Added temp results from README, added more hyperparameter runs and added temporal results to presentation

2021-06-08 21:50:31 +00:00 · 2021-06-08 21:50:31 +00:00 · 33941658b9
parent 60a48ce49c
commit 33941658b9
3 changed files with 312 additions and 18 deletions
--- a/1-first-project/Slides/IUI_MP1_Presentation-1.pptx
+++ b/1-first-project/Slides/IUI_MP1_Presentation-1.pptx
--- a/1-first-project/tdt/Hyperparameter.ipynb
+++ b/1-first-project/tdt/Hyperparameter.ipynb
@ -3,7 +3,7 @@
  {
   "cell_type": "code",
   "execution_count": 1,
-   "id": "cf20b791",
+   "id": "25685460",
   "metadata": {},
   "outputs": [],
   "source": [
@ -14,7 +14,7 @@
  {
   "cell_type": "code",
   "execution_count": 2,
-   "id": "8114cccf",
+   "id": "a7b5d6ab",
   "metadata": {},
   "outputs": [],
   "source": [
@ -30,7 +30,7 @@
  {
   "cell_type": "code",
   "execution_count": 3,
-   "id": "e1ebb5fe",
+   "id": "8a37e95b",
   "metadata": {},
   "outputs": [],
   "source": [
@ -52,7 +52,7 @@
  {
   "cell_type": "code",
   "execution_count": 4,
-   "id": "e2315c69",
+   "id": "53e288a8",
   "metadata": {},
   "outputs": [],
   "source": [
@ -73,7 +73,7 @@
  {
   "cell_type": "code",
   "execution_count": 5,
-   "id": "62536ff0",
+   "id": "0e638fb8",
   "metadata": {},
   "outputs": [],
   "source": [
@ -97,7 +97,7 @@
  {
   "cell_type": "code",
   "execution_count": 6,
-   "id": "dd1162bb",
+   "id": "5080bf16",
   "metadata": {},
   "outputs": [],
   "source": [
@ -111,7 +111,7 @@
  {
   "cell_type": "code",
   "execution_count": 7,
-   "id": "6879e37a",
+   "id": "41f26d6c",
   "metadata": {},
   "outputs": [],
   "source": [
@ -138,7 +138,7 @@
  {
   "cell_type": "code",
   "execution_count": 8,
-   "id": "51f25f8e",
+   "id": "9bf4ea28",
   "metadata": {},
   "outputs": [],
   "source": [
@ -174,7 +174,7 @@
  {
   "cell_type": "code",
   "execution_count": 9,
-   "id": "4ccd56dd",
+   "id": "fde0b3cf",
   "metadata": {},
   "outputs": [],
   "source": [
@ -197,7 +197,7 @@
  {
   "cell_type": "code",
   "execution_count": 10,
-   "id": "4ed39aad",
+   "id": "9712dd25",
   "metadata": {},
   "outputs": [],
   "source": [
@ -218,7 +218,7 @@
  {
   "cell_type": "code",
   "execution_count": 11,
-   "id": "92e85d4f",
+   "id": "6decb953",
   "metadata": {},
   "outputs": [],
   "source": [
@ -230,7 +230,7 @@
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "f81aa159",
+   "id": "ff6a75e9",
   "metadata": {},
   "outputs": [
    {
@ -891,7 +891,55 @@
      "              Dense Count 1: 2\n",
      "              Dense Neurons 1: 1800\n",
      "              Dense Count 2: 3\n",
-      "              Dense Neurons 2: 1200\n"
