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<img src=\"images/stapler.png\" width=500/>\n",
+    "<img src=\"images/stapler.png\" width=\"500\"/>\n",
     "\n",
     "We will use `matplotlib` to read the image as a numpy ndarray:"
    ]
@@ -226,7 +226,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<img src=\"images/derivative_of_gaussian.png\" width=400/>"
+    "<img src=\"images/derivative_of_gaussian.png\" width=\"400\"/>"
    ]
   },
   {
@@ -318,7 +318,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<img src=\"images/laplacian.png\" width=200/>"
+    "<img src=\"images/laplacian.png\" width=\"200\"/>"
    ]
   },
   {
@@ -334,7 +334,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<img src=\"images/laplacian_kernels.png\" width=300/>"
+    "<img src=\"images/laplacian_kernels.png\" width=\"300\"/>"
    ]
   },
   {
@@ -400,7 +400,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.2"
+   "version": "3.6.9"
   }
  },
  "nbformat": 4,
diff --git a/notebooks/chapter24/Objects in Images.ipynb b/notebooks/chapter24/Objects in Images.ipynb
@@ -306,7 +306,7 @@
    "source": [
     "The bounding boxes are drawn on the original picture showed in the following:\n",
     "\n",
-    "<img src=\"images/stapler_bbox.png\" width=500/>"
+    "<img src=\"images/stapler_bbox.png\" width=\"500\"/>"
    ]
   },
   {
@@ -324,7 +324,7 @@
     "\n",
     "[Ross Girshick et al.](https://arxiv.org/pdf/1311.2524.pdf) proposed a method where they use selective search to extract just 2000 regions from the image. Then the regions in bounding boxes are feed into a convolutional neural network to perform classification. The brief architecture can be shown as:\n",
     "\n",
-    "<img src=\"images/RCNN.png\" width=500/>"
+    "<img src=\"images/RCNN.png\" width=\"500\"/>"
    ]
   },
   {
@@ -446,7 +446,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.2"
+   "version": "3.6.9"
   }
  },
  "nbformat": 4,

Original file line number	Diff line number	Diff line change
`@@ -40,7 +40,7 @@`
`40`	`40`	`"cell_type": "markdown",`
`41`	`41`	`"metadata": {},`
`42`	`42`	`"source": [`
`43`		`- "<img src= images/mse_plot.png width=500/>"`
	`43`	`+ "<img src=\"images/mse_plot.png\" width=\"500\"/>"`
`44`	`44`	`]`
`45`	`45`	`},`
`46`	`46`	`{`
`@@ -88,7 +88,7 @@`
`88`	`88`	`"cell_type": "markdown",`
`89`	`89`	`"metadata": {},`
`90`	`90`	`"source": [`
`91`		`- "<img src= images/corss_entropy_plot.png width=500/>"`
	`91`	`+ "<img src=\"images/corss_entropy_plot.png\" width=\"500\"/>"`
`92`	`92`	`]`
`93`	`93`	`},`
`94`	`94`	`{`
`@@ -390,7 +390,7 @@`
`390`	`390`	`"name": "python",`
`391`	`391`	`"nbconvert_exporter": "python",`
`392`	`392`	`"pygments_lexer": "ipython3",`
`393`		`- "version": "3.7.2"`
	`393`	`+ "version": "3.6.9"`
`394`	`394`	`}`
`395`	`395`	`},`
`396`	`396`	`"nbformat": 4,`
Original file line number	Diff line number	Diff line change
`@@ -251,7 +251,7 @@`
`251`	`251`	`"cell_type": "markdown",`
`252`	`252`	`"metadata": {},`
`253`	`253`	`"source": [`
`254`		`- "<img src=\"images/backprop.png\" width=500/>"`
	`254`	`+ "<img src=\"images/backprop.png\" width=\"500\"/>"`
`255`	`255`	`]`
`256`	`256`	`},`
`257`	`257`	`{`
`@@ -260,7 +260,7 @@`
`260`	`260`	`"source": [`
