Successfully generating results_dict!

.gitignore

@@ -4,3 +4,7 @@ output
 share
 input_img.jpg
 input_img.jpg
+app.py
+input_img.jpg
+requirements.txt
+__pycache__

=1.12

@@ -1,14 +1,14 @@
-Requirement already satisfied: xtcocotools in ./lib/python3.10/site-packages (1.14.3)
-Requirement already satisfied: numpy>=1.20.0 in ./lib/python3.10/site-packages (from xtcocotools) (1.23.0)
-Requirement already satisfied: setuptools>=18.0 in ./lib/python3.10/site-packages (from xtcocotools) (65.5.0)
-Requirement already satisfied: cython>=0.27.3 in ./lib/python3.10/site-packages (from xtcocotools) (3.0.7)
-Requirement already satisfied: matplotlib>=2.1.0 in ./lib/python3.10/site-packages (from xtcocotools) (3.7.4)
-Requirement already satisfied: cycler>=0.10 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (0.12.1)
-Requirement already satisfied: fonttools>=4.22.0 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (4.47.0)
-Requirement already satisfied: contourpy>=1.0.1 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (1.2.0)
-Requirement already satisfied: packaging>=20.0 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (23.2)
-Requirement already satisfied: pyparsing>=2.3.1 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (2.4.5)
-Requirement already satisfied: kiwisolver>=1.0.1 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (1.4.5)
-Requirement already satisfied: python-dateutil>=2.7 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (2.8.2)
-Requirement already satisfied: pillow>=6.2.0 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (9.4.0)
-Requirement already satisfied: six>=1.5 in ./lib/python3.10/site-packages (from python-dateutil>=2.7->matplotlib>=2.1.0->xtcocotools) (1.16.0)
+Requirement already satisfied: xtcocotools in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (1.14.3)
+Requirement already satisfied: cython>=0.27.3 in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (from xtcocotools) (3.0.7)
+Requirement already satisfied: setuptools>=18.0 in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (from xtcocotools) (60.2.0)
+Requirement already satisfied: numpy>=1.20.0 in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (from xtcocotools) (1.26.3)
+Requirement already satisfied: matplotlib>=2.1.0 in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (from xtcocotools) (3.8.2)
+Requirement already satisfied: pyparsing>=2.3.1 in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (3.1.1)
+Requirement already satisfied: fonttools>=4.22.0 in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (4.47.0)
+Requirement already satisfied: cycler>=0.10 in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (0.12.1)
+Requirement already satisfied: packaging>=20.0 in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (23.2)
+Requirement already satisfied: python-dateutil>=2.7 in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (2.8.2)
+Requirement already satisfied: contourpy>=1.0.1 in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (1.2.0)
+Requirement already satisfied: kiwisolver>=1.3.1 in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (1.4.5)
+Requirement already satisfied: pillow>=8 in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (10.2.0)
+Requirement already satisfied: six>=1.5 in /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages (from python-dateutil>=2.7->matplotlib>=2.1.0->xtcocotools) (1.16.0)

app.py

@@ -11,15 +11,22 @@ os.system("pip install 'mmpose'")
 
 import gradio as gr
 
-def generate_output(front_img, side_img):
+def generate_output(front_img_path, side_img_path):
     # TODO: These file names will need to be unique in case of multiple requests at once, and they will need to be deleted after the function is done.
-    front_keypoint_result = predict_pose(front_img, "front.jpg")
-    side_keypoint_result = predict_pose(side_img, "side.jpg")
+    front_keypoint_result = predict_pose(front_img_path, "front.jpg")
+    side_keypoint_result = predict_pose(side_img_path, "side.jpg")
 
-    front_seg_mask = calculate_seg_mask(front_img)
-    side_rcnn_mask = calculate_seg_mask(side_img)
+    # Should we create the image separately? Seems weird to get it as a result from this only to use it in something else below.
+    front_image = front_keypoint_result[0]
+    side_image = side_keypoint_result[0]
 