+      "              Dense Neurons 2: 1200\n",
+      "Accuracy: 78.40\n",
+      "Testing with: Threshold: 70\n",
+      "              Leeway: 0\n",
+      "              Epoch: 20\n",
+      "              Dense Count 1: 2\n",
+      "              Dense Neurons 1: 1800\n",
+      "              Dense Count 2: 3\n",
+      "              Dense Neurons 2: 1800\n",
+      "Accuracy: 78.09\n",
+      "Testing with: Threshold: 70\n",
+      "              Leeway: 0\n",
+      "              Epoch: 20\n",
+      "              Dense Count 1: 2\n",
+      "              Dense Neurons 1: 1800\n",
+      "              Dense Count 2: 3\n",
+      "              Dense Neurons 2: 2400\n",
+      "Accuracy: 77.56\n",
+      "Testing with: Threshold: 70\n",
+      "              Leeway: 0\n",
+      "              Epoch: 20\n",
+      "              Dense Count 1: 2\n",
+      "              Dense Neurons 1: 2400\n",
+      "              Dense Count 2: 1\n",
+      "              Dense Neurons 2: 600\n",
+      "Accuracy: 78.10\n",
+      "Testing with: Threshold: 70\n",
+      "              Leeway: 0\n",
+      "              Epoch: 20\n",
+      "              Dense Count 1: 2\n",
+      "              Dense Neurons 1: 2400\n",
+      "              Dense Count 2: 1\n",
+      "              Dense Neurons 2: 1200\n",
+      "Accuracy: 78.49\n",
+      "Testing with: Threshold: 70\n",
+      "              Leeway: 0\n",
+      "              Epoch: 20\n",
+      "              Dense Count 1: 2\n",
+      "              Dense Neurons 1: 2400\n",
+      "              Dense Count 2: 1\n",
+      "              Dense Neurons 2: 1800\n",
+      "Accuracy: 78.24\n",
+      "Testing with: Threshold: 70\n",
+      "              Leeway: 0\n",
+      "              Epoch: 20\n",
+      "              Dense Count 1: 2\n",
+      "              Dense Neurons 1: 2400\n",
+      "              Dense Count 2: 1\n",
+      "              Dense Neurons 2: 2400\n"
     ]
    }
   ],
@ -932,7 +980,7 @@
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "ee06862c",
+   "id": "89a47c03",
   "metadata": {},
   "outputs": [],
   "source": [
@ -942,7 +990,7 @@
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "32c1ff00",
+   "id": "7520408c",
   "metadata": {},
   "outputs": [],
   "source": [
--- a/1-first-project/tdt/README.md
+++ b/1-first-project/tdt/README.md
@ -74,6 +74,7 @@ This segment are notes dedicated to the neural network itself.
 ```python
 thresh      = 100
 leeway      = 5
+epoch       = 20

 model = Sequential()

@ -102,6 +103,7 @@ Evaluate on test data
 ```python
 thresh      = 75
 leeway      = 3
+epoch       = 20