`261`	`261`	`"Applying optimizers and back-propagation algorithm together, we can update the weights of a neural network to minimize the loss function with alternatively doing forward and back-propagation process. Here is a figure form [here](https://medium.com/datathings/neural-networks-and-backpropagation-explained-in-a-simple-way-f540a3611f5e) describing how a neural network updates its weights:\n",`
`262`	`262`	`"\n",`
`263`		`- "<img src=\"images/nn_steps.png\" width=700></img>"`
	`263`	`+ "<img src=\"images/nn_steps.png\" width=\"700\"></img>"`
`264`	`264`	`]`
`265`	`265`	`},`
`266`	`266`	`{`
`@@ -303,7 +303,7 @@`
`303`	`303`	`"name": "python",`
`304`	`304`	`"nbconvert_exporter": "python",`
`305`	`305`	`"pygments_lexer": "ipython3",`
`306`		`- "version": "3.7.2"`
	`306`	`+ "version": "3.6.9"`
`307`	`307`	`}`
`308`	`308`	`},`
`309`	`309`	`"nbformat": 4,`
Original file line number	Diff line number	Diff line change
`@@ -12,7 +12,7 @@`
`12`	`12`	`"\n",`
`13`	`13`	`"Recurrent neural networks address this issue. They are networks with loops in them, allowing information to persist.\n",`
`14`	`14`	`"\n",`
`15`		`- "<img src=\"images/rnn_unit.png\" width=500/>"`
	`15`	`+ "<img src=\"images/rnn_unit.png\" width=\"500\"/>"`
`16`	`16`	`]`
`17`	`17`	`},`
`18`	`18`	`{`
`@@ -21,7 +21,7 @@`
`21`	`21`	`"source": [`
`22`	`22`	`"A recurrent neural network can be thought of as multiple copies of the same network, each passing a message to a successor. Consider what happens if we unroll the above loop:\n",`
`23`	`23`	`" \n",`
`24`		`- "<img src=\"images/rnn_units.png\" width=500/>"`
	`24`	`+ "<img src=\"images/rnn_units.png\" width=\"500\"/>"`
`25`	`25`	`]`
`26`	`26`	`},`
`27`	`27`	`{`
`@@ -30,7 +30,7 @@`
`30`	`30`	`"source": [`
`31`	`31`	`"As demonstrated in the book, recurrent neural networks may be connected in many different ways: sequences in the input, the output, or in the most general case both.\n",`
`32`	`32`	`"\n",`
`33`		`- "<img src=\"images/rnn_connections.png\" width=700/>"`
	`33`	`+ "<img src=\"images/rnn_connections.png\" width=\"700\"/>"`
`34`	`34`	`]`
`35`	`35`	`},`
`36`	`36`	`{`
`@@ -303,7 +303,7 @@`
`303`	`303`	`"\n",`
`304`	`304`	`"Autoencoders are an unsupervised learning technique in which we leverage neural networks for the task of representation learning. It works by compressing the input into a latent-space representation, to do transformations on the data. \n",`
`305`	`305`	`"\n",`
`306`		`- "<img src=\"images/autoencoder.png\" width=800/>"`
	`306`	`+ "<img src=\"images/autoencoder.png\" width=\"800\"/>"`
`307`	`307`	`]`
`308`	`308`	`},`
`309`	`309`	`{`
`@@ -314,7 +314,7 @@`
`314`	`314`	`"\n",`
`315`	`315`	`"Autoencoders have different architectures for different kinds of data. Here we only provide a simple example of a vanilla encoder, which means they're only one hidden layer in the network:\n",`
`316`	`316`	`"\n",`
`317`		`- "<img src=\"images/vanilla.png\" width=500/>\n",`
	`317`	`+ "<img src=\"images/vanilla.png\" width=\"500\"/>\n",`
`318`	`318`	`"\n",`
`319`	`319`	`"You can view the source code by:"`
`320`	`320`	`]`
`@@ -479,7 +479,7 @@`
`479`	`479`	`"name": "python",`
`480`	`480`	`"nbconvert_exporter": "python",`
