Upload 4 files

pages/1_💾_Data.py

@@ -29,38 +29,23 @@ st.session_state['user_group'] = backend
 # #     with st.sidebar:
 # st.sidebar.title("🎈Explore Data Panel")
 
-st.title("🎈Explore Data Panel")
+st.title("Explore Data Panel for OCT Image Analysis")
 
 st.write(
         """
         ##
-        Examining data is the key factor here and it provides deta-centric approach. Thus this module provides details regarding forllowing aspect of the data . 
+        Examining the data is the key factor for better understanding of the AI system.Therefore,this panel introduces deta-centric approach by providing details regarding forllowing aspect of the data . 
         """)
 
+
 list_test = """<ul>
-                        <li>Data preprocessing: asdsdfdf</li>
-                        <li>Data source: asdsdfdf</li>
-                        <li>Data onboarding: asdsdfdf</li>
-                    </ul>"""
+                    <li>Data Source Information: This tab contains information regarding following aspect of the data: 
+                        modality,format, domain, ethical considerations including license and data version. </li>
+                    <li>Exploratory Data Stats: This tab includes exploratory data analysis info covering following aspects: train/validation/test data division,summary statistics, sample visualization from each category.</li>
+                    <li>Data Onboarding: This tab provides details of data pre-processing and post-processing steps applied over the dataset before traning, and data augmentations.</li>
+                 </ul>"""
 st.markdown(list_test, unsafe_allow_html=True)
 
 
-# with st.sidebar.expander("🧩 COMPONENTS", True):
-
-#     # genre = st.radio("",('Data Info', 'Data EDA', 'Data ONboard'))
-#     status_a = st.checkbox("Test editor", key="a")
-#     status_b = st.checkbox("Ace editor", key="b")
-# if status_a:
-#     st.write("A checked")
-# if status_a and status_b:
-#     st.write("They arechecked")
-
 if backend == "Developer":
     get_product_dev_page_layout()
-    # st.checkbox("Ace editor", key="b", disabled=selected)
-    # page.item("Ace editor", components.ace_editor)
-    # page.item("Disqus", components.disqus)
-    # page.item("Elements⭐", components.elements)
-    # page.item("Pandas profiling", components.pandas_profiling)
-    # page.item("Quill editor", components.quill_editor)
-    # page.item("React player", components.react_player)

pages/2_📝_Model.py

@@ -28,16 +28,18 @@ st.session_state['user_group'] = backend
 st.title("Explore Model Panel for OCT Image Analysis")
 st.write(
         """
-        ##
-        Examining model details for the develop models. This section highlights the overview of the developed model for specific user groups.
-        Developer, model owners and managers can use this section by hemselves.
+       The users can find following information regarding the AI model developed for the task: what the mode does, how it was developed and how it is used. Thus, we provide answers 
+       to those questions via below described tabs.
         """)
 
 list_test = """<ul>
-                        <li><strong>Dev</li>
-                        <li><strong>Deploy</li>
-                        <li><strong>General</li>
-                    </ul>"""
+                <li>Model generic information: This tab contains summary of the model’s details, including its main features, capabilities, and intended use. 
+                    It also hihglights the model’s behaviour, such as the type of data inputs(image, feature etc) it can handle and the types of outputs it produces.</li>
+                <li>Model development information: The tab includes information on the hyperparameters, model development framework such as Tensorflow or PyTorch, and other technical details. It also includes a complete analysis of the model’s inference performance, such as the model size, 
+                        hardware-specific (GPU and CPU) inference time,and speed, as well as reproducibility check list.</li>
+                <li>Model deployment information: This tab provides information on how the model is used in production, including details on the inference speed and latency,  
+                        and how users can access and interact with the model in production.</li>
+                </ul>"""
 st.markdown(list_test, unsafe_allow_html=True)
 
 if backend == "Developer":

