From 668e8ce61db8c4b6d289a8fa66fa4481905d3cc4 Mon Sep 17 00:00:00 2001
From: Michiel_VE <r0794174@student.thomasmore.be>
Date: Sat, 1 Jun 2024 12:35:39 +0300
Subject: [PATCH] update what image is send
---
Func/ClassifierModule.py | 15 +++---
Func/DrawImages.py | 20 +++++++
Func/Helpers.py | 5 +-
Model/labels.txt | 4 +-
main.py | 3 +-
trainModel.ipynb | 114 +++++++++++++++++++++++----------------
trainModel.py | 4 +-
7 files changed, 106 insertions(+), 59 deletions(-)
create mode 100644 Func/DrawImages.py
diff --git a/Func/ClassifierModule.py b/Func/ClassifierModule.py
index 9b784d8..672e119 100644
--- a/Func/ClassifierModule.py
+++ b/Func/ClassifierModule.py
@@ -1,6 +1,7 @@
import keras
import numpy as np
import cv2
+from cvzone.HandTrackingModule import HandDetector
class Classifier:
@@ -20,7 +21,8 @@ class Classifier:
else:
print("No Labels Found")
- def getPrediction(self, img, draw=True, pos=(50, 50), scale=2, color=(0, 255, 0)):
+ def getPrediction(self, img):
+ cv2.imshow("imgFixed classifier", img)
img_resized = cv2.resize(img, (224, 224))
image_array = np.asarray(img_resized)
normalized_image_array = (image_array.astype(np.float32) / 127.0) - 1
@@ -30,30 +32,29 @@ class Classifier:
prediction = self.model.predict(self.data)
index_val = np.argmax(prediction)
- if draw and self.labels_path:
- label_text = str(self.list_labels[index_val])
- cv2.putText(img, label_text, pos, cv2.FONT_HERSHEY_COMPLEX, scale, color, 2)
-
return list(prediction[0]), index_val
def main():
cap = cv2.VideoCapture(0)
+ detector = HandDetector(maxHands=1)
mask_classifier = Classifier('Model/keras_model.h5', 'Model/labels.txt')
while True:
ret, frame = cap.read()
+ hands, img = detector.findHands(frame)
+
if not ret:
print("Failed to capture frame")
break
- prediction = mask_classifier.getPrediction(frame)
+ prediction = mask_classifier.getPrediction(img)
print("Prediction:", prediction)
- cv2.imshow("Image", frame)
+
if cv2.waitKey(1) & 0xFF == ord('q'):
break
diff --git a/Func/DrawImages.py b/Func/DrawImages.py
new file mode 100644
index 0000000..be948e2
--- /dev/null
+++ b/Func/DrawImages.py
@@ -0,0 +1,20 @@
+import matplotlib.pyplot as plt
+import numpy as np
+
+
+def plot_images(images, labels, class_indices):
+ num_images = len(images)
+ grid_size = int(np.ceil(np.sqrt(num_images)))
+
+ plt.figure(figsize=(15, 15))
+ for i in range(num_images):
+ plt.subplot(grid_size, grid_size, i + 1)
+ img = images[i]
+ plt.imshow(img)
+
+ label = np.argmax(labels[i])
+ label_name = list(class_indices.keys())[list(class_indices.values()).index(label)]
+ plt.title(label_name)
+ plt.axis('off')
+ plt.tight_layout()
+ plt.show()
\ No newline at end of file
diff --git a/Func/Helpers.py b/Func/Helpers.py
index a096e33..d8c2026 100644
--- a/Func/Helpers.py
+++ b/Func/Helpers.py
@@ -21,7 +21,8 @@ def CalculateHeight(size, h, w, imgCropped, imgFixed):
def GetPrediction(classifier, imgFixed):
- prediction, index = classifier.getPrediction(imgFixed, draw=False)
+ cv2.imshow('imgFixed helper', imgFixed)
+ prediction, index = classifier.getPrediction(imgFixed)
return prediction, index
@@ -35,4 +36,4 @@ def GetLabels(path):
letter = parts[1]
letters.append(letter)
- return letters
+ return letters
\ No newline at end of file
