pms/umz21
4
2
Fork 1
Code Issues Pull Requests Releases Wiki Activity

Wykład 11 - sieci neuronowe w praktyce - poprawki

Browse Source
This commit is contained in:
Paweł Skórzewski 2021-05-26 11:25:35 +02:00
parent f531933b38
commit 8c67bcbc33
2 changed files with 107 additions and 137 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

75
wyk/10_Propagacja_wsteczna.ipynb
View File

@ -858,7 +858,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 52, "execution_count": 1,
"metadata": { "metadata": {
"slideshow": { "slideshow": {
"slide_type": "subslide" "slide_type": "subslide"
@ -878,7 +878,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 53, "execution_count": 2,
"metadata": { "metadata": {
"slideshow": { "slideshow": {
"slide_type": "notes" "slide_type": "notes"
@ -901,7 +901,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 54, "execution_count": 3,
"metadata": { "metadata": {
"slideshow": { "slideshow": {
"slide_type": "subslide" "slide_type": "subslide"
@ -934,7 +934,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 55, "execution_count": 4,
"metadata": { "metadata": {
"slideshow": { "slideshow": {
"slide_type": "subslide" "slide_type": "subslide"
@ -969,7 +969,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 56, "execution_count": 9,
"metadata": { "metadata": {
"scrolled": true, "scrolled": true,
"slideshow": { "slideshow": {
@ -981,19 +981,19 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Model: \"sequential_21\"\n", "Model: \"sequential_1\"\n",
"_________________________________________________________________\n", "_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n", "Layer (type) Output Shape Param # \n",
"=================================================================\n", "=================================================================\n",
"dense_59 (Dense) (None, 512) 401920 \n", "dense_3 (Dense) (None, 512) 401920 \n",
"_________________________________________________________________\n", "_________________________________________________________________\n",
"dropout_2 (Dropout) (None, 512) 0 \n", "dropout (Dropout) (None, 512) 0 \n",
"_________________________________________________________________\n", "_________________________________________________________________\n",
"dense_60 (Dense) (None, 512) 262656 \n", "dense_4 (Dense) (None, 512) 262656 \n",
"_________________________________________________________________\n", "_________________________________________________________________\n",
"dropout_3 (Dropout) (None, 512) 0 \n", "dropout_1 (Dropout) (None, 512) 0 \n",
"_________________________________________________________________\n", "_________________________________________________________________\n",
"dense_61 (Dense) (None, 10) 5130 \n", "dense_5 (Dense) (None, 10) 5130 \n",
"=================================================================\n", "=================================================================\n",
"Total params: 669,706\n", "Total params: 669,706\n",
"Trainable params: 669,706\n", "Trainable params: 669,706\n",
@ -1009,12 +1009,13 @@
"model.add(Dense(512, activation='relu'))\n", "model.add(Dense(512, activation='relu'))\n",
"model.add(Dropout(0.2))\n", "model.add(Dropout(0.2))\n",
"model.add(Dense(num_classes, activation='softmax'))\n", "model.add(Dense(num_classes, activation='softmax'))\n",
"model.summary()" "\n",
"model.summary() # wyświetl podsumowanie architektury sieci"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 57, "execution_count": 10,
"metadata": { "metadata": {
"slideshow": { "slideshow": {
"slide_type": "subslide" "slide_type": "subslide"
@ -1035,7 +1036,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 58, "execution_count": 12,
"metadata": { "metadata": {
"slideshow": { "slideshow": {
"slide_type": "subslide" "slide_type": "subslide"
@ -1046,25 +1047,35 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Epoch 1/5\n", "Epoch 1/10\n",
"469/469 [==============================] - 11s 23ms/step - loss: 0.2463 - accuracy: 0.9238 - val_loss: 0.1009 - val_accuracy: 0.9690\n", "469/469 [==============================] - 20s 42ms/step - loss: 0.0957 - accuracy: 0.9708 - val_loss: 0.0824 - val_accuracy: 0.9758\n",
