"import matplotlib.pyplot as plt import numpy as np import pandas as pd import seaborn…
- User
"import matplotlib.pyplot as plt import numpy as np import pandas as pd import seaborn as sns import cv2 import random import tensorflow as tf import tkinter as tk from tkinter import filedialog from PIL import ImageTk, Image from ipywidgets import interact, interactive, fixed, interact_manual, HBox, VBox import ipywidgets as widgets from IPython.display import display, clear_output from tensorflow.keras.preprocessing import image from tensorflow.keras.optimizers import Adam, SGD, RMSprop, AdamW, Adadelta, Adagrad, Adamax, Adafactor, Nadam, Ftrl from tensorflow.keras.preprocessing.image import ImageDataGenerator from tqdm import tqdm import os from sklearn.utils import shuffle from sklearn.preprocessing import LabelEncoder from sklearn.model_selection import train_test_split from tensorflow.keras.models import Sequential, Model, load_model from tensorflow.keras.layers import ( GlobalAveragePooling2D, Dropout, Dense, Conv2D, MaxPooling2D, Flatten, Dropout, BatchNormalization, Activation, concatenate, Conv2DTranspose, Input, Reshape, UpSampling2D, ) from tensorflow.keras.applications import ( EfficientNetV2B0, EfficientNetV2B1, EfficientNetV2B2, EfficientNetV2B3, EfficientNetV2L, EfficientNetV2M, EfficientNetV2S, ) from tensorflow.keras.applications import Xception from tensorflow.keras.applications import VGG16, VGG19 from tensorflow.keras.applications import ResNet50, ResNet101, ResNet152, ResNetRS50, ResNetRS101 from tensorflow.keras.applications import InceptionResNetV2, ConvNeXtXLarge, ConvNeXtBase, DenseNet121, MobileNetV2, NASNetLarge, NASNetMobile from tensorflow.keras.utils import to_categorical from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, TensorBoard, ModelCheckpoint from sklearn.metrics import classification_report, confusion_matrix import ipywidgets as widgets import io from PIL import Image from IPython.display import display, clear_output from ipywidgets import Output, Button from warnings import filterwarnings from google.colab import drive drive.mount("/content/gdrive") def load_data(data_folders): X_data = [] # Combined data y_class_labels = [] # Combined classification labels y_seg_labels = [] # Combined segmentation labels for folderPath in data_folders: for label in labels: label_folder_path = os.path.join(folderPath, label) for filename in tqdm(os.listdir(label_folder_path)): if filename.endswith(".jpg"): img = cv2.imread(os.path.join(label_folder_path, filename)) img = cv2.resize(img, (image_size, image_size)) X_data.append(img) y_class_labels.append(label) seg_filename = filename.split(".")[0] + ".png" seg_img = cv2.imread(os.path.join(label_folder_path, seg_filename), 0) seg_img = cv2.resize(seg_img, (image_size, image_size)) seg_img = np.where(seg_img > 0, 1, 0) # Convert segmentation mask to binary y_seg_labels.append(seg_img) X_data = np.array(X_data) y_class_labels = np.array(y_class_labels) y_seg_labels = np.array(y_seg_labels) X_data, y_class_labels, y_seg_labels = shuffle(X_data, y_class_labels, y_seg_labels, random_state=101) return X_data, y_class_labels, y_seg_labels
def split_data(X_data, y_class_labels, y_seg_labels, train_ratio, val_ratio, test_ratio): num_samples = len(X_data) num_train_samples = int(train_ratio * num_samples) num_val_samples = int(val_ratio * num_samples) num_test_samples = int(test_ratio * num_samples) X_train = X_data[:num_train_samples] y_train_class = y_class_labels[:num_train_samples] y_train_seg = y_seg_labels[:num_train_samples] X_val = X_data[num_train_samples: num_train_samples + num_val_samples] y_val_class = y_class_labels[num_train_samples: num_train_samples + num_val_samples] y_val_seg = y_seg_labels[num_train_samples: num_train_samples + num_val_samples] X_test = X_data[num_train_samples + num_val_samples: num_train_samples + num_val_samples + num_test_samples] y_test_class = y_class_labels[num_train_samples + num_val_samples: num_train_samples + num_val_samples + num_test_samples] y_test_seg = y_seg_labels[num_train_samples + num_val_samples: num_train_samples + num_val_samples + num_test_samples] # Convert class labels to categorical label_encoder = LabelEncoder() y_train_class_encoded = label_encoder.fit_transform(y_train_class) y_train_class_categorical = to_categorical(y_train_class_encoded) y_val_class_encoded = label_encoder.transform(y_val_class) y_val_class_categorical = to_categorical(y_val_class_encoded) y_test_class_encoded = label_encoder.transform(y_test_class) y_test_class_categorical = to_categorical(y_test_class_encoded) return ( X_train, y_train_class_categorical, y_train_seg, X_val, y_val_class_categorical, y_val_seg, X_test, y_test_class_categorical, y_test_seg, )
def build_model(input_shape, num_classes): num_filter = 32 # 16/32 best, 8: best classification but no segment # Encoder (Done) inputs = Input(input_shape) conv1 = Conv2D(num_filter * 1, 3, activation="linear", padding="same", strides=1)(inputs) bn1 = BatchNormalization()(conv1) relu1 = Activation("relu")(bn1) conv2 = Conv2D(num_filter * 1, 3, activation="linear", padding="same", strides=1)(relu1) bn2 = BatchNormalization()(conv2) relu2 = Activation("relu")(bn2) down1 = MaxPooling2D(pool_size=(2, 2), strides=2)(relu2) conv3 = Conv2D(num_filter * 2, 3, activation="linear", padding="same", strides=1)(down1) bn3 = BatchNormalization()(conv3) relu3 = Activation("relu")(bn3) conv4 = Conv2D(num_filter * 2, 3, activation="linear", padding="same", strides=1)(relu3) bn4 = BatchNormalization()(conv4) relu4 = Activation("relu")(bn4) down2 = MaxPooling2D(pool_size=(2, 2), strides=2)(relu4) conv5 = Conv2D(num_filter * 4, 3, activation="linear", padding="same", strides=1)(down2) bn5 = BatchNormalization()(conv5) relu5 = Activation("relu")(bn5) conv6 = Conv2D(num_filter * 4, 3, activation="linear", padding="same", strides=1)(relu5) bn6 = BatchNormalization()(conv6) relu6 = Activation("relu")(bn6) down3 = MaxPooling2D(pool_size=(2, 2), strides=2)(relu6) conv7 = Conv2D(num_filter * 8, 3, activation="linear", padding="same", strides=1)(down3) bn7 = BatchNormalization()(conv7) relu7 = Activation("relu")(bn7) conv8 = Conv2D(num_filter * 8, 3, activation="linear", padding="same", strides=1)(relu7) bn8 = BatchNormalization()(conv8) relu8 = Activation("relu")(bn8) # Middle down4 = MaxPooling2D(pool_size=(2, 2), strides=2)(relu8) conv9 = Conv2D(num_filter * 16, 3, activation="linear", padding="same", strides=1)(down4) bn9 = BatchNormalization()(conv9) relu9 = Activation("relu")(bn9) conv10 = Conv2D(num_filter * 16, 3, activation="linear", padding="same", strides=1)(relu9) bn10 = BatchNormalization()(conv10) relu10 = Activation("relu")(bn10) up1 = UpSampling2D(size=(2, 2), interpolation="bilinear")(relu10) # Decoder (Done) concat1 = concatenate([up1, relu8], axis=-1) # , axis=3 conv11 = Conv2D(num_filter * 8, 3, activation="linear", padding="same", strides=1)(concat1) bn11 = BatchNormalization()(conv11) relu11 = Activation("relu")(bn11) conv12 = Conv2D(num_filter * 8, 3, activation="linear", padding="same", strides=1)(relu11) bn12 = BatchNormalization()(conv12) relu12 = Activation("relu")(bn12) up2 = UpSampling2D(size=(2, 2), interpolation="bilinear")(relu12) concat2 = concatenate([up2, relu6], axis=-1) # , axis=3 conv13 = Conv2D(num_filter * 4, 3, activation="linear", padding="same", strides=1)(concat2) bn13 = BatchNormalization()(conv13) relu13 = Activation("relu")(bn13) conv14 = Conv2D(num_filter * 4, 3, activation="linear", padding="same", strides=1)(relu13) bn14 = BatchNormalization()(conv14) relu14 = Activation("relu")(bn14) up3 = UpSampling2D(size=(2, 2), interpolation="bilinear")(relu14) concat3 = concatenate([up3, relu4], axis=-1) # , axis=3 conv15 = Conv2D(num_filter * 2, 3, activation="linear", padding="same", strides=1)(concat3) bn15 = BatchNormalization()(conv15) relu15 = Activation("relu")(bn15) conv16 = Conv2D(num_filter * 2, 3, activation="linear", padding="same", strides=1)(relu15) bn16 = BatchNormalization()(conv16) relu16 = Activation("relu")(bn16) up4 = UpSampling2D(size=(2, 2), interpolation="bilinear")(relu16) concat4 = concatenate([up4, relu2], axis=-1) # , axis=3 conv17 = Conv2D(num_filter * 1, 3, activation="linear", padding="same", strides=1)(concat4) bn17 = BatchNormalization()(conv17) relu17 = Activation("relu")(bn17) conv18 = Conv2D(num_filter * 1, 3, activation="linear", padding="same", strides=1)(relu17) bn18 = BatchNormalization()(conv18) relu18 = Activation("relu")(bn18) # Segmentation branch segmentation_output = Conv2D(1, 1, activation="sigmoid", name="segmentation_output")(relu18) # original # Classification branch (Not done) gap1 = GlobalAveragePooling2D()(relu8) gap2 = GlobalAveragePooling2D()(relu10) gap3 = GlobalAveragePooling2D()(relu12) conv20 = Conv2D(16, 3, activation="linear", padding="same", strides=1)(segmentation_output) bn20 = BatchNormalization()(conv20) relu20 = Activation("relu")(bn20) down5 = MaxPooling2D(pool_size=(4, 4), strides=4)(relu20) conv21 = Conv2D(32, 3, activation="linear", padding="same", strides=1)(down5) bn21 = BatchNormalization()(conv21) relu21 = Activation("relu")(bn21) down6 = MaxPooling2D(pool_size=(4, 4), strides=4)(relu21) conv22 = Conv2D(64, 3, activation="linear", padding="same", strides=1)(down6) bn22 = BatchNormalization()(conv22) relu22 = Activation("relu")(bn22) down7 = MaxPooling2D(pool_size=(4, 4), strides=4)(relu22) flatten1 = Flatten()(down7) concat5 = concatenate([gap1, gap2, gap3, flatten1], axis=-1) # FC layers fc1 = Dense(1024, activation="relu")(concat5) dropout1 = Dropout(0.5)(fc1) fc2 = Dense(1024, activation="relu")(dropout1) dropout2 = Dropout(0.5)(fc2) classification_output = Dense(num_classes, activation="softmax", name="classification_output")(dropout2) # Define the model model = Model(inputs=inputs, outputs=[classification_output, segmentation_output]) return model
def segmentation_loss(y_true, y_pred): y_true = tf.cast(y_true, tf.float32) y_pred = tf.cast(y_pred, tf.float32) bce_loss = tf.keras.losses.binary_crossentropy(y_true, y_pred) smooth = 1e-5 intersection = tf.reduce_sum(y_true * y_pred) union = tf.reduce_sum(y_true) + tf.reduce_sum(y_pred) dice_loss = 1.0 - 2.0 * (intersection + smooth) / (union + smooth) segmentation_loss = bce_loss + 1 * dice_loss return segmentation_loss
def train_model(model, X_train, y_train_class, y_train_seg, X_val, y_val_class, y_val_seg, batch_size, epochs): checkpoint = ModelCheckpoint( "multitask_best_weights.h5", monitor="val_classification_output_accuracy", save_best_only=True, mode="max", verbose=1,) reduce_lr = ReduceLROnPlateau( monitor="val_classification_output_accuracy", factor=0.3, patience=2, min_delta=0.001, mode="auto", verbose=1,) tensorboard = TensorBoard(log_dir="logs") model.compile( optimizer=Adam(lr=0.001), loss={"classification_output": "categorical_crossentropy", "segmentation_output": segmentation_loss}, metrics={"classification_output": "accuracy", "segmentation_output": "accuracy"}, loss_weights={"classification_output": 1, "segmentation_output": 1},) history = model.fit( X_train, {"classification_output": y_train_class, "segmentation_output": y_train_seg}, validation_data=(X_val, {"classification_output": y_val_class, "segmentation_output": y_val_seg}), epochs=epochs, verbose=1, batch_size=batch_size, callbacks=[checkpoint, reduce_lr, tensorboard],) return history