pages/3_🎯_Evaluation_Panel.py

@@ -23,13 +23,19 @@ backend = st.sidebar.selectbox(
 
 st.session_state['user_group'] = backend
 
-st.title("Evaluation Details")
-
+st.title("Explore Performance Panel for OCT Image Analysis")
 st.write(
-    """
-    ##
-    This section gives on averview of the performance metrics and results on test set.
-    """)
+        """
+       This panel provides information on the evaluation of the AI model’s performance, including details on the metrics used and the results of the evaluation. USerrs can also find 
+       our notes regarding the issues. The performance metric visualizations and samples of failure and success cases are given in in this panel as well.""")
+
+list_test = """<ul>
+                    <li>Evaluation Metrics: This tab explains the details of the performance metrics and how each metric is calculated. 
+                        Users can also find the characteristics of the evaluation data set. </li>
+                    <li>Performance Summary: This tab includes visualizations of the performance metrics over test set.</li>
+                    <li>Limitations: This tab provides examples of observed failure and success cases, along with visualizations and any possible observations behind the failure cases.</li>
+                </ul>"""
+st.markdown(list_test, unsafe_allow_html=True)
 
 if backend == "Developer":
     get_product_dev_page_layout()

pages/4_🔬_Decision_Exploration_Panel.py

@@ -1,458 +1,39 @@
-import os
-import sys 
-import json
-import shutil
-import urllib.request
-from pathlib import Path
-import pathlib
-import time
-import urllib
-from ast import literal_eval
-import albumentations as A
-import tensorflow as tf
-
-import cv2
-import numpy as np
-import pandas as pd
-import plotly.express as px
-import matplotlib.pyplot as plt
-from PIL import Image
-
 import streamlit as st
-
-import seaborn as sns
+import sys,os
 
 sys.path.append(f'{os.getcwd()}/utils')
-from utils.eval_users import get_product_dev_page_layout
-
-# print(os.getcwd())
-
-# Hide GPU from visible devices
-tf.config.set_visible_devices([], 'GPU')
-# Enable GPU memory growth - avoid allocating all memory at start
-# gpus = tf.config.experimental.list_physical_devices(device_type='GPU')
-# for gpu in gpus:
-#     tf.config.experimental.set_memory_growth(device=gpu, enable=True)
-
-from utils.control import show_tsne_vis,show_random_samples
 
-from utils.annoy_sampling import load_annoy_tree
-# from utils import (
-#     load_augmentations_config,
-#     get_arguments,
-#     get_placeholder_params,
-#     select_transformations,
-#     show_random_params,
-# )
-# from visuals import (
-#     select_image,
-#     show_credentials,
-#     show_docstring,
-#     get_transormations_params,
-# )
+from utils.decisions_users import get_product_dev_page_layout
 
-from utils.model_utils import load_model
-from utils.model_utils import get_feature_vector, get_feature_extractor_model, get_predictions_and_roi
-
-sns.set_style('darkgrid')
-plt.rcParams['axes.grid'] = False
+# st.write(st.session_state.user_group)
+USER_GROUPS = ["Developer", "Manager", "Practitioner"]
 
 st.set_page_config(layout="wide")
 
