Skip to content

Enhancement: Complete AlexNet Architecture with Additional Convolutional Layers (Issue 64) #112

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Enhancement: Complete AlexNet Architecture with Additional Convolutional Layers (Issue 64) #112

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a4522fa
Added a 4th convolutional layer (conv4) to the AlexNet architecture t…
T-Ezzoury Nov 15, 2024
4b81435
Added a 5th convolutional layer (conv5) to extend the architecture an…
T-Ezzoury Nov 15, 2024
20ef87e
Added weights and biases for conv4 and conv5 to the model's parameter…
T-Ezzoury Nov 15, 2024
1a7b16a
Updated the input to the first fully connected layer to align with th…
T-Ezzoury Nov 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 27 additions & 4 deletions deep-learning/tensor-flow-examples/notebooks/3_neural_networks/alexnet.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": null,
"metadata": {
"collapsed": true
},
Expand Down Expand Up @@ -142,9 +142,28 @@
" # Apply Dropout\n",
" norm3 = tf.nn.dropout(norm3, _dropout)\n",
"\n",
" # Add a 4th Convolution Layer\n",
" conv4 = conv2d('conv4', norm3, _weights['wc4'], _biases['bc4'])\n",
" # Apply Max Pooling\n",
" pool4 = max_pool('pool4', conv4, k=2)\n",
" # Apply Normalization\n",
" norm4 = norm('norm4', pool4, lsize=4)\n",
" # Apply Dropout\n",
" norm4 = tf.nn.dropout(norm4, _dropout)\n",
"\n",
" # Add a 5th Convolution Layer\n",
" conv5 = conv2d('conv5', norm4, _weights['wc5'], _biases['bc5'])\n",
" # Apply Max Pooling\n",
" pool5 = max_pool('pool5', conv5, k=2)\n",
" # Apply Normalization\n",
" norm5 = norm('norm5', pool5, lsize=4)\n",
" # Apply Dropout\n",
" norm5 = tf.nn.dropout(norm5, _dropout)\n",
"\n",
" # Fully connected layer\n",
" # Reshape conv3 output to fit dense layer input\n",
" dense1 = tf.reshape(norm3, [-1, _weights['wd1'].get_shape().as_list()[0]]) \n",
" # Update the reshape input for the fully connected layer to reflect the output of norm5\n",
" dense1 = tf.reshape(norm5, [-1, _weights['wd1'].get_shape().as_list()[0]]) \n",
"\n",
" # Relu activation\n",
" dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1')\n",
" \n",
Expand All @@ -158,7 +177,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": null,
"metadata": {
"collapsed": true
},
Expand All @@ -169,6 +188,8 @@
" 'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64])),\n",
" 'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128])),\n",
" 'wc3': tf.Variable(tf.random_normal([3, 3, 128, 256])),\n",
" 'wc4': tf.Variable(tf.random_normal([3, 3, 256, 384])),\n",
" 'wc5': tf.Variable(tf.random_normal([3, 3, 384, 256])),\n",
" 'wd1': tf.Variable(tf.random_normal([4*4*256, 1024])),\n",
" 'wd2': tf.Variable(tf.random_normal([1024, 1024])),\n",
" 'out': tf.Variable(tf.random_normal([1024, 10]))\n",
Expand All @@ -177,6 +198,8 @@
" 'bc1': tf.Variable(tf.random_normal([64])),\n",
" 'bc2': tf.Variable(tf.random_normal([128])),\n",
" 'bc3': tf.Variable(tf.random_normal([256])),\n",
" 'bc4': tf.Variable(tf.random_normal([384])),\n",
" 'bc5': tf.Variable(tf.random_normal([256])),\n",
" 'bd1': tf.Variable(tf.random_normal([1024])),\n",
" 'bd2': tf.Variable(tf.random_normal([1024])),\n",
" 'out': tf.Variable(tf.random_normal([n_classes]))\n",
Expand Down