def evaluate_model(model, X_test, y_test_class, y_test_seg): with tf.keras.utils.custom_object_scope({"segmentation_loss": segmentation_loss}): # Load the best model weights best_model = load_model("multitask_best_weights.h5") # Evaluate the model on test data test_loss, test_class_loss, test_seg_loss, test_class_acc, test_seg_acc = best_model.evaluate( X_test, {"classification_output": y_test_class, "segmentation_output": y_test_seg}) print("Test Classification Loss:", test_class_loss) print("Test Segmentation Loss:", test_seg_loss) print("Test Classification Accuracy:", test_class_acc) print("Test Segmentation Accuracy:", test_seg_acc) # Evaluate the model on validation data val_loss, val_class_loss, val_seg_loss, val_class_acc, val_seg_acc = best_model.evaluate( X_val, {'classification_output': y_val_class, 'segmentation_output': y_val_seg}) print("Validation Classification Loss:", val_class_loss) print("Validation Segmentation Loss:", val_seg_loss) print("Validation Classification Accuracy:", val_class_acc) print("Validation Segmentation Accuracy:", val_seg_acc) # Evaluate the model on training data train_loss, train_class_loss, train_seg_loss, train_class_acc, train_seg_acc = best_model.evaluate(X_train, {'classification_output': y_train_class, 'segmentation_output': y_train_seg}) print("Train Classification Loss:", train_class_loss) print("Train Segmentation Loss:", train_seg_loss) print("Train Classification Accuracy:", train_class_acc) print("Train Segmentation Accuracy:", train_seg_acc) # Return test classification accuracy return test_class_acc
def plot_performance(history): # Plot classification accuracy classification_train_accuracy = history.history["classification_output_accuracy"] classification_val_accuracy = history.history["val_classification_output_accuracy"] plt.figure(figsize=(7, 3)) plt.plot(classification_train_accuracy, label="Training Accuracy") plt.plot(classification_val_accuracy, label="Validation Accuracy") plt.title("Classification Accuracy") plt.xlabel("Epochs") plt.ylabel("Accuracy") plt.legend() plt.show() # Plot classification loss classification_train_loss = history.history["classification_output_loss"] classification_val_loss = history.history["val_classification_output_loss"] plt.figure(figsize=(7, 3)) plt.plot(classification_train_loss, "b", label="Training Loss") plt.plot(classification_val_loss, "r", label="Validation Loss") plt.title("Classification Loss") plt.xlabel("Epochs") plt.ylabel("Loss") plt.legend() plt.show() # Plot segmentation accuracy segmentation_train_accuracy = history.history["segmentation_output_accuracy"] segmentation_val_accuracy = history.history["val_segmentation_output_accuracy"] plt.figure(figsize=(7, 3)) plt.plot(segmentation_train_accuracy, label="Training Accuracy") plt.plot(segmentation_val_accuracy, label="Validation Accuracy") plt.title("Segmentation Accuracy") plt.xlabel("Epochs") plt.ylabel("Accuracy") plt.legend() plt.show() # Plot segmentation loss segmentation_train_loss = history.history["segmentation_output_loss"] segmentation_val_loss = history.history["val_segmentation_output_loss"] plt.figure(figsize=(7, 3)) plt.plot(segmentation_train_loss, "b", label="Training Loss") plt.plot(segmentation_val_loss, "r", label="Validation Loss") plt.title("Segmentation Loss") plt.xlabel("Epochs") plt.ylabel("Loss") plt.legend() plt.show()
def test_model(model, X_test, y_test_class, y_test_seg, labels, num_images=5): random_indices = np.random.choice(len(X_test), num_images, replace=False) selected_images = X_test[random_indices] selected_labels = y_test_class[random_indices] selected_masks = y_test_seg[random_indices] predictions = model.predict(selected_images) predicted_classes = np.argmax(predictions[0], axis=1) predicted_masks = predictions[1]