-#https://github.com/IliaLarchenko/albumentations-demo/blob/3cb6528a513fe3b35dbb2c2a63cdcfbb9bb2a932/src/utils.py#L149
-
-GRAD_CAM_IMAGE_DIR = f'{os.getcwd()}/data/gradcam_vis_data/'
-TEST_CSV_FILE =   f'{os.getcwd()}/data/test_set_pred_prop.csv'
-
-annoy_tree_save_path =f'{os.getcwd()}/data/filtered_train_embedding/representative_samples_emb.annoy'
-test_emb_path = f'{os.getcwd()}/data/filtered_train_embedding/test_embeddings.npy'
-test_emb_id_path =f'{os.getcwd()}/data/filtered_train_embedding/test_ids.npy'
-
-train_emb_id_path =f'{os.getcwd()}/data/filtered_train_embedding/representative_train_ids.npy'
-
-repr_id_path =f'{os.getcwd()}/data/filtered_train_embedding/representative_train_ids.npy'
-borderline_id_path =f'{os.getcwd()}/data/filtered_train_embedding/borderline_train_ids.npy'
-
-MODEL_PATH = f'{os.getcwd()}/model/keras_model_0422/'
-
-ROOT_FIG_DIR = f'{os.getcwd()}/figures/'
-
-test_emb = np.load(test_emb_path)
-test_ids = np.load(test_emb_id_path)
-test_id_list = list(test_ids)
-test_labels = [_id.split("\\")[1] for _id in test_id_list]
-print(" NUmber of test samples: ",len(test_labels))
-test_features = test_emb.reshape(-1,1792)
-
-
-# train embedding list
-train_ids = np.load(train_emb_id_path)
-train_id_list = list(train_ids)
-train_labels = [_id.split("\\")[1] for _id in train_id_list]
-print(" NUmber of training samples: ",len(train_labels))
-
-annoy_tree = load_annoy_tree(test_features.shape[1],annoy_tree_save_path)
-def annoy_matching(annoy_f,query_item, query_index, n=10):
-            return annoy_f.get_nns_by_vector(query_item, n)
-
-def get_img(fn ,thumbnail=False):
-    img = Image.open(fn)
-    if thumbnail:
-        img.thumbnail((100,100))
-    return img
-
-
-### Within the streamlit.cache() decorator you’ll get better performance 
-# if you use allow_output_mutation=True because this means Streamlit just uses the same copy of the model in memory, 
-# rather than reloading when it’s re-run.
-
-# MODEL_WEIGHTS = f'{DEFAULT_MODEL_BASE_DIR}/hpe_epoch107_.hdf5'
-# MODEL_JSON = f'{DEFAULT_MODEL_BASE_DIR}/hpe_hourglass_stacks_04_.json'
-
-# MODEL_WEIGHTS_DEPLOYMENT_URL = 'https://github.com/robertklee/COCO-Human-Pose/releases/download/v0.1-alpha/hpe_epoch107_.hdf5'
-# MODEL_JSON_DEPLOYMENT_URL = 'https://github.com/robertklee/COCO-Human-Pose/releases/download/v0.1-alpha/hpe_hourglass_stacks_04_.json'
-
-# Constants for sidebar dropdown
-SIDEBAR_OPTION_PROJECT_INFO = "Show Panel Info"
-SIDEBAR_OPTION_GLOBAL_EXP = "Show Global Explanations"
-SIDEBAR_OPTION_INSTANCE_EXP = "Select a Demo Image"
-SIDEBAR_OPTION_INSTANCE_AUG= "Apply Augmentations"
-
-
-
-SIDEBAR_OPTIONS = [SIDEBAR_OPTION_PROJECT_INFO, SIDEBAR_OPTION_GLOBAL_EXP,SIDEBAR_OPTION_INSTANCE_EXP, SIDEBAR_OPTION_INSTANCE_AUG]
-
-def plot_n_similar(seed_id,similar_ids, test_path,n=10, scale=5):
-    f,ax = plt.subplots(1,n+1,figsize=((n+1)*scale,scale))
-    # print(os.path.basename(test_labels[seed_id])[:-4])
-    title = "SEED ID:{0}\nLabel:{1}".format(seed_id,os.path.basename(test_labels[seed_id]))
-    # print("path:", test_labels[seed_id].replace("F:/","E:/"))
-    ax[0].imshow(get_img(test_path.replace("F:/","E:/")),cmap='gray')
-    ax[0].set_title(title,fontsize=12)
-    for i in range(len(similar_ids)):
-        ax[i+1].imshow(get_img(similar_ids[i].replace("F:/","E:/")),cmap='gray')
-        title = "ID:{0}\nDistance: {1:.3f}\nLabel:{2}".format(i,0.1223,os.path.basename(similar_ids[i])[:-4])  
-        ax[i+1].set_title(title,fontsize=10)
-    f.suptitle("Images similar to seed_id {0}".format(seed_id),fontsize=18)
-    plt.subplots_adjust(top=0.5)
