diff --git a/cars/architecture-investigations/architecture.ipynb b/cars/architecture-investigations/architecture.ipynb index 40acb40..e9ecfbb 100644 --- a/cars/architecture-investigations/architecture.ipynb +++ b/cars/architecture-investigations/architecture.ipynb @@ -266,4 +266,4 @@ }, "nbformat": 4, "nbformat_minor": 5 -} +} \ No newline at end of file diff --git a/cars/architecture-investigations/conv/nonlinear/l1/2parts/alexnet-l1-2part.prototxt b/cars/architecture-investigations/conv/nonlinear/l1/2parts/alexnet-l1-2part.prototxt new file mode 100644 index 0000000..574c338 --- /dev/null +++ b/cars/architecture-investigations/conv/nonlinear/l1/2parts/alexnet-l1-2part.prototxt @@ -0,0 +1,478 @@ +# AlexNet +name: "AlexNet" +layer { + name: "train-data" + type: "Data" + top: "data" + top: "label" + transform_param { + mirror: true + crop_size: 227 + } + data_param { + batch_size: 128 + } + include { stage: "train" } +} +layer { + name: "val-data" + type: "Data" + top: "data" + top: "label" + transform_param { + crop_size: 227 + } + data_param { + batch_size: 32 + } + include { stage: "val" } +} + +################ +# CONV 1 +################ + +layer { + name: "conv1" + type: "Convolution" + bottom: "data" + top: "conv1" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 24 + kernel_size: 11 + stride: 4 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0 + } + } +} +layer { + name: "relu1" + type: "ReLU" + bottom: "conv1" + top: "conv1" +} +layer { + name: "norm1" + type: "LRN" + bottom: "conv1" + top: "norm1" + lrn_param { + local_size: 5 + alpha: 0.0001 + beta: 0.75 + } +} + +################ +# CONV 1.2 +################ + +layer { + name: "conv1.2" + type: "Convolution" + bottom: "norm1" + top: "conv1.2" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 24 + kernel_size: 11 + stride: 4 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0 + } + } +} +layer { + name: "relu1.2" + type: "ReLU" + bottom: "conv1.2" + top: "conv1.2" +} +layer { + name: "norm1.2" + type: "LRN" + bottom: "conv1.2" + top: "norm1.2" + lrn_param { + local_size: 5 + alpha: 0.0001 + beta: 0.75 + } +} + +layer { + name: "pool1" + type: "Pooling" + bottom: "norm1.2" + top: "pool1" + pooling_param { + pool: MAX + kernel_size: 3 + stride: 2 + } +} + +################ +# CONV 2 +################ + +layer { + name: "conv2" + type: "Convolution" + bottom: "pool1" + top: "conv2" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 2 + kernel_size: 5 + group: 2 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0.1 + } + } +} +layer { + name: "relu2" + type: "ReLU" + bottom: "conv2" + top: "conv2" +} +layer { + name: "norm2" + type: "LRN" + bottom: "conv2" + top: "norm2" + lrn_param { + local_size: 5 + alpha: 0.0001 + beta: 0.75 + } +} +layer { + name: "pool2" + type: "Pooling" + bottom: "norm2" + top: "pool2" + pooling_param { + pool: MAX + kernel_size: 3 + stride: 2 + } +} + +################ +# CONV 3 +################ + +layer { + name: "conv3" + type: "Convolution" + bottom: "pool2" + top: "conv3" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 384 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0 + } + } +} +layer { + name: "relu3" + type: "ReLU" + bottom: "conv3" + top: "conv3" +} + +################ +# CONV 4 +################ + +layer { + name: "conv4" + type: "Convolution" + bottom: "conv3" + top: "conv4" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 384 + pad: 1 + kernel_size: 3 + group: 2 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0.1 + } + } +} +layer { + name: "relu4" + type: "ReLU" + bottom: "conv4" + top: "conv4" +} + +################ +# CONV 5 +################ + +layer { + name: "conv5" + type: "Convolution" + bottom: "conv4" + top: "conv5" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 1 + kernel_size: 3 + group: 2 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0.1 + } + } +} +layer { + name: "relu5" + type: "ReLU" + bottom: "conv5" + top: "conv5" +} +layer { + name: "pool5" + type: "Pooling" + bottom: "conv5" + top: "pool5" + pooling_param { + pool: MAX + kernel_size: 3 + stride: 2 + } +} + +################ +# DENSE 1 +################ + +layer { + name: "fc6" + type: "InnerProduct" + bottom: "pool5" + top: "fc6" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + inner_product_param { + num_output: 4096 + weight_filler { + type: "gaussian" + std: 0.005 + } + bias_filler { + type: "constant" + value: 0.1 + } + } +} +layer { + name: "relu6" + type: "ReLU" + bottom: "fc6" + top: "fc6" +} +layer { + name: "drop6" + type: "Dropout" + bottom: "fc6" + top: "fc6" + dropout_param { + dropout_ratio: 0.5 + } +} + +################ +# DENSE 2 +################ + +layer { + name: "fc7" + type: "InnerProduct" + bottom: "fc6" + top: "fc7" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + inner_product_param { + num_output: 4096 + weight_filler { + type: "gaussian" + std: 0.005 + } + bias_filler { + type: "constant" + value: 0.1 + } + } +} +layer { + name: "relu7" + type: "ReLU" + bottom: "fc7" + top: "fc7" +} +layer { + name: "drop7" + type: "Dropout" + bottom: "fc7" + top: "fc7" + dropout_param { + dropout_ratio: 0.5 + } +} + +################ +# OUTPUT +################ + +layer { + name: "fc8" + type: "InnerProduct" + bottom: "fc7" + top: "fc8" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + inner_product_param { + # Since num_output is unset, DIGITS will automatically set it to the + # number of classes in your dataset. + # Uncomment this line to set it explicitly: + #num_output: 1000 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0 + } + } +} + +################ +# STATS +################ + +layer { + name: "accuracy" + type: "Accuracy" + bottom: "fc8" + bottom: "label" + top: "accuracy" + include { stage: "val" } +} +layer { + name: "loss" + type: "SoftmaxWithLoss" + bottom: "fc8" + bottom: "label" + top: "loss" + exclude { stage: "deploy" } +} +layer { + name: "softmax" + type: "Softmax" + bottom: "fc8" + top: "softmax" + include { stage: "deploy" } +} diff --git a/cars/architecture-investigations/conv/nonlinear/l1/4parts/alexnet-l1-4part.prototxt b/cars/architecture-investigations/conv/nonlinear/l1/4parts/alexnet-l1-4part.prototxt new file mode 100644 index 0000000..7c7d7bd --- /dev/null +++ b/cars/architecture-investigations/conv/nonlinear/l1/4parts/alexnet-l1-4part.prototxt @@ -0,0 +1,576 @@ +# AlexNet +name: "AlexNet" +layer { + name: "train-data" + type: "Data" + top: "data" + top: "label" + transform_param { + mirror: true + crop_size: 227 + } + data_param { + batch_size: 128 + } + include { stage: "train" } +} +layer { + name: "val-data" + type: "Data" + top: "data" + top: "label" + transform_param { + crop_size: 227 + } + data_param { + batch_size: 32 + } + include { stage: "val" } +} + +################ +# CONV 1 +################ + +layer { + name: "conv1" + type: "Convolution" + bottom: "data" + top: "conv1" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 24 + kernel_size: 11 + stride: 4 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0 + } + } +} +layer { + name: "relu1" + type: "ReLU" + bottom: "conv1" + top: "conv1" +} +layer { + name: "norm1" + type: "LRN" + bottom: "conv1" + top: "norm1" + lrn_param { + local_size: 5 + alpha: 0.0001 + beta: 0.75 + } +} + +################ +# CONV 1.2 +################ + +layer { + name: "conv1.2" + type: "Convolution" + bottom: "norm1" + top: "conv1.2" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 24 + kernel_size: 11 + stride: 4 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0 + } + } +} +layer { + name: "relu1.2" + type: "ReLU" + bottom: "conv1.2" + top: "conv1.2" +} +layer { + name: "norm1.2" + type: "LRN" + bottom: "conv1.2" + top: "norm1.2" + lrn_param { + local_size: 5 + alpha: 0.0001 + beta: 0.75 + } +} + +################ +# CONV 1.3 +################ + +layer { + name: "conv1.3" + type: "Convolution" + bottom: "norm1.2" + top: "conv1.3" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 24 + kernel_size: 11 + stride: 4 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0 + } + } +} +layer { + name: "relu1.3" + type: "ReLU" + bottom: "conv1.3" + top: "conv1.3" +} +layer { + name: "norm1.3" + type: "LRN" + bottom: "conv1.3" + top: "norm1.3" + lrn_param { + local_size: 5 + alpha: 0.0001 + beta: 0.75 + } +} + +################ +# CONV 1.4 +################ + +layer { + name: "conv1.4" + type: "Convolution" + bottom: "norm1.3" + top: "conv1.4" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 24 + kernel_size: 11 + stride: 4 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0 + } + } +} +layer { + name: "relu1.4" + type: "ReLU" + bottom: "conv1.4" + top: "conv1.4" +} +layer { + name: "norm1.4" + type: "LRN" + bottom: "conv1.4" + top: "norm1.4" + lrn_param { + local_size: 5 + alpha: 0.0001 + beta: 0.75 + } +} + +layer { + name: "pool1" + type: "Pooling" + bottom: "norm1.4" + top: "pool1" + pooling_param { + pool: MAX + kernel_size: 3 + stride: 2 + } +} + +################ +# CONV 2 +################ + +layer { + name: "conv2" + type: "Convolution" + bottom: "pool1" + top: "conv2" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 2 + kernel_size: 5 + group: 2 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0.1 + } + } +} +layer { + name: "relu2" + type: "ReLU" + bottom: "conv2" + top: "conv2" +} +layer { + name: "norm2" + type: "LRN" + bottom: "conv2" + top: "norm2" + lrn_param { + local_size: 5 + alpha: 0.0001 + beta: 0.75 + } +} +layer { + name: "pool2" + type: "Pooling" + bottom: "norm2" + top: "pool2" + pooling_param { + pool: MAX + kernel_size: 3 + stride: 2 + } +} + +################ +# CONV 3 +################ + +layer { + name: "conv3" + type: "Convolution" + bottom: "pool2" + top: "conv3" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 384 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0 + } + } +} +layer { + name: "relu3" + type: "ReLU" + bottom: "conv3" + top: "conv3" +} + +################ +# CONV 4 +################ + +layer { + name: "conv4" + type: "Convolution" + bottom: "conv3" + top: "conv4" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 384 + pad: 1 + kernel_size: 3 + group: 2 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0.1 + } + } +} +layer { + name: "relu4" + type: "ReLU" + bottom: "conv4" + top: "conv4" +} + +################ +# CONV 5 +################ + +layer { + name: "conv5" + type: "Convolution" + bottom: "conv4" + top: "conv5" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 1 + kernel_size: 3 + group: 2 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0.1 + } + } +} +layer { + name: "relu5" + type: "ReLU" + bottom: "conv5" + top: "conv5" +} +layer { + name: "pool5" + type: "Pooling" + bottom: "conv5" + top: "pool5" + pooling_param { + pool: MAX + kernel_size: 3 + stride: 2 + } +} + +################ +# DENSE 1 +################ + +layer { + name: "fc6" + type: "InnerProduct" + bottom: "pool5" + top: "fc6" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + inner_product_param { + num_output: 4096 + weight_filler { + type: "gaussian" + std: 0.005 + } + bias_filler { + type: "constant" + value: 0.1 + } + } +} +layer { + name: "relu6" + type: "ReLU" + bottom: "fc6" + top: "fc6" +} +layer { + name: "drop6" + type: "Dropout" + bottom: "fc6" + top: "fc6" + dropout_param { + dropout_ratio: 0.5 + } +} + +################ +# DENSE 2 +################ + +layer { + name: "fc7" + type: "InnerProduct" + bottom: "fc6" + top: "fc7" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + inner_product_param { + num_output: 4096 + weight_filler { + type: "gaussian" + std: 0.005 + } + bias_filler { + type: "constant" + value: 0.1 + } + } +} +layer { + name: "relu7" + type: "ReLU" + bottom: "fc7" + top: "fc7" +} +layer { + name: "drop7" + type: "Dropout" + bottom: "fc7" + top: "fc7" + dropout_param { + dropout_ratio: 0.5 + } +} + +################ +# OUTPUT +################ + +layer { + name: "fc8" + type: "InnerProduct" + bottom: "fc7" + top: "fc8" + param { + lr_mult: 1 + decay_mult: 1 + } + param { + lr_mult: 2 + decay_mult: 0 + } + inner_product_param { + # Since num_output is unset, DIGITS will automatically set it to the + # number of classes in your dataset. + # Uncomment this line to set it explicitly: + #num_output: 1000 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + value: 0 + } + } +} + +################ +# STATS +################ + +layer { + name: "accuracy" + type: "Accuracy" + bottom: "fc8" + bottom: "label" + top: "accuracy" + include { stage: "val" } +} +layer { + name: "loss" + type: "SoftmaxWithLoss" + bottom: "fc8" + bottom: "label" + top: "loss" + exclude { stage: "deploy" } +} +layer { + name: "softmax" + type: "Softmax" + bottom: "fc8" + top: "softmax" + include { stage: "deploy" } +} diff --git a/cars/data-aug-investigations/data-aug.ipynb b/cars/data-aug-investigations/data-aug.ipynb index 8da1327..acfd734 100644 --- a/cars/data-aug-investigations/data-aug.ipynb +++ b/cars/data-aug-investigations/data-aug.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 14, + "execution_count": 1, "id": "3c568ab9", "metadata": {}, "outputs": [], @@ -33,7 +33,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 2, "id": "1b2471d2", "metadata": {}, "outputs": [], @@ -75,7 +75,7 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ @@ -86,7 +86,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 4, "id": "c664a31c", "metadata": {}, "outputs": [ @@ -94,7 +94,7 @@ "output_type": "display_data", "data": { "text/plain": "
", - "image/svg+xml": "\n\n\n \n \n \n \n 2021-04-19T23:24:37.147700\n image/svg+xml\n \n \n Matplotlib v3.4.1, https://matplotlib.org/\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n", + "image/svg+xml": "\n\n\n \n \n \n \n 2021-04-20T07:39:58.933563\n image/svg+xml\n \n \n Matplotlib v3.4.1, https://matplotlib.org/\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n", "image/png": "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\n" }, "metadata": { @@ -120,15 +120,15 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 5, "metadata": {}, "outputs": [ { "output_type": "display_data", "data": { "text/plain": "
", - "image/svg+xml": "\n\n\n \n \n \n \n 2021-04-19T23:39:59.623821\n image/svg+xml\n \n \n Matplotlib v3.4.1, https://matplotlib.org/\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n", - "image/png": "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\n" + "image/svg+xml": "\n\n\n \n \n \n \n 2021-04-20T07:39:59.201174\n image/svg+xml\n \n \n Matplotlib v3.4.1, https://matplotlib.org/\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n", + "image/png": "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\n" }, "metadata": { "needs_background": "light"