bg_color = '#303030' # Lighter than black, as per the previous specification text_color = 'white' for i in range(num_images): plt.figure(figsize=(10, 5)) plt.subplot(2, 3, 1) plt.imshow(selected_images[i]) plt.title(f"Input Image\nGround Truth Label: {labels[np.argmax(selected_labels[i])]}\nPredicted Label: {labels[predicted_classes[i]]}", color=text_color) plt.axis("off") plt.gcf().set_facecolor(bg_color) plt.subplot(2, 3, 2) plt.imshow(selected_masks[i].squeeze(), cmap="gray") plt.title("Ground Truth Segmentation Mask", color=text_color) plt.axis("off") plt.subplot(2, 3, 3) plt.imshow(predicted_masks[i].squeeze(), cmap="gray") plt.title("Predicted Segmentation Mask", color=text_color) plt.axis("off") plt.tight_layout() plt.show()preprocess and predict on the selected image
out = Output() ''' def predict_image(image_path): # Load and preprocess the image img = cv2.imread(image_path) img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) # Convert BGR to RGB img_resized = cv2.resize(img, (image_size, image_size)) img_expanded = np.expand_dims(img_resized, axis=0) # Predict using the model class_output, seg_output = model.predict(img_expanded) # Get the predicted class predicted_class_index = np.argmax(class_output) predicted_class = labels[predicted_class_index] # Clear the previous output with out: clear_output(wait=True) # Visualize the input and segmentation output fig, axs = plt.subplots(1, 3, figsize=(15, 5)) axs[0].imshow(img) axs[0].set_title("Input Image") axs[0].axis("off")
axs[1].imshow(seg_output[0, :, :, 0], cmap='gray') axs[1].set_title("Segmentation Output") axs[1].axis("off") class_probabilities = class_output[0] x_pos = np.arange(len(labels)) axs[2].bar(x_pos, class_probabilities, align='center', alpha=0.7, color='blue') axs[2].set_xticks(x_pos) axs[2].set_xticklabels(labels, rotation=45, ha="right") axs[2].set_ylabel('Probability') axs[2].set_ylim([0, 1]) axs[2].set_title(f'Classification Output\nPredicted Class: {predicted_class}') # Increased title font size for i, v in enumerate(class_probabilities): axs[2].text(i, v + 0.02, f"{v:.2f}", color='black', ha='center') plt.tight_layout() plt.show()'''
def predict_image(image_path): # Load and preprocess the image img = cv2.imread(image_path) img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) # Convert BGR to RGB img_resized = cv2.resize(img, (image_size, image_size)) img_expanded = np.expand_dims(img_resized, axis=0) # Predict using the model class_output, seg_output = model.predict(img_expanded) # Get the predicted class predicted_class_index = np.argmax(class_output) predicted_class = labels[predicted_class_index] # Clear the previous output with out: clear_output(wait=True) # Configure specific style options for lighter background fig, axs = plt.subplots(1, 3, figsize=(15, 5))
# Lighten background bg_color = '#303030' # Lighter than black for contrast fig.patch.set_facecolor(bg_color) for ax in axs: ax.set_facecolor(bg_color) # Set spines color to lighter tone ax.spines['bottom'].set_color('grey') ax.spines['top'].set_color('grey') ax.spines['right'].set_color('grey') ax.spines['left'].set_color('grey') ax.tick_params(axis='x', colors='white') ax.tick_params(axis='y', colors='white') axs[0].imshow(img) axs[0].set_title("Input Image", color='white', fontweight='bold') axs[0].axis("off") axs[1].imshow(seg_output[0, :, :, 0], cmap='gray') axs[1].set_title("Segmentation Output", color='white', fontweight='bold') axs[1].axis("off") # Adjusted plot for classification class_probabilities = class_output[0] x_pos = np.arange(len(labels)) bars = axs[2].bar(x_pos, class_probabilities, align='center', alpha=0.7, color='cyan') axs[2].set_xticks(x_pos) axs[2].set_xticklabels(labels, rotation=45, ha="right", color='white') axs[2].set_ylabel('Probability', color='white') axs[2].set_ylim([0, 1]) axs[2].set_title(f'Classification Output\nPredicted Class: {predicted_class}', color='white', fontweight='bold') for i, v in enumerate(class_probabilities): axs[2].text(i, v + 0.02, f"{v:.2f}", color='white', ha='center') plt.tight_layout() plt.show()Define a callback function to handle the uploaded file
def on_upload(change): # Get the uploaded file uploaded_filename = next(iter(uploader.value)) uploaded_file = uploader.value[uploaded_filename] # Save the uploaded file with open(uploaded_filename, 'wb') as f: f.write(uploaded_file['content']) # Predict and visualize the image predict_image(uploaded_filename)
