anton/mlpractical
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fixing inconsistent channel ordering in constructor and docstring shape descriptions.

Browse Source
This commit is contained in:
Matt Graham 2016-11-09 19:40:46 +00:00
parent 60edabd261
commit d290f4513d
1 changed files with 12 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
notebooks/Convolutional layer tests.ipynb
View File

@ -96,10 +96,12 @@
" corresponds to `y = conv2d(x, K) + b`.\n",
"\n",
" Args:\n",
" inputs: Array of layer inputs of shape (batch_size, input_dim).\n",
" inputs: Array of layer inputs of shape \n",
" (batch_size, num_input_channels, input_dim_1, input_dim_2).\n",
"\n",
" Returns:\n",
" outputs: Array of layer outputs of shape (batch_size, output_dim).\n",
" outputs: Array of layer outputs of shape \n",
" (batch_size, num_output_channels, output_dim_1, output_dim_2).\n",
" \"\"\"\n",
" raise NotImplementedError()\n",
"\n",
@ -121,7 +123,7 @@
"\n",
" Returns:\n",
" Array of gradients with respect to the layer inputs of shape\n",
" (batch_size, input_dim).\n",
" (batch_size, num_input_channels, input_dim_1, input_dim_2).\n",
" \"\"\"\n",
" raise NotImplementedError()\n",
"\n",
@ -132,7 +134,7 @@
" inputs: array of inputs to layer of shape (batch_size, input_dim)\n",
" grads_wrt_to_outputs: array of gradients with respect to the layer\n",
" outputs of shape\n",
" (batch_size, num_output-_channels, output_dim_1, output_dim_2).\n",
" (batch_size, num_output_channels, output_dim_1, output_dim_2).\n",
"\n",
" Returns:\n",
" list of arrays of gradients with respect to the layer parameters\n",
@ -232,8 +234,8 @@
" [ 5403., 5469., 5535.]]]]\n",
" )\n",
" layer = layer_class(\n",
" num_input_channels=kernels.shape[0], \n",
" num_output_channels=kernels.shape[1], \n",
" num_input_channels=kernels.shape[1], \n",
" num_output_channels=kernels.shape[0], \n",
" input_dim_1=inputs.shape[2], \n",
" input_dim_2=inputs.shape[3],\n",
" kernel_dim_1=kernels.shape[2],\n",
@ -319,8 +321,8 @@
" [ 226., 440., 468., 222.],\n",
" [ 105., 199., 209., 96.]]]])\n",
" layer = layer_class(\n",
" num_input_channels=kernels.shape[0], \n",
" num_output_channels=kernels.shape[1], \n",
" num_input_channels=kernels.shape[1], \n",
" num_output_channels=kernels.shape[0], \n",
" input_dim_1=inputs.shape[2], \n",
" input_dim_2=inputs.shape[3],\n",
" kernel_dim_1=kernels.shape[2],\n",
@ -384,8 +386,8 @@
" true_kernel_grads = true_kernel_grads[:, :, ::-1, ::-1]\n",
" true_bias_grads = np.array([-126., 36.])\n",
" layer = layer_class(\n",
" num_input_channels=kernels.shape[0], \n",
" num_output_channels=kernels.shape[1], \n",
" num_input_channels=kernels.shape[1], \n",
" num_output_channels=kernels.shape[0], \n",
" input_dim_1=inputs.shape[2], \n",
" input_dim_2=inputs.shape[3],\n",
" kernel_dim_1=kernels.shape[2],\n",