"Epoch 2/5\n", "Epoch 2/10\n",
"469/469 [==============================] - 10s 22ms/step - loss: 0.1042 - accuracy: 0.9681 - val_loss: 0.0910 - val_accuracy: 0.9739\n", "469/469 [==============================] - 20s 43ms/step - loss: 0.0693 - accuracy: 0.9793 - val_loss: 0.0807 - val_accuracy: 0.9772\n",
"Epoch 3/5\n", "Epoch 3/10\n",
"469/469 [==============================] - 11s 23ms/step - loss: 0.0774 - accuracy: 0.9762 - val_loss: 0.0843 - val_accuracy: 0.9755\n", "469/469 [==============================] - 18s 38ms/step - loss: 0.0563 - accuracy: 0.9827 - val_loss: 0.0861 - val_accuracy: 0.9758\n",
"Epoch 4/5\n", "Epoch 4/10\n",
"469/469 [==============================] - 11s 24ms/step - loss: 0.0606 - accuracy: 0.9815 - val_loss: 0.0691 - val_accuracy: 0.9818\n", "469/469 [==============================] - 18s 37ms/step - loss: 0.0485 - accuracy: 0.9857 - val_loss: 0.0829 - val_accuracy: 0.9794\n",
"Epoch 5/5\n", "Epoch 5/10\n",
"469/469 [==============================] - 10s 22ms/step - loss: 0.0504 - accuracy: 0.9848 - val_loss: 0.0886 - val_accuracy: 0.9772\n" "469/469 [==============================] - 19s 41ms/step - loss: 0.0428 - accuracy: 0.9876 - val_loss: 0.0955 - val_accuracy: 0.9766\n",
"Epoch 6/10\n",
"469/469 [==============================] - 22s 47ms/step - loss: 0.0377 - accuracy: 0.9887 - val_loss: 0.0809 - val_accuracy: 0.9794\n",
"Epoch 7/10\n",
"469/469 [==============================] - 17s 35ms/step - loss: 0.0338 - accuracy: 0.9904 - val_loss: 0.1028 - val_accuracy: 0.9788\n",
"Epoch 8/10\n",
"469/469 [==============================] - 17s 36ms/step - loss: 0.0322 - accuracy: 0.9911 - val_loss: 0.0937 - val_accuracy: 0.9815\n",
"Epoch 9/10\n",
"469/469 [==============================] - 18s 37ms/step - loss: 0.0303 - accuracy: 0.9912 - val_loss: 0.0916 - val_accuracy: 0.9829.0304 - accu\n",
"Epoch 10/10\n",
"469/469 [==============================] - 16s 34ms/step - loss: 0.0263 - accuracy: 0.9926 - val_loss: 0.0958 - val_accuracy: 0.9812\n"
] ]
}, },
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"<tensorflow.python.keras.callbacks.History at 0x1ed6e0565b0>" "<tensorflow.python.keras.callbacks.History at 0x228eac95ac0>"
] ]
}, },
"execution_count": 58, "execution_count": 12,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -1072,13 +1083,13 @@
"source": [ "source": [
"model.compile(loss='categorical_crossentropy', optimizer=keras.optimizers.RMSprop(), metrics=['accuracy'])\n", "model.compile(loss='categorical_crossentropy', optimizer=keras.optimizers.RMSprop(), metrics=['accuracy'])\n",
"\n", "\n",
"model.fit(x_train, y_train, batch_size=128, epochs=5, verbose=1,\n", "model.fit(x_train, y_train, batch_size=128, epochs=10, verbose=1,\n",
" validation_data=(x_test, y_test))" " validation_data=(x_test, y_test))"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 60, "execution_count": 8,
"metadata": { "metadata": {
"slideshow": { "slideshow": {
"slide_type": "subslide" "slide_type": "subslide"
@ -1089,8 +1100,8 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Test loss: 0.08859136700630188\n", "Test loss: 0.0757974311709404\n",
"Test accuracy: 0.9771999716758728\n" "Test accuracy: 0.9810000061988831\n"
] ]
} }
], ],
@ -1109,7 +1120,7 @@
} }
}, },
"source": [ "source": [
"Warstwa _dropout_ to metoda regularyzacji, służy zapobieganiu nadmiernemu dopasowaniu sieci. Polega na tym, że część węzłów sieci jest usuwana w sposób losowy." "Warstwa *dropout* to metoda regularyzacji, służy zapobieganiu nadmiernemu dopasowaniu sieci. Polega na tym, że część węzłów sieci jest usuwana w sposób losowy."
] ]
}, },
{ {
@ -1884,7 +1895,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.5" "version": "3.8.3"
}, },
"livereveal": { "livereveal": {
"start_slideshow_at": "selected", "start_slideshow_at": "selected",

169
wyk/11_Wielowarstwowe_sieci_neuronowe.ipynb
View File

File diff suppressed because one or more lines are too long