Define a function to handle the button click event and clear the output
clear_button = Button(description='Clear') def clear_output_button_clicked(button): out.clear_output() clear_button.on_click(clear_output_button_clicked)
Set image size
image_size = 224
Define labels
labels = ["bridge", "excess", "good", "insuff", "no"]
Set data folders
data_folders = [ "/content/gdrive/MyDrive/Deep learning/FYP_2/4 Dataset Ratio 60 20 20/jit012/jit0/b_dip/train", "/content/gdrive/MyDrive/Deep learning/FYP_2/4 Dataset Ratio 60 20 20/jit012/jit0/b_dip/val", "/content/gdrive/MyDrive/Deep learning/FYP_2/4 Dataset Ratio 60 20 20/jit012/jit0/b_dip/test",]
Load data
X_data, y_class_labels, y_seg_labels = load_data(data_folders)
Set image size
image_size = 224
Split data
train_ratio = 0.2 val_ratio = 0.2 test_ratio = 0.6 X_train, y_train_class, y_train_seg, X_val, y_val_class, y_val_seg, X_test, y_test_class, y_test_seg = split_data( X_data, y_class_labels, y_seg_labels, train_ratio, val_ratio, test_ratio)
Print the counts
print("Number of train images:", len(X_train)) print("Number of train binary masks:", len(y_train_seg)) print("Number of validation images:", len(X_val)) print("Number of validation binary masks:", len(y_val_seg)) print("Number of test images:", len(X_test)) print("Number of test binary masks:", len(y_test_seg)) input_shape = (image_size, image_size, 3) num_classes = len(labels) saved_model_path = "/content/gdrive/MyDrive/Deep learning/FYP_2/4 Dataset Ratio 60 20 20/jit012/jit0/b_dip/model/pcbmtl_bdip.h5" custom_objects = {"segmentation_loss": segmentation_loss}
Load model
model = load_model(saved_model_path, custom_objects=custom_objects)
Test model
test_model(model, X_test, y_test_class, y_test_seg, labels, num_images=5) uploader = widgets.FileUpload(accept='image/*', multiple=False) uploader.observe(on_upload, names='value') buttons_layout = HBox([uploader, clear_button]) display(buttons_layout) display(out) " The above is the Python code with Keras to do inference using the multi-task learning model, this model will take the image as input and provide one classification output and one segmentation output, this code let user to select one image and performance inference, however the predicted output always produce the wrong classification output. Check and correct these functions to solve the problem:"def predict_image(image_path): # Load and preprocess the image img = cv2.imread(image_path) img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) # Convert BGR to RGB img_resized = cv2.resize(img, (image_size, image_size)) img_expanded = np.expand_dims(img_resized, axis=0) # Predict using the model class_output, seg_output = model.predict(img_expanded) # Get the predicted class predicted_class_index = np.argmax(class_output) predicted_class = labels[predicted_class_index] # Clear the previous output with out: clear_output(wait=True) # Configure specific style options for lighter background fig, axs = plt.subplots(1, 3, figsize=(15, 5))
# Lighten background bg_color = '#303030' # Lighter than black for contrast fig.patch.set_facecolor(bg_color) for ax in axs: ax.set_facecolor(bg_color) # Set spines color to lighter tone ax.spines['bottom'].set_color('grey') ax.spines['top'].set_color('grey') ax.spines['right'].set_color('grey') ax.spines['left'].set_color('grey') ax.tick_params(axis='x', colors='white') ax.tick_params(axis='y', colors='white') axs[0].imshow(img) axs[0].set_title("Input Image", color='white', fontweight='bold') axs[0].axis("off") axs[1].imshow(seg_output[0, :, :, 0], cmap='gray') axs[1].set_title("Segmentation Output", color='white', fontweight='bold') axs[1].axis("off") # Adjusted