-    measures = calculate_all_measures(front_keypoint_result, side_keypoint_result, front_seg_mask, side_rcnn_mask)
+    front_keypoint_data = front_keypoint_result[1]
+    side_keypoint_data = side_keypoint_result[1]
+
+    front_seg_mask = calculate_seg_mask(front_img_path)
+    side_rcnn_mask = calculate_seg_mask(side_img_path)
+
+    measures = calculate_all_measures(front_image, side_image, front_keypoint_data, side_keypoint_data, front_seg_mask, side_rcnn_mask)
 
     return (front_keypoint_result[0], front_keypoint_result[1], side_keypoint_result[0], side_keypoint_result[1])
 

calculate_masks.py

@@ -3,8 +3,6 @@ from transformers import SegformerImageProcessor, AutoModelForSemanticSegmentati
 import torch.nn as nn
 
 def calculate_seg_mask(image):
-    image = Image.open(image).convert("RGB")
-
     processor = SegformerImageProcessor.from_pretrained("mattmdjaga/segformer_b2_clothes")
     model = AutoModelForSemanticSegmentation.from_pretrained("mattmdjaga/segformer_b2_clothes")
 

calculate_measures.py

@@ -1,4 +1,5 @@
 import numpy as np
+import pandas as pd
 
 def get_width(mask, keypoint_y):
     pred_np = mask.numpy()
@@ -10,9 +11,35 @@ def get_width(mask, keypoint_y):
 
     return last_index-first_index
 
-def calculate_all_measures(front_keypoints, side_keypoints, front_seg_mask, side_rcnn_mask):
+def calculate_bbox(original_image, keypoint_1, keypoint_2):
+    # Determine bounding box coordinates
+    min_x = 0
+    min_y = int(min(keypoint_1[1], keypoint_2[1]))
+    max_y = int(max(keypoint_1[1], keypoint_2[1]))
+    # Set max_x to be the width of the image
+    max_x = original_image.size[0]
+    return [min_x, max_x, min_y, max_y]
+
+def get_volume_result(mask_of_interest, original_image, max_x, min_x, max_y, min_y):
+    # thr = mask_of_interest[mask_of_interest > 0].mean()
+    thr = 0
+    if min_x < 0 or max_x > mask_of_interest.shape[1] or min_y < 0 or max_y > mask_of_interest.shape[0]:
+        print("Warning: Invalid indices for slicing.")
+    if min_x < max_x and min_y < max_y:
+        region_inside_bounding_box = mask_of_interest[min_y:max_y, min_x:max_x] > thr
+        return region_inside_bounding_box.sum()
+    else:
+        print("Invalid bounding box indices.")
+    return None
+
+def calculate_all_measures(front_image, side_image, front_keypoint_data, side_keypoint_data, front_seg_mask, side_rcnn_mask):
     results_dict = {}
 
+    front_keypoints = front_keypoint_data['keypoints']
+    front_keypoint_names = front_keypoint_data['keypoint_names']
+    side_keypoints = side_keypoint_data['keypoints']
+    side_keypoint_names = side_keypoint_data['keypoint_names']
+
     # calculate the body length
     # pick the longer from the two ankle keypoints on y coordinate
     side_body_length = side_keypoints[15][1] if side_keypoints[15][1] > side_keypoints[16][1] else side_keypoints[16][1]
@@ -56,49 +83,51 @@ def calculate_all_measures(front_keypoints, side_keypoints, front_seg_mask, side
     results_dict['waist_width'] = get_width(front_seg_mask, waist_y)
 
