display_simulation_curves.py 3.5 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120
  1. import numpy as np
  2. import pandas as pd
  3. import matplotlib.pyplot as plt
  4. import os, sys, argparse
  5. from modules.utils.data import get_image_features
  6. from modules.utils import config as cfg
  7. learned_zones_folder = cfg.learned_zones_folder
  8. models_name = cfg.models_names_list
  9. label_freq = 6
  10. def display_curves(folder_path, model_name):
  11. """
  12. @brief Method used to display simulation given .csv files
  13. @param folder_path, folder which contains all .csv files obtained during simulation
  14. @param model_name, current name of model
  15. @return nothing
  16. """
  17. for name in models_name:
  18. if name in model_name:
  19. data_filename = model_name
  20. learned_zones_folder_path = os.path.join(learned_zones_folder, data_filename)
  21. data_files = [x for x in os.listdir(folder_path) if '.png' not in x]
  22. scene_names = [f.split('_')[3] for f in data_files]
  23. for id, f in enumerate(data_files):
  24. print(scene_names[id])
  25. path_file = os.path.join(folder_path, f)
  26. scenes_zones_used_file_path = os.path.join(learned_zones_folder_path, scene_names[id] + '.csv')
  27. zones_used = []
  28. with open(scenes_zones_used_file_path, 'r') as f:
  29. zones_used = [int(x) for x in f.readline().split(';') if x != '']
  30. print(zones_used)
  31. df = pd.read_csv(path_file, header=None, sep=";")
  32. fig=plt.figure(figsize=(35, 22))
  33. fig.suptitle("Detection simulation for " + scene_names[id] + " scene", fontsize=20)
  34. for index, row in df.iterrows():
  35. row = np.asarray(row)
  36. threshold = row[2]
  37. start_index = row[3]
  38. step_value = row[4]
  39. counter_index = 0
  40. current_value = start_index
  41. while(current_value < threshold):
  42. counter_index += 1
  43. current_value += step_value
  44. fig.add_subplot(4, 4, (index + 1))
  45. plt.plot(row[5:])
  46. if index in zones_used:
  47. ax = plt.gca()
  48. ax.set_facecolor((0.9, 0.95, 0.95))
  49. # draw vertical line from (70,100) to (70, 250)
  50. plt.plot([counter_index, counter_index], [-2, 2], 'k-', lw=2, color='red')
  51. if index % 4 == 0:
  52. plt.ylabel('Not noisy / Noisy', fontsize=20)
  53. if index >= 12:
  54. plt.xlabel('Samples per pixel', fontsize=20)
  55. x_labels = [id * step_value + start_index for id, val in enumerate(row[5:]) if id % label_freq == 0]
  56. x = [v for v in np.arange(0, len(row[5:])+1) if v % label_freq == 0]
  57. plt.xticks(x, x_labels, rotation=45)
  58. plt.ylim(-1, 2)
  59. plt.savefig(os.path.join(folder_path, scene_names[id] + '_simulation_curve.png'))
  60. #plt.show()
  61. def main():
  62. parser = argparse.ArgumentParser(description="Display simulations curves from simulation data")
  63. parser.add_argument('--folder', type=str, help='Folder which contains simulations data for scenes')
  64. parser.add_argument('--model', type=str, help='Name of the model used for simulations')
  65. args = parser.parse_args()
  66. p_folder = args.folder
  67. if args.model:
  68. p_model = args.model
  69. else:
  70. # find p_model from folder if model arg not given (folder path need to have model name)
  71. if p_folder.split('/')[-1]:
  72. p_model = p_folder.split('/')[-1]
  73. else:
  74. p_model = p_folder.split('/')[-2]
  75. print(p_model)
  76. display_curves(p_folder, p_model)
  77. print(p_folder)
  78. if __name__== "__main__":
  79. main()