import gradio as gr import numpy as np import pandas as pd import os # our own helper tools import clustering import utils import logging logging.getLogger().setLevel(logging.INFO) from tensorflow import keras #import keras # print(keras.__version__) # print(keras.__file__) from keras.layers import TFSMLayer #image_threshold = 20 # --- Constants and Model Loading --- IMAGE_PATH = "classified_damage_sites.png" CSV_PATH = "classified_damage_sites.csv" DEFAULT_IMAGE_PATH = "SE_001_cut.png" model1_windowsize = [250,250] #model1_threshold = 0.7 #model1 = keras.models.load_model('rwthmaterials_dp800_network1_inclusion_converted.h5') model1 = TFSMLayer('rwthmaterials_dp800_network1_inclusion', call_endpoint='serving_default') #model1.compile() damage_classes = {3: "Martensite",2: "Interface",0:"Notch",1:"Shadowing"} model2_windowsize = [100,100] #model2_threshold = 0.5 #model2 = keras.models.load_model('rwthmaterials_dp800_network2_damage_converted.h5') model2 = TFSMLayer('rwthmaterials_dp800_network2_damage', call_endpoint='serving_default') #model2.compile() ## ## Function to do the actual damage classification ## def damage_classification(SEM_image,image_threshold, model1_threshold, model2_threshold): damage_sites = {} ## ## clustering ## logging.debug('---------------: clustering :=====================') all_centroids = clustering.get_centroids(SEM_image, image_threshold=image_threshold, fill_holes=True, filter_close_centroids=True, filter_radius=90) for i in range(len(all_centroids)) : key = (all_centroids[i][0],all_centroids[i][1]) damage_sites[key] = 'Not Classified' ## ## Inclusions vs the rest ## logging.debug('---------------: prepare model 1 :=====================') images_model1 = utils.prepare_classifier_input(SEM_image, all_centroids, window_size=model1_windowsize) # debugging function to check the input to the classifier #from utils import debug_classification_input #debug_classification_input(images_model1) logging.debug('---------------: run model 1 :=====================') #y1_pred = model1.predict(np.asarray(images_model1, float)) #y1_pred = model1(np.asarray(images_model1, float)) # logging.debug('---------------: model1 threshold :=====================') # inclusions = y1_pred[:,0].reshape(len(y1_pred),1) # inclusions = np.where(inclusions > model1_threshold) batch_model1 = np.array(images_model1, dtype=np.float32) logging.debug(f"Model 1 input shape: {batch_model1.shape}") # Get predictions from model 1 y1_pred_raw = model1(batch_model1) logging.debug(f"Model 1 raw output type: {type(y1_pred_raw)}") # Extract actual predictions from the model output y1_pred = utils.extract_predictions_from_tfsm(y1_pred_raw) logging.debug(f"Model 1 predictions shape: {y1_pred.shape}") logging.debug(f"Model 1 predictions sample: {y1_pred[:3] if len(y1_pred) > 0 else 'Empty'}") # Handle predictions based on their shape if len(y1_pred.shape) == 2: # Predictions are 2D: (batch_size, num_classes) inclusions = y1_pred[:, 0] # Get first column (inclusion probability) elif len(y1_pred.shape) == 1: # Predictions are 1D: (batch_size,) inclusions = y1_pred else: raise ValueError(f"Unexpected prediction shape: {y1_pred.shape}") logging.debug('---------------: model1 threshold :=====================') inclusions = np.where(inclusions > model1_threshold) logging.debug('Inclusions found at indices:') logging.debug(inclusions) logging.debug('---------------: model 1 update dict :=====================') for i in range(len(inclusions[0])): centroid_id = inclusions[0][i] coordinates = all_centroids[centroid_id] key = (coordinates[0], coordinates[1]) damage_sites[key] = 'Inclusion' logging.debug('Damage sites after model 1') logging.debug(damage_sites) ## ## Martensite cracking, etc ## logging.debug('---------------: prepare model 2 :=====================') centroids_model2 = [] for key, value in damage_sites.items(): if value == 'Not Classified': coordinates = list([key[0],key[1]]) centroids_model2.append(coordinates) logging.debug('Centroids model 2') logging.debug(centroids_model2) logging.debug('---------------: prepare model 2 :=====================') images_model2 = utils.prepare_classifier_input(SEM_image, centroids_model2, window_size=model2_windowsize) logging.debug('Images model 2') logging.debug(images_model2) logging.debug('---------------: run model 2 :=====================') #y2_pred = model2.predict(np.asarray(images_model2, float)) #y2_pred = model2(np.asarray(images_model2, float)) batch_model2 = np.array(images_model2, dtype=np.float32) logging.debug(f"Model 2 input shape: {batch_model2.shape}") # Get predictions from model 2 y2_pred_raw = model2(batch_model2) logging.debug(f"Model 2 raw output type: {type(y2_pred_raw)}") # Extract actual predictions from the model output y2_pred = utils.extract_predictions_from_tfsm(y2_pred_raw) logging.debug(f"Model 2 predictions shape: {y2_pred.shape}") logging.debug(f"Model 2 predictions sample: {y2_pred[:3] if len(y2_pred) > 0 else 'Empty'}") logging.debug(y2_pred) logging.debug('---------------: model2 threshold :=====================') damage_index = np.asarray(y2_pred > model2_threshold).nonzero() for