plot for classification class_probabilities = class_output[0] x_pos = np.arange(len(labels)) bars = axs[2].bar(x_pos, class_probabilities, align='center', alpha=0.7, color='cyan') axs[2].set_xticks(x_pos) axs[2].set_xticklabels(labels, rotation=45, ha="right", color='white') axs[2].set_ylabel('Probability', color='white') axs[2].set_ylim([0, 1]) axs[2].set_title(f'Classification Output\nPredicted Class: {predicted_class}', color='white', fontweight='bold') for i, v in enumerate(class_probabilities): axs[2].text(i, v + 0.02, f"{v:.2f}", color='white', ha='center') plt.tight_layout() plt.show()Define a callback function to handle the uploaded file
def on_upload(change): # Get the uploaded file uploaded_filename = next(iter(uploader.value)) uploaded_file = uploader.value[uploaded_filename] # Save the uploaded file with open(uploaded_filename, 'wb') as f: f.write(uploaded_file['content']) # Predict and visualize the image predict_image(uploaded_filename)
Define a function to handle the button click event and clear the output
clear_button = Button(description='Clear') def clear_output_button_clicked(button): out.clear_output() clear_button.on_click(clear_output_button_clicked)"
- Assistant
Your
predict_imagefunction appears to be set up correctly in terms of loading, preprocessing, and predicting using an image with the model. However, there are a few areas you might want to review or consider if the classification output is consistently incorrect:-
Model Accuracy and Training: Ensure that the model was properly trained, and it achieved high accuracy on the training, validation, and test datasets. An underfit or overfit model could perform poorly on new data.
-
Label Encoding: Double-check the
labelsarray to ensure it is in the same order as when the model was trained. Any discrepancy would result in the wrong label being outputted for the correct class index. -
Image Preprocessing Consistency: It's essential that the preprocessing steps you apply to the image before prediction are exactly the same as those applied to the images during model training. This includes the resizing operation, scaling of pixel values (if applied during training), and any other augmentation or preprocessing step.
-
Model Predict Method: Double-check that the model's
predictmethod is being used correctly, and the outputs are being interpreted correctly. You are doing this part right, but it's good to review:class_output, seg_output = model.predict(img_expanded)Ensure that
class_outputandseg_outputcorrectly correspond to the classification and segmentation outputs of the model, respectively. -
Inspect Model Architecture: Review the model architecture to ensure it's designed as expected for multitask learning. Sometimes, errors in the architecture could inadvertently prioritize one task over the other, possibly leading to imbalanced learning.
-
Error in Loading the Model: If you're loading a model, ensure that custom objects, especially if you have custom loss functions or layers, are correctly mapped. You've done this for the
segmentation_loss, but ensure all necessary custom objects are included if there are more.custom_objects = {"segmentation_loss": segmentation_loss} model = load_model(saved_model_path, custom_objects=custom_objects) -
Version Compatibility: Ensure that the TensorFlow and Keras versions are compatible with your model. Sometimes, discrepancies between the version used for training and the version used for prediction can introduce issues.
If after checking these points you still encounter issues, consider additional debugging steps like:
- Manual Testing: Manually test the model with a few known images and observe the outputs to identify any pattern in the misclassification.
- Verbose Outputs: Add additional print statements or logs to confirm that the inputs to the model and its outputs are as expected.