diff --git a/Model/labels.txt b/Model/labels.txt
index 30b5960..5fbcfab 100644
--- a/Model/labels.txt
+++ b/Model/labels.txt
@@ -1,4 +1,6 @@
0 A
1 B
2 C
-3 D
\ No newline at end of file
+3 D
+4 E
+5 F
\ No newline at end of file
diff --git a/main.py b/main.py
index 4a6a59a..418e488 100644
--- a/main.py
+++ b/main.py
@@ -45,6 +45,7 @@ while True:
else:
CalculateHeight(size, h, w, imgCropped, imgFixed)
+ cv2.imshow("imgFixed", imgFixed)
prediction, index = GetPrediction(classifier, imgFixed)
print('pred', prediction)
@@ -52,7 +53,7 @@ while True:
cv2.putText(imgOutput, letters[index], (x, y), cv2.FONT_HERSHEY_TRIPLEX, 2, (255, 0, 255), 2)
- cv2.imshow("img", imgOutput)
+ cv2.imshow("img main", imgOutput)
key = cv2.waitKey(1)
if key == ord('p'):
diff --git a/trainModel.ipynb b/trainModel.ipynb
index 97c3462..e849f59 100644
--- a/trainModel.ipynb
+++ b/trainModel.ipynb
@@ -2,76 +2,80 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 51,
"id": "62c6c5c3-d2ba-4e79-b533-828c3083e8ea",
- "metadata": {},
+ "metadata": {
+ "is_executing": true
+ },
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
+ "Num GPUs Available: 1\n",
+ "Physical devices cannot be modified after being initialized\n",
"Found 1529 images belonging to 6 classes.\n",
"Found 380 images belonging to 6 classes.\n",
"Epoch 1/10\n",
- "48/48 [==============================] - 29s 470ms/step - loss: 1.0985 - accuracy: 0.5284 - val_loss: 0.7411 - val_accuracy: 0.6868\n",
+ "24/24 [==============================] - 21s 851ms/step - loss: 1.1108 - accuracy: 0.5134 - val_loss: 0.8370 - val_accuracy: 0.6842\n",
"Epoch 2/10\n",
- "48/48 [==============================] - 20s 417ms/step - loss: 0.5369 - accuracy: 0.7757 - val_loss: 0.5103 - val_accuracy: 0.7921\n",
+ "24/24 [==============================] - 21s 862ms/step - loss: 0.6156 - accuracy: 0.7613 - val_loss: 0.4063 - val_accuracy: 0.8447\n",
"Epoch 3/10\n",
- "48/48 [==============================] - 20s 417ms/step - loss: 0.2837 - accuracy: 0.8875 - val_loss: 0.8421 - val_accuracy: 0.7105\n",
+ "24/24 [==============================] - 22s 915ms/step - loss: 0.2704 - accuracy: 0.9006 - val_loss: 0.2283 - val_accuracy: 0.9316\n",
"Epoch 4/10\n",
- "48/48 [==============================] - 20s 417ms/step - loss: 0.1952 - accuracy: 0.9228 - val_loss: 0.2502 - val_accuracy: 0.8947\n",
+ "24/24 [==============================] - 22s 909ms/step - loss: 0.1532 - accuracy: 0.9477 - val_loss: 0.1145 - val_accuracy: 0.9579\n",
"Epoch 5/10\n",
- "48/48 [==============================] - 20s 419ms/step - loss: 0.1007 - accuracy: 0.9647 - val_loss: 0.0922 - val_accuracy: 0.9632\n",
+ "24/24 [==============================] - 22s 905ms/step - loss: 0.1324 - accuracy: 0.9516 - val_loss: 0.2525 - val_accuracy: 0.9026\n",
"Epoch 6/10\n",
- "48/48 [==============================] - 19s 404ms/step - loss: 0.0690 - accuracy: 0.9719 - val_loss: 0.1608 - val_accuracy: 0.9316\n",
+ "24/24 [==============================] - 22s 912ms/step - loss: 0.0737 - accuracy: 0.9719 - val_loss: 0.0519 - val_accuracy: 0.9816\n",
"Epoch 7/10\n",
- "48/48 [==============================] - 19s 406ms/step - loss: 0.0707 - accuracy: 0.9745 - val_loss: 0.1129 - val_accuracy: 0.9500\n",