i in range(len(damage_index[0])): index = damage_index[0][i] identified_class = damage_index[1][i] label = damage_classes[identified_class] coordinates = centroids_model2[index] #print('Damage {} \t identified as {}, \t coordinates {}'.format(i, label, coordinates)) key = (coordinates[0], coordinates[1]) damage_sites[key] = label ## ## show the damage sites on the image ## logging.debug("-----------------: final damage sites :=================") logging.debug(damage_sites) image_path = 'classified_damage_sites.png' image = utils.show_boxes(SEM_image, damage_sites, save_image=True, image_path=image_path) ## ## export data ## csv_path = 'classified_damage_sites.csv' cols = ['x', 'y', 'damage_type'] data = [] for key, value in damage_sites.items(): data.append([key[0], key[1], value]) df = pd.DataFrame(columns=cols, data=data) df.to_csv(csv_path) return image, image_path, csv_path ## --------------------------------------------------------------------------------------------------------------- ## main app interface ## ----------------------------------------------------------------------------------------------------------------- with gr.Blocks() as app: gr.Markdown('# Damage Classification in Dual Phase Steels') gr.Markdown('This app classifies damage types in dual phase steels. Two models are used. The first model is used to identify inclusions in the steel. The second model is used to identify the remaining damage types: Martensite cracking, Interface Decohesion, Notch effect and Shadows.') gr.Markdown('The models used in this app are based on the following papers:') gr.Markdown('Kusche, C., Reclik, T., Freund, M., Al-Samman, T., Kerzel, U., & Korte-Kerzel, S. (2019). Large-area, high-resolution characterisation and classification of damage mechanisms in dual-phase steel using deep learning. PloS one, 14(5), e0216493. [Link](https://doi.org/10.1371/journal.pone.0216493)') #gr.Markdown('Medghalchi, S., Kusche, C. F., Karimi, E., Kerzel, U., & Korte-Kerzel, S. (2020). Damage analysis in dual-phase steel using deep learning: transfer from uniaxial to biaxial straining conditions by image data augmentation. Jom, 72, 4420-4430. [Link](https://link.springer.com/article/10.1007/s11837-020-04404-0)') gr.Markdown('Setareh Medghalchi, Ehsan Karimi, Sang-Hyeok Lee, Benjamin Berkels, Ulrich Kerzel, Sandra Korte-Kerzel, Three-dimensional characterisation of deformation-induced damage in dual phase steel using deep learning, Materials & Design, Volume 232, 2023, 112108, ISSN 0264-1275, [link] (https://doi.org/10.1016/j.matdes.2023.112108') gr.Markdown('Original data and code, including the network weights, can be found at Zenodo [link](https://zenodo.org/records/8065752)') #image_input = gr.Image(value='data/X4-Aligned_cropped_upperleft_small.png', label='Example SEM Image (DP800 steel)',) with gr.Row(): with gr.Column(scale=1): #image_input = gr.Image(type="pil", label="Upload SEM Image") image_input = gr.Image(type="pil", label="Upload SEM Image", value=DEFAULT_IMAGE_PATH if os.path.exists(DEFAULT_IMAGE_PATH) else None) cluster_threshold_input = gr.Number(value=20, label="Image Binarization Threshold") model1_threshold_input = gr.Number(value=0.7, label="Inclusion Model Certainty (0-1)") model2_threshold_input = gr.Number(value=0.5, label="Damage Model Certainty (0-1)") classify_btn = gr.Button("Run Classification", variant="primary") with gr.Column(scale=2): output_image = gr.Image(label="Classified Image") # Initialize DownloadButtons as hidden. They will become visible after a successful run. # Explicitly setting value=None to be safe, though visible=False should imply it. download_image_btn = gr.DownloadButton(label="Download Image", value=None, visible=False) download_csv_btn = gr.DownloadButton(label="Download CSV", value=None, visible=False) # This wrapper function handles the UI updates, which is the robust way to use Gradio. def run_classification_and_update_ui(sem_image, cluster_thresh, m1_thresh, m2_thresh): """ Calls the core logic and then returns updates for the Gradio UI components. """ try: # Call the main processing function classified_img, img_path, csv_path = damage_classification(sem_image, cluster_thresh, m1_thresh, m2_thresh) # Return the results in the correct order to update the output components. # Use gr.update to change properties of a component, like visibility and value. return ( classified_img, gr.update(value=img_path, visible=True), gr.update(value=csv_path, visible=True) ) except Exception as e: # Catch any error during classification and display it gracefully logging.error(f"Error during classification: {e}") gr.Warning(f"An error occurred: {e}") # Keep download buttons hidden on error and clear image return ( None, # Clear the image on error gr.update(visible=False), gr.update(visible=False) ) # Connect the button's click event to the wrapper function classify_btn.click( fn=run_classification_and_update_ui, inputs=[ image_input, cluster_threshold_input, model1_threshold_input, model2_threshold_input ], outputs=[ output_image, download_image_btn, download_csv_btn ], ) if __name__ == "__main__": app.launch()