`481`	`481`	`"pygments_lexer": "ipython3",`
`482`		`- "version": "3.6.8"`
	`482`	`+ "version": "3.6.9"`
`483`	`483`	`}`
`484`	`484`	`},`
`485`	`485`	`"nbformat": 4,`
Original file line number	Diff line number	Diff line change
`@@ -69,7 +69,7 @@`
`69`	`69`	`"cell_type": "markdown",`
`70`	`70`	`"metadata": {},`
`71`	`71`	`"source": [`
`72`		`- "<img src=\"images/gradients.png\" width=700/>"`
	`72`	`+ "<img src=\"images/gradients.png\" width=\"700\"/>"`
`73`	`73`	`]`
`74`	`74`	`},`
`75`	`75`	`{`
`@@ -105,7 +105,7 @@`
`105`	`105`	`"cell_type": "markdown",`
`106`	`106`	`"metadata": {},`
`107`	`107`	`"source": [`
`108`		`- "<img src=\"images/stapler.png\" width=500/>\n",`
	`108`	`+ "<img src=\"images/stapler.png\" width=\"500\"/>\n",`
`109`	`109`	`"\n",`
`110`	`110`	"We will use `matplotlib` to read the image as a numpy ndarray:"
`111`	`111`	`]`
`@@ -226,7 +226,7 @@`
`226`	`226`	`"cell_type": "markdown",`
`227`	`227`	`"metadata": {},`
`228`	`228`	`"source": [`
`229`		`- "<img src=\"images/derivative_of_gaussian.png\" width=400/>"`
	`229`	`+ "<img src=\"images/derivative_of_gaussian.png\" width=\"400\"/>"`
`230`	`230`	`]`
`231`	`231`	`},`
`232`	`232`	`{`
`@@ -318,7 +318,7 @@`
`318`	`318`	`"cell_type": "markdown",`
`319`	`319`	`"metadata": {},`
`320`	`320`	`"source": [`
`321`		`- "<img src=\"images/laplacian.png\" width=200/>"`
	`321`	`+ "<img src=\"images/laplacian.png\" width=\"200\"/>"`
`322`	`322`	`]`
`323`	`323`	`},`
`324`	`324`	`{`
`@@ -334,7 +334,7 @@`
`334`	`334`	`"cell_type": "markdown",`
`335`	`335`	`"metadata": {},`
`336`	`336`	`"source": [`
`337`		`- "<img src=\"images/laplacian_kernels.png\" width=300/>"`
	`337`	`+ "<img src=\"images/laplacian_kernels.png\" width=\"300\"/>"`
`338`	`338`	`]`
`339`	`339`	`},`
`340`	`340`	`{`
`@@ -400,7 +400,7 @@`
`400`	`400`	`"name": "python",`
`401`	`401`	`"nbconvert_exporter": "python",`
`402`	`402`	`"pygments_lexer": "ipython3",`
`403`		`- "version": "3.7.2"`
	`403`	`+ "version": "3.6.9"`
`404`	`404`	`}`
`405`	`405`	`},`
`406`	`406`	`"nbformat": 4,`
Original file line number	Diff line number	Diff line change
`@@ -306,7 +306,7 @@`
`306`	`306`	`"source": [`
`307`	`307`	`"The bounding boxes are drawn on the original picture showed in the following:\n",`
`308`	`308`	`"\n",`
`309`		`- "<img src=\"images/stapler_bbox.png\" width=500/>"`
	`309`	`+ "<img src=\"images/stapler_bbox.png\" width=\"500\"/>"`
`310`	`310`	`]`
`311`	`311`	`},`
`312`	`312`	`{`
`@@ -324,7 +324,7 @@`
`324`	`324`	`"\n",`
`325`	`325`	`"[Ross Girshick et al.](https://arxiv.org/pdf/1311.2524.pdf) proposed a method where they use selective search to extract just 2000 regions from the image. Then the regions in bounding boxes are feed into a convolutional neural network to perform classification. The brief architecture can be shown as:\n",`
`326`	`326`	`"\n",`
`327`		`- "<img src=\"images/RCNN.png\" width=500/>"`
	`327`	`+ "<img src=\"images/RCNN.png\" width=\"500\"/>"`
`328`	`328`	`]`
`329`	`329`	`},`
`330`	`330`	`{`
`@@ -446,7 +446,7 @@`
`446`	`446`	`"name": "python",`
`447`	`447`	`"nbconvert_exporter": "python",`
`448`	`448`	`"pygments_lexer": "ipython3",`
`449`		`- "version": "3.7.2"`
	`449`	`+ "version": "3.6.9"`
`450`	`450`	`}`
`451`	`451`	`},`
`452`	`452`	`"nbformat": 4,`