-    return f
-
-def load_image(filename,change_url=True):
-    # if change_url:
-    print(filename)
-    print(os.path.exists(filename))
-    img = cv2.imread(filename)
-    return img
-
-@st.cache(allow_output_mutation=True)
-def get_model(model_path):
-    new_model = tf.keras.models.load_model(model_path)
-    # keras_model = load_model(model_path)
-    return new_model
-
-@st.cache(allow_output_mutation=True)
-def get_feature_vector_model(model_path):
-    keras_model = tf.keras.models.load_model(model_path)
-    feature_extractor =  tf.keras.Model(keras_model.inputs,keras_model.layers[-3].output)
-    return feature_extractor
-    # feature_mod = get_feature_extractor_model(keras_model)
-    # return feature_mod
-
-def load_pd_data_frame(df_csv_path):
-    return pd.read_csv(df_csv_path)
-
-def get_path_list_from_df(df_data):
-    return list(df_data['path'])
-
-def get_class_probs_from_df(df_data):
-    return list(df_data['class_probs'])
-
-
-def visualize_bar_plot(df_data):
-    fig = px.bar(df_data, x="probability", y="class", orientation='h')
-    return fig
-
-# def get_file_content_as_string(path):
-#     """[summary]
-
-#     Args:
-#         path (string): path to  instructions.md
-
-#     Returns:
-#         url (url): url format
-#     """
-
-#     #url = 'https://raw.githubusercontent.com/streamlit/demo-self-driving/master/' + path
-#     path = os.path.abspath(path)
-#     url=pathlib.Path(path).as_uri()
-#     #url = path
-#     response = urllib.request.urlopen(url)
-#     return response.read().decode("utf-8")
-
-def run_instance_exp(img_path, img_path_list,prob_list,grad_vis_path_list):
-
-    st.subheader('Instance Exploration')
-    # st.columns((1,1,1))  with row4_2:
-    LABELS = ['CNV', 'DRUSEN', 'DME', 'NORMAL']
-
-    left_column, middle_column, right_column = st.columns((1,1,1))
-    display_image = load_image(img_path)
-    # fig = px.imshow(display_image)
-    # left_column.plotly_chart(fig, use_container_width=True)
-    left_column.image(cv2.resize(display_image, (180,180)),caption = "Selected Input")
-
-    # get class probabilities
-    indx = img_path_list.index(img_path)
-    print(img_path)
-    prb_tmp = prob_list[indx]
-    print(f"{prb_tmp[1:-1]}")
-    clss_probs = literal_eval('"'+prb_tmp[1:-1]+'"')
-    print(clss_probs[1:-1].split(' '))
-    prob_cls = [float(p) for p in clss_probs[1:-1].split(' ')]
-    tmp_df = pd.DataFrame.from_dict({'class':LABELS,'probability':prob_cls})
-    print(tmp_df.head())
-    fig = plt.figure(figsize=(15, 13))
-    sns.barplot(x='probability', y='class', data=tmp_df)
-    middle_column.pyplot(fig)
-    # st.caption('Predictions')
-
-    tmp_grad_img = GRAD_CAM_IMAGE_DIR + img_path.split("\\")[-2] +'/'+img_path.split("\\") [-1] 
-    
-    display_image = load_image(tmp_grad_img,replace=False)
-    # left_column.plotly_chart(fig, use_container_width=True)
-    right_column.image(display_image,caption = "ROI")
-
-    # seed_id = 900
-    seed_id = test_id_list.index(img_path)
-    query_item = test_features[seed_id]
-    print(query_item.shape)
-    closest_idxs = annoy_matching(annoy_tree,query_item, seed_id, 10)
-    closest_fns = [train_ids[close_i] for close_i in closest_idxs]
-    st.subheader('Top-10 Similar Samples from Gallery Set')
-    st.pyplot(plot_n_similar(seed_id,closest_fns, img_path,n=10, scale=4))
-
-    # ax = sns.barplot(x='totalCount', y='name', data=df)
-    # plt_fig = visualize_bar_plot(tmp_df)
-    # middle_column.plotly_chart(plt_fig, use_container_width=True)
-
-def run_instance_exp_keras_model(img_path, new_model, feature_extractor_model):