+ "24/24 [==============================] - 23s 952ms/step - loss: 0.0663 - accuracy: 0.9797 - val_loss: 0.0544 - val_accuracy: 0.9842\n",
"Epoch 8/10\n",
- "48/48 [==============================] - 19s 401ms/step - loss: 0.0674 - accuracy: 0.9791 - val_loss: 0.0428 - val_accuracy: 0.9868\n",
+ "24/24 [==============================] - 22s 918ms/step - loss: 0.0482 - accuracy: 0.9817 - val_loss: 0.0489 - val_accuracy: 0.9711\n",
"Epoch 9/10\n",
- "48/48 [==============================] - 19s 400ms/step - loss: 0.0260 - accuracy: 0.9922 - val_loss: 0.0619 - val_accuracy: 0.9711\n",
+ "24/24 [==============================] - 22s 928ms/step - loss: 0.0240 - accuracy: 0.9908 - val_loss: 0.0337 - val_accuracy: 0.9868\n",
"Epoch 10/10\n",
- "48/48 [==============================] - 20s 404ms/step - loss: 0.0142 - accuracy: 0.9961 - val_loss: 0.0146 - val_accuracy: 0.9947\n",
- "12/12 [==============================] - 4s 329ms/step - loss: 0.0094 - accuracy: 0.9974\n",
- "Test loss: 0.009386303834617138, Test accuracy: 0.9973683953285217\n",
- "Model: \"sequential\"\n",
+ "24/24 [==============================] - 22s 911ms/step - loss: 0.0224 - accuracy: 0.9922 - val_loss: 0.0411 - val_accuracy: 0.9895\n",
+ "6/6 [==============================] - 4s 717ms/step - loss: 0.0078 - accuracy: 1.0000\n",
+ "Test loss: 0.007844111882150173, Test accuracy: 1.0\n",
+ "Model: \"sequential_32\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
- " conv2d (Conv2D) (None, 222, 222, 32) 896 \n",
+ " conv2d_128 (Conv2D) (None, 222, 222, 32) 896 \n",
" \n",
- " max_pooling2d (MaxPooling2D (None, 111, 111, 32) 0 \n",
- " ) \n",
+ " max_pooling2d_128 (MaxPooli (None, 111, 111, 32) 0 \n",
+ " ng2D) \n",
" \n",
- " conv2d_1 (Conv2D) (None, 109, 109, 64) 18496 \n",
+ " conv2d_129 (Conv2D) (None, 109, 109, 64) 18496 \n",
" \n",
- " max_pooling2d_1 (MaxPooling (None, 54, 54, 64) 0 \n",
- " 2D) \n",
+ " max_pooling2d_129 (MaxPooli (None, 54, 54, 64) 0 \n",
+ " ng2D) \n",
" \n",
- " conv2d_2 (Conv2D) (None, 52, 52, 128) 73856 \n",
+ " conv2d_130 (Conv2D) (None, 52, 52, 128) 73856 \n",
" \n",
- " max_pooling2d_2 (MaxPooling (None, 26, 26, 128) 0 \n",
- " 2D) \n",
+ " max_pooling2d_130 (MaxPooli (None, 26, 26, 128) 0 \n",
+ " ng2D) \n",
" \n",
- " conv2d_3 (Conv2D) (None, 24, 24, 256) 295168 \n",
+ " conv2d_131 (Conv2D) (None, 24, 24, 256) 295168 \n",
" \n",
- " max_pooling2d_3 (MaxPooling (None, 12, 12, 256) 0 \n",
- " 2D) \n",
+ " max_pooling2d_131 (MaxPooli (None, 12, 12, 256) 0 \n",
+ " ng2D) \n",
" \n",
- " flatten (Flatten) (None, 36864) 0 \n",
+ " flatten_32 (Flatten) (None, 36864) 0 \n",
" \n",
- " dense (Dense) (None, 256) 9437440 \n",
+ " dense_96 (Dense) (None, 256) 9437440 \n",
" \n",
- " dense_1 (Dense) (None, 128) 32896 \n",
+ " dense_97 (Dense) (None, 128) 32896 \n",
" \n",
- " dense_2 (Dense) (None, 6) 774 \n",
+ " dense_98 (Dense) (None, 6) 774 \n",
" \n",
"=================================================================\n",
"Total params: 9,859,526\n",
"Trainable params: 9,859,526\n",
"Non-trainable params: 0\n",
"_________________________________________________________________\n",
- "It took: 3.55 minutes\n"
+ "It took: 3.74 minutes\n"
]
}
],
@@ -84,21 +88,30 @@
"from tensorflow.keras.callbacks import EarlyStopping\n",
"from tensorflow.keras.optimizers import Adam\n",
"import tensorflow as tf\n",