 model = Sequential()

@ -130,6 +132,7 @@ Evaluate on test data
 ```python
 thresh      = 10
 leeway      = 3
+epoch       = 20

 model = Sequential()

@ -153,11 +156,12 @@ Evaluate on test data
 82/82 [==============================] - 0s 2ms/step - loss: 2.5231 - acc: 0.3696
 ```

-#### Test4 (71.51%)
+#### Test4 (69.66%)

 ```python
 thresh      = 50
 leeway      = 3
+epoch       = 20

 model = Sequential()

@ -178,7 +182,249 @@ model.add(Dense(26, activation='softmax'))

 ```
 Evaluate on test data
-82/82 [==============================] - 0s 2ms/step - loss: 1.5005 - acc: 0.7151
+82/82 [==============================] - 0s 2ms/step - loss: 1.6965 - acc: 0.6966
 ```

-#### Test5 ()
+
+#### Test5 (73.13%)
+
+```python
+thresh      = 60
+leeway      = 3
+epoch       = 20
+
+model = Sequential()
+
+model.add(Flatten(input_shape=X_filter[0].shape))
+
+model.add(BatchNormalization())
+
+model.add(Dense(1560, activation='relu'))
+
+model.add(Dense(750, activation='relu'))
+
+model.add(Dense(300, activation='relu'))
+
+model.add(Dense(156, activation='relu'))
+
+model.add(Dense(26, activation='softmax'))
+```
+
+```
+Evaluate on test data
+82/82 [==============================] - 0s 2ms/step - loss: 1.4886 - acc: 0.7313
+```
+
+#### Test6 (75.68%)
+
+```python
+thresh      = 68
+leeway      = 3
+epoch       = 20
+
+model = Sequential()
+
+model.add(Flatten(input_shape=X_filter[0].shape))
+
+model.add(BatchNormalization())
+
+model.add(Dense(1560, activation='relu'))
+
+model.add(Dense(750, activation='relu'))
+
+model.add(Dense(300, activation='relu'))
+
+model.add(Dense(156, activation='relu'))
+
+model.add(Dense(26, activation='softmax'))
+```
+
+```
+Evaluate on test data
+82/82 [==============================] - 0s 2ms/step - loss: 1.4227 - acc: 0.7568
+```
+
+#### Test7 (76.07%)
+
+```python
+thresh      = 68
+leeway      = 3
+epoch       = 30
+
+model = Sequential()
+
+model.add(Flatten(input_shape=X_filter[0].shape))
+
+model.add(BatchNormalization())
+
+model.add(Dense(1560, activation='relu'))
+
+model.add(Dense(750, activation='relu'))
+
+model.add(Dense(300, activation='relu'))
+
+model.add(Dense(156, activation='relu'))
+
+model.add(Dense(26, activation='softmax'))
+```
+
+```
+Evaluate on test data
+82/82 [==============================] - 0s 2ms/step - loss: 1.5863 - acc: 0.7607
+```
+
+#### Test8 (75.49%)
+
+```python
+THRESH = 70
+LEEWAY = 3
+EPOCH = 30
+
+DENSE_COUNT = 5
+DENSE_NEURONS = 1800
+```
+
+```
+Evaluate on test data
+21/21 [==============================] - 0s 2ms/step - loss: 1.5598 - acc: 0.7684
+```
+
+#### Test9 (78.15%)
+
+```python
+THRESH = 70
+LEEWAY = 1
+EPOCH = 30
+
+DENSE_COUNT = 5
+DENSE_NEURONS = 1800
+```
+
+```
+Evaluate on test data
+21/21 [==============================] - 0s 2ms/step - loss: 1.4677 - acc: 0.7815
+```
+
+#### Test10 (77.64%)
+
+```python
+THRESH = 70
+LEEWAY = 0
+EPOCH = 30
+
+DENSE_COUNT = 5
+DENSE_NEURONS = 1900
+```
+
+
+#### Test11 (77.41%)
+
+```python
+THRESH = 70
+LEEWAY = 0
+EPOCH = 30
+
+DENSE_COUNT = 5
+DENSE_NEURONS = 1800
+```
+
+#### Test12 (73.90%)
+
+```python
+THRESH = 70
+LEEWAY = 0
+EPOCH = 30
+
+DENSE_COUNT = 5
+DENSE_NEURONS = 1800
+
+DENSE_COUNT = 5
+DENSE_NEURONS = 900
+```
+
+#### Test13 (78.89%)
+
+NORM->FLAT->DENSE
+```python
+THRESH = 70
+LEEWAY = 0
+EPOCH = 30
+
+DENSE_COUNT = 5
+DENSE_NEURONS = 1900
+```
+
+#### Test14 (79.04%)
+
+NORM->FLAT->DENSE
+```python
+THRESH = 70
+LEEWAY = 0
+EPOCH = 30
+
+DENSE_COUNT = 5
+DENSE_NEURONS = 1800
+```
+
+#### Test15 (79.00%)
+
+NORM->FLAT->DENSE
+```python
+THRESH = 70
+LEEWAY = 0
+EPOCH = 30
+
+DENSE_COUNT = 5
+DENSE_NEURONS = 1700
+```
+
+#### Test16 (78.69%)
+
+NORM->FLAT->DENSE
+```python
+THRESH = 70
+LEEWAY = 0
+EPOCH = 30
+
+DENSE_COUNT = 5
+DENSE_NEURONS = 1600
+```
+
+#### Test17 (78.57%)
+
+NORM->FLAT->DENSE
+```python
+THRESH = 70
+LEEWAY = 0
+EPOCH = 30
+
+DENSE_COUNT = 4
+DENSE_NEURONS = 1800
+```
+
+#### Test18 (78.12%)
+
+NORM->FLAT->DENSE
+```python
+THRESH = 70
+LEEWAY = 0
+EPOCH = 30
+
+DENSE_COUNT = 6
+DENSE_NEURONS = 1800
+```
+
+#### Test19 (79.13%)
+
+NORM->FLAT->DENSE
+```python
+THRESH = 70
+LEEWAY = 0
+EPOCH = 30
+
+DENSE_COUNT = 3
+DENSE_NEURONS = 1800
+
+DENSE2_COUNT = 2
+DENSE2_NEURONS = 1200
+```