-
-    st.subheader('Instance Exploration')
-    # st.columns((1,1,1))  with row4_2:
-    LABELS = ['CNV', 'DRUSEN', 'DME', 'NORMAL']
-
-    left_column, middle_column, right_column = st.columns((1,1,1))
-    print(img_path)
-    org_img_path = img_path
-
-    img_path = f'{os.getcwd()}/data/oct2017/test/' + img_path.split("\\")[-2] +'/'+img_path.split("\\") [-1]
-    # img_path.replace("F:/XAI/data/OCT2017/","/home/hodor/dev/Learning/XAI/streamlit_demo/multipage-app/data/xai_framework_data/")
-    display_image = load_image(img_path)
-    # fig = px.imshow(display_image)
-    # left_column.plotly_chart(fig, use_container_width=True)
-    left_column.image(cv2.resize(display_image, (180,180)),caption = "Selected Input")
-   
-
-    roi_img, probs = get_predictions_and_roi(img_path, new_model)
-
-    ## probs
-    print(np.asarray(probs))
-    print(probs.shape)
-    prob_cls =np.asarray(probs)[0]
-    print(prob_cls)
-    tmp_df = pd.DataFrame.from_dict({'class':LABELS,'probability':prob_cls})
-    fig = plt.figure(figsize=(5, 4))
-    sns.barplot(x='probability', y='class', data=tmp_df)
-    middle_column.pyplot(fig)
-    # middle_column.write("Probabilities")
-
-    # grad img 
-    right_column.image(roi_img, caption = "Decision ROI")
-
-    # seed_id = 900
-    seed_id = test_id_list.index(org_img_path)
-    query_item = get_feature_vector(img_path,feature_extractor_model)
-    query_item = query_item.reshape(-1,1792)
-    print(query_item.shape)
-    closest_idxs = annoy_matching(annoy_tree,query_item[0,:], seed_id, 10)
-    closest_fns = [train_ids[close_i] for close_i in closest_idxs]
-
-    closest_fns_tmp = [f'{os.getcwd()}/data/oct2017/train/' + each_fn.split("\\")[-2] +'/'+each_fn.split("\\") [-1] 
-                for each_fn in closest_fns]
-    print(closest_fns)
-    st.subheader('Top-10 Similar Samples from Gallery Set')
-    st.pyplot(plot_n_similar(seed_id,closest_fns_tmp, img_path,n=10,scale=3))
-   
-
-
-def run_augmentations(transforms,image):
-    data = None
-    try:
-                # apply the transformation to the image
-        data = A.Compose(transforms)(image=image)
-        error = 0
-    except ValueError:
-        error = 1
-    
-    return data, error
-
-@st.cache
-def get_sample():
-    print("running!")
-
-def main():
-
-    st.sidebar.warning('\
-        Please upload SINGLE single...')
-    st.sidebar.write(" ------ ")
-    st.sidebar.title("Explore the Instance Predictions and Explanations")
-    new_model =  get_model(MODEL_PATH)
-    feature_extractor_model = get_feature_vector_model(MODEL_PATH)
-
-    app_mode = st.sidebar.selectbox("Please select from the following", SIDEBAR_OPTIONS)
-
-    if app_mode == SIDEBAR_OPTION_PROJECT_INFO:
-        st.sidebar.write(" ------ ")
-        st.sidebar.success("Project information showing on the right!")
-        # st.write(get_file_content_as_string("README.md"))
-
-    elif app_mode == SIDEBAR_OPTION_INSTANCE_EXP:
-        st.sidebar.write(" ------ ")
-
-        DF_TEST_PROP = load_pd_data_frame(TEST_CSV_FILE)
-        IMG_PATH_LISTS = get_path_list_from_df(DF_TEST_PROP)
-        IMG_CLSS_PROBS_LIST = get_class_probs_from_df(DF_TEST_PROP)
-        grad_vis_path_list = None
-
-        # new_model = load_model(MODEL_PATH)
-        option = st.sidebar.selectbox('Please select a sample image, then click Explain Me button', IMG_PATH_LISTS)
-        pressed = st.sidebar.button('Explain ME')
-        if pressed:
-            st.empty()
-            st.sidebar.write('Please wait for the magic to happen! This may take up to a minute.')