     # Calculate bounding box for thigh
-    # right_knee = side_keypoints[side_keypoint_names.index("right_knee")]
-    # right_hip = side_keypoints[side_keypoint_names.index("right_hip")]
-    # # Calculate bounding box for torso
-    # right_shoulder = side_keypoints[side_keypoint_names.index("right_shoulder")]
-
-    # # Replace keypoints, keypoint_names, combined_mask, and original_image with your actual data
-    # thigh_bbox = calculate_bbox(side_original_image, right_knee, right_hip)
-    # torso_bbox = calculate_bbox(side_original_image, right_hip, right_shoulder)
-    # # Calculate midpoint coordinates
-    # torso_midpoint = [0, (right_hip[1] + right_shoulder[1]) / 2]
-    # lower_torso_bbox = calculate_bbox(side_original_image, right_hip, torso_midpoint)
-    # upper_torso_bbox = calculate_bbox(side_original_image, torso_midpoint, right_shoulder)
-
-    # # Replace keypoints, keypoint_names, combined_mask, and original_image with your actual data
-    # thigh_area = get_volume_result(side_rcnn_mask, side_original_image, thigh_bbox[1], thigh_bbox[0], thigh_bbox[3], thigh_bbox[2]) # Thigh volume
-    # torso_area = get_volume_result(side_rcnn_mask, side_original_image, torso_bbox[1], torso_bbox[0], torso_bbox[3], torso_bbox[2]) # Torso volume
-    # lower_torso_area = get_volume_result(side_rcnn_mask, side_original_image, lower_torso_bbox[1], lower_torso_bbox[0], lower_torso_bbox[3], lower_torso_bbox[2]) # Lower torso volume
-    # upper_torso_area = get_volume_result(side_rcnn_mask, side_original_image, upper_torso_bbox[1], upper_torso_bbox[0], upper_torso_bbox[3], upper_torso_bbox[2]) # Upper torso volume
-    # full_side_body_area = (side_rcnn_mask > 0).sum()
-    # # print(f"Thigh area: {thigh_area}")
-    # # print(f"Torso area: {torso_area}")
-    # # print(f"Lower torso area: {lower_torso_area}")
-    # # print(f"Upper torso area: {upper_torso_area}")
-    # results_dict['thigh_area'] = thigh_area
-    # results_dict['torso_area'] = torso_area
-    # results_dict['lower_torso_area'] = lower_torso_area
-    # results_dict['upper_torso_area'] = upper_torso_area
-    # results_dict['full_side_body_area'] = full_side_body_area
+    right_knee = side_keypoints[side_keypoint_names.index("right_knee")]
+    right_hip = side_keypoints[side_keypoint_names.index("right_hip")]
+    # Calculate bounding box for torso
+    right_shoulder = side_keypoints[side_keypoint_names.index("right_shoulder")]
+
+    # Replace keypoints, keypoint_names, combined_mask, and original_image with your actual data
+    thigh_bbox = calculate_bbox(side_image, right_knee, right_hip)
+    torso_bbox = calculate_bbox(side_image, right_hip, right_shoulder)
+    # Calculate midpoint coordinates
+    torso_midpoint = [0, (right_hip[1] + right_shoulder[1]) / 2]
+    lower_torso_bbox = calculate_bbox(side_image, right_hip, torso_midpoint)
+    upper_torso_bbox = calculate_bbox(side_image, torso_midpoint, right_shoulder)
+
+    # Replace keypoints, keypoint_names, combined_mask, and original_image with your actual data
+    thigh_area = get_volume_result(side_rcnn_mask, side_image, thigh_bbox[1], thigh_bbox[0], thigh_bbox[3], thigh_bbox[2]) # Thigh volume
+    torso_area = get_volume_result(side_rcnn_mask, side_image, torso_bbox[1], torso_bbox[0], torso_bbox[3], torso_bbox[2]) # Torso volume
+    lower_torso_area = get_volume_result(side_rcnn_mask, side_image, lower_torso_bbox[1], lower_torso_bbox[0], lower_torso_bbox[3], lower_torso_bbox[2]) # Lower torso volume
+    upper_torso_area = get_volume_result(side_rcnn_mask, side_image, upper_torso_bbox[1], upper_torso_bbox[0], upper_torso_bbox[3], upper_torso_bbox[2]) # Upper torso volume
+    full_side_body_area = (side_rcnn_mask > 0).sum()
+    # print(f"Thigh area: {thigh_area}")
+    # print(f"Torso area: {torso_area}")
+    # print(f"Lower torso area: {lower_torso_area}")
+    # print(f"Upper torso area: {upper_torso_area}")
+    results_dict['thigh_area'] = thigh_area
+    results_dict['torso_area'] = torso_area
+    results_dict['lower_torso_area'] = lower_torso_area
+    results_dict['upper_torso_area'] = upper_torso_area
+    results_dict['full_side_body_area'] = full_side_body_area
 