- Simpler Model: As a debugging step, train a simpler model (or even just the classification part) to see if the problem persists, which can help isolate whether the issue is with the data, model architecture, or code logic.
Remember, debugging machine learning models can be iterative and might require multiple approaches to identify the root cause of the issue.
-
- User
Show the fixed code
- Assistant
Assuming that the main issue lies within the
predict_imagefunction and the code around model loading and preprocessing is correct, I will provide a revised version of thepredict_imagefunction and related components with some additional comments to ensure everything is as expected. Note that unless there's a specific error being thrown or observed, the fixes will focus on ensuring data consistency and correct usage of components.Revised
predict_imageFunction and Related Code:# Set image size and labels consistently with the training phase image_size = 224 labels = ["bridge", "excess", "good", "insuff", "no"] # Assuming this model path and custom_objects are correctly specified as per your training phase saved_model_path = "/content/gdrive/MyDrive/Deep learning/FYP_2/4 Dataset Ratio 60 20 20/jit012/jit0/b_dip/model/pcbmtl_bdip.h5" custom_objects = {"segmentation_loss": segmentation_loss} def predict_image(image_path, model, labels): img = cv2.imread(image_path) img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) # Ensure conversion from BGR to RGB img_resized = cv2.resize(img, (image_size, image_size)) / 255.0 # Resize and scale if necessary img_expanded = np.expand_dims(img_resized, axis=0) # Expand dims to match input shape # Predict using the model class_output, seg_output = model.predict(img_expanded) predicted_class_index = np.argmax(class_output) predicted_class = labels[predicted_class_index] with out: clear_output(wait=True) display_image_and_predictions(img, seg_output, class_output, predicted_class, labels) def display_image_and_predictions(input_image, seg_output, class_output, predicted_class, labels): # Configure style options for display bg_color = '#303030' text_color = 'white' plt.figure(figsize=(15, 5)) plt.subplot(1, 3, 1) plt.imshow(input_image) plt.title("Input Image", color=text_color) plt.axis('off') plt.subplot(1, 3, 2) plt.imshow(seg_output[0, :, :, 0], cmap='gray') plt.title("Segmentation Output", color=text_color) plt.axis('off') plt.subplot(1, 3, 3) x_pos = np.arange(len(labels)) plt.bar(x_pos, class_output[0], align='center', alpha=0.7, color='cyan') plt.xticks(x_pos, labels, rotation=45, ha="right", color=text_color) plt.yticks(color=text_color) plt.ylabel('Probability', color=text_color) plt.ylim([0, 1]) plt.title(f'Classification Output\nPredicted Class: {predicted_class}', color=text_color) plt.tight_layout() plt.show() # Load model once (ensure this is done correctly) model = load_model(saved_model_path, custom_objects=custom_objects) # Assuming the uploader and out widget are correctly defined and initialized def on_upload(change): uploaded_filename = next(iter(uploader.value)) uploaded_file = uploader.value[uploaded_filename] with open(uploaded_filename, 'wb') as f: f.write(uploaded_file['content']) predict_image(uploaded_filename, model, labels) uploader.observe(on_upload, names='value') clear_button = Button(description='Clear') def clear_output_button_clicked(button): out.clear_output() clear_button.on_click(clear_output_button_clicked) # Display UI components display(widgets.HBox([uploader, clear_button]), out)Key Revisions:
- Image Preprocessing: Added a scaling step (
/ 255.0) during image preprocessing. If your model expects pixel values in the range[0, 1](common when using CNNs), this step is crucial. - Display Function Refactoring: Separated the logic for displaying images and their predictions into a
display_image_and_predictionsfunction for better code organization and readability. - Model Loading: Reminder to load the model outside of function calls if possible to avoid reloading it on every prediction, which is inefficient.
- Error Handling and Validation: While not explicitly added, consider including error handling for file reading (
cv2.imread), model prediction, and other steps that might fail under certain conditions.
Ensure your model path and
custom_objectsdefinition match what was used during training, especially if using custom layers, activations, or loss functions. - Image Preprocessing: Added a scaling step (
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.