-            run_instance_exp_keras_model(option, new_model,feature_extractor_model)
-            # run_instance_exp(option, IMG_PATH_LISTS,IMG_CLSS_PROBS_LIST,grad_vis_path_list)
-
-    elif app_mode == SIDEBAR_OPTION_GLOBAL_EXP:
-        borderline_cases = np.load(borderline_id_path)
-        representative_cases = np.load(repr_id_path)
-        borderline_id_list = list(borderline_cases)
-        # print(borderline_id_list)
-
-        borderline_id_list = [f'{os.getcwd()}/data/oct2017/train/' + each_fn.split("\\")[-2] +'/'+each_fn.split("\\") [-1] 
-                for each_fn in borderline_id_list]
-        representative_id_list = list(representative_cases)
-        representative_id_list = [f'{os.getcwd()}/data/oct2017/train/' + each_fn.split("\\")[-2] +'/'+each_fn.split("\\") [-1] 
-                for each_fn in representative_id_list]
-        print(representative_id_list)
-        print(borderline_id_list)
-        #with upload:
-        st.sidebar.info('GLOABAL EXPLANATION!! ')
-        option = st.sidebar.selectbox('Please select Global Samples, then click Explain Me button', ["Representative Samples","Borderline Cases"])
-        if option:
-            clss = st.sidebar.selectbox('Select A Class', ["CNV","DME", "NORMAL", "DRUSEN"])
-            side_1, side_2 = st.sidebar.columns(2)
-            # cls1, cls2, cls3, cls4 = st.sidebar.columns(4)
-            # st.sidebar.title("Choose A Class:")
-        # with cls1:
-        #     st.radio('', ["CNV"])
-        # with cls2:
-        #     st.radio('', ["DRUSEN"])
-        # with cls3:
-        #     st.radio('', ["DME"])
-        # with cls4:
-        #     st.radio('', ["NORMAL"])
-        with side_1:
-            check_emb = st.checkbox('Embdedding Space Visuzalization')
-
-        with side_2:
-            check_samp = st.checkbox('Random Sample Visuzalization')
-
-        if check_emb and check_samp:
-            st.write("Emb and vis")
-            if option.startswith("Rep"):
-                filter_lst = list(filter(lambda k: clss in k, representative_id_list))
-                show_random_samples(filter_lst,clss)
-                show_tsne_vis("./figures/tsne_representative.png", title="Representative")
-            else:
-                filter_lst = list(filter(lambda k: clss in k, borderline_id_list))
-                show_random_samples(filter_lst,clss)
-                show_tsne_vis(f"{ROOT_FIG_DIR}/tsne_borderline.png", title="Borderline")
-        elif check_emb:
-            st.write("embedding vis")
-            if option.startswith("Rep"):
-                show_tsne_vis(f"{ROOT_FIG_DIR}/tsne_representative.png", title="Representative")
-            else:
-                show_tsne_vis(f"{ROOT_FIG_DIR}/tsne_borderline.png", title="Borderline")
-        elif check_samp:
-            st.write("rand vis")
-            if option.startswith("Rep"):
-                filter_lst = list(filter(lambda k: clss in k, representative_id_list))
-                show_random_samples(filter_lst,clss)
-            else:
-                filter_lst = list(filter(lambda k: clss in k, borderline_id_list))
-                show_random_samples(filter_lst,clss)
-
-
-        # f = st.sidebar.file_uploader("Please Select to Upload an Image", type=['png', 'jpg', 'jpeg', 'tiff', 'gif'])
-        # if f is not None:
-        #     tfile = tempfile.NamedTemporaryFile(delete=True)
-        #     tfile.write(f.read())
-        #     st.sidebar.write('Please wait for the magic to happen! This may take up to a minute.')
-        #     run_app(tfile)
-    # elif app_mode == SIDEBAR_OPTION_INSTANCE_AUG:
-    #     DF_TEST_PROP = load_pd_data_frame(TEST_CSV_FILE)
-    #     IMG_PATH_LISTS = get_path_list_from_df(DF_TEST_PROP)
-    #     get_sample()
-    #     option = st.sidebar.selectbox('Please select a sample image, then choose augmentations', IMG_PATH_LISTS)
-
-    #     side_1, side_2 = st.columns(2)
-    #     with side_2:
-    #         st.title("Testing!!")
-    #     with side_1:
-    #         st.title("Demo of Albumentations")
-    #         image_box = st.empty()
-    #         image =load_image(option.replace("F:/","E:/"))
-
-    #                     # proceed only if everything is ok
-
-    #         image_box.image(image, caption="Original  image")
-    #         # image was loaded successfully
-    #         placeholder_params = get_placeholder_params(image)
-
-    #             # load the config
-    #         augmentations = load_augmentations_config(
-    #                 placeholder_params, "configs/augs.json"
-    #             )
-
-    #             # get the list of transformations names
-    #         transform_names = select_transformations(augmentations, interface_type="Simple")
-
-    #             # get parameters for each transform
-    #         transforms = get_transormations_params(transform_names, augmentations)
-
-    #         data, error = run_augmentations(transforms, image)
-
-    #         if error == 0:
-    #             augmented_image = data["image"]
-    #                 # show title
-    #             # st.title("Demo of Albumentations")
-    #                 # show the images
-    #             width_transformed = int(
-    #                     image.shape[1]  / image.shape[1] * augmented_image.shape[1]
-    #             )
-    #             image_box.image(
-    #                         augmented_image,
-    #                         caption="Transformed image",
-    #                     )
-    #         # side_1.image(augmented_image, caption="Original  image")
-
-    else:
-        raise ValueError('Selected sidebar option is not implemented. Please open an issue on Github: https://github.com/kaplansinan/MLOps')
-
-    # st.plotly_chart(fig)
-
-# new_model = load_model(MODEL_PATH)
-main()
-expander_faq = st.expander("More About Our Project")
-expander_faq.write("Hi there! If you have any questions about our project, or simply want to check out the source code, please visit our github repo: https://github.com/kaplansinan/MLOPS")
+if 'user_group' not in st.session_state:
+    index_tmp = 0
+else: 
+    index_tmp = USER_GROUPS.index(st.session_state['user_group'])
+
+#Sidebar for USER GROUPS
+st.sidebar.title("USER GROUPS")
+backend = st.sidebar.selectbox(
+            "Select User-Group ", USER_GROUPS, index=index_tmp
+        )
+
+st.session_state['user_group'] = backend
+
+st.title("DecisionExploration Panel for OCT Image Analysis")
+st.write(
+        """
+       This panel provides information on the evaluation of the AI model’s performance, including details on the metrics used and the results of the evaluation. USerrs can also find 
+       our notes regarding the issues. The performance metric visualizations and samples of failure and success cases are given in in this panel as well.""")
+
+list_test = """<ul>
+                    <li>Evaluation Metrics: This tab explains the details of the performance metrics and how each metric is calculated. 
+                        Users can also find the characteristics of the evaluation data set. </li>
+                </ul>"""
+st.markdown(list_test, unsafe_allow_html=True)
+
+if backend == "Developer":
+    get_product_dev_page_layout()