     # # calculate ratios
-    # results_dict['thigh_normalised'] = thigh_area / side_body_length
-    # results_dict['torso_normalised'] = torso_area / side_body_length
-    # results_dict['thigh_to_torso_ratio_normalised'] = results_dict['thigh_normalised'] / results_dict['torso_normalised']
-    # results_dict['thigh_to_torso_ratio'] = thigh_area / torso_area
-    # results_dict['upper_torso_normalised'] = upper_torso_area / side_body_length
-    # results_dict['lower_torso_normalised'] = lower_torso_area / side_body_length
-    # results_dict['upper_to_lower_torso_normalised_ratio'] =  results_dict['upper_torso_normalised'] / results_dict['lower_torso_normalised']
-    # results_dict['upper_to_lower_torso_ratio'] = upper_torso_area / lower_torso_area
-    # results_dict['shoulder_to_hip_ratio'] = results_dict['shoulder_width'] / results_dict['hip_width']
-    # results_dict['shoulder_to_waist_ratio'] = results_dict['shoulder_width'] / results_dict['waist_width']
-    # results_dict['waist_to_hip_ratio'] = results_dict['waist_width'] / results_dict['hip_width']
-    # results_dict['thigh_to_body_ratio'] = thigh_area / full_side_body_area
-    # results_dict['upper_torso_to_body_ratio'] = upper_torso_area / full_side_body_area
-    # results_dict['upper_torso_to_body_ratio'] = upper_torso_area / full_side_body_area
-
-    return dict
+    results_dict['thigh_normalised'] = thigh_area / side_body_length
+    results_dict['torso_normalised'] = torso_area / side_body_length
+    results_dict['thigh_to_torso_ratio_normalised'] = results_dict['thigh_normalised'] / results_dict['torso_normalised']
+    results_dict['thigh_to_torso_ratio'] = thigh_area / torso_area
+    results_dict['upper_torso_normalised'] = upper_torso_area / side_body_length
+    results_dict['lower_torso_normalised'] = lower_torso_area / side_body_length
+    results_dict['upper_to_lower_torso_normalised_ratio'] =  results_dict['upper_torso_normalised'] / results_dict['lower_torso_normalised']
+    results_dict['upper_to_lower_torso_ratio'] = upper_torso_area / lower_torso_area
+    results_dict['shoulder_to_hip_ratio'] = results_dict['shoulder_width'] / results_dict['hip_width']
+    results_dict['shoulder_to_waist_ratio'] = results_dict['shoulder_width'] / results_dict['waist_width']
+    results_dict['waist_to_hip_ratio'] = results_dict['waist_width'] / results_dict['hip_width']
+    results_dict['thigh_to_body_ratio'] = thigh_area / full_side_body_area
+    results_dict['upper_torso_to_body_ratio'] = upper_torso_area / full_side_body_area
+    results_dict['upper_torso_to_body_ratio'] = upper_torso_area / full_side_body_area
+
+    results_df = pd.DataFrame(results_dict)
+
+    return results_dict

requirements.txt

@@ -18,3 +18,4 @@ thop~=0.1.1-2209072238
 timm~=0.9.2
 super-gradients~=3.2.0
 openmim
+transformers