- "from keras import layers, models\n",
"\n",
"from Func.getSubFolders import count_sub_folders\n",
"\n",
+ "\n",
"path = 'Data'\n",
"output = 'Model/keras_model.h5'\n",
"start_time = time.time()\n",
"\n",
- "# runtime error\n",
- "# physical_devices = tf.config.experimental.list_physical_devices('GPU')\n",
- "# print(\"Num GPUs Available: \", len(physical_devices))\n",
- "# if len(physical_devices) > 0:\n",
- "# tf.config.experimental.set_memory_growth(physical_devices[0], True)\n",
- "# else:\n",
- "# print(\"No GPU available. Using CPU.\")\n",
+ "physical_devices = tf.config.list_physical_devices('GPU')\n",
+ "print(\"Num GPUs Available: \", len(physical_devices))\n",
+ "if len(physical_devices) > 0:\n",
+ " try:\n",
+ " # Set memory growth to true\n",
+ " for device in physical_devices:\n",
+ " tf.config.experimental.set_memory_growth(device, True)\n",
+ " \n",
+ " # Optionally, you can set a memory limit if necessary\n",
+ " # tf.config.set_logical_device_configuration(\n",
+ " # physical_devices[0],\n",
+ " # [tf.config.LogicalDeviceConfiguration(memory_limit=4096)]) # Set to 4GB\n",
+ " except RuntimeError as e:\n",
+ " print(e)\n",
+ "else:\n",
+ " print(\"No GPU available. Using CPU.\")\n",
"\n",
"\n",
"# Step 1: Load and Preprocess Images\n",
@@ -113,26 +126,35 @@
"\n",
"test_datagen = ImageDataGenerator(rescale=1. / 255)\n",
"\n",
+ "\n",
"# Step 2: Label the Data\n",
"train_set = datagen.flow_from_directory(\n",
" path,\n",
- " target_size=(224, 224),\n",
- " batch_size=32,\n",
+ " target_size=(300, 300),\n",
+ " batch_size=64,\n",
" class_mode='categorical',\n",
" subset='training'\n",
")\n",
"\n",
"test_set = datagen.flow_from_directory(\n",
" path,\n",
- " target_size=(224, 224),\n",
- " batch_size=32,\n",
+ " target_size=(300, 300),\n",
+ " batch_size=64,\n",
" class_mode='categorical',\n",
" subset='validation'\n",
")\n",
"\n",
+ "# draw Images\n",
+ "# images, labels = next(test_set)\n",
+ "\n",
+ "# class_indices = test_set.class_indices\n",
+ "# plot_images(images, labels, class_indices)\n",
+ "\n",
+ "\n",
+ "\n",
"# Step 4: Build the Model\n",
"model = Sequential()\n",
- "model.add(Conv2D(32, (3, 3), input_shape=(224, 224, 3), activation='relu'))\n",
+ "model.add(Conv2D(32, (3, 3), input_shape=(300, 300, 3), activation='relu'))\n",
"model.add(MaxPooling2D(pool_size=(2, 2)))\n",
"\n",
"model.add(Conv2D(64, (3, 3), activation='relu'))\n",
@@ -214,7 +236,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "67803a21-51f7-4bec-98fc-4efa8f75bab9",
+ "id": "ec102c63-b7d9-4f22-9f3e-a6bd12995a4f",
"metadata": {},
"outputs": [],
"source": []
diff --git a/trainModel.py b/trainModel.py
index 9e81941..860f0b3 100644
--- a/trainModel.py
+++ b/trainModel.py
@@ -37,7 +37,7 @@ train_set = datagen.flow_from_directory(
test_set = datagen.flow_from_directory(
path,
- target_size=(224, 224),
+ target_size=(300, 300),
batch_size=32,
class_mode='categorical',
subset='validation'
@@ -45,7 +45,7 @@ test_set = datagen.flow_from_directory(
# Step 4: Build the Model
model = Sequential()
-model.add(Conv2D(32, (3, 3), input_shape=(224, 224, 3), activation='relu'))
+model.add(Conv2D(32, (3, 3), input_shape=(300, 300, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3), activation='relu'))
--
GitLab