0. 可視化特征圖
import matplotlib.pyplot as plt
import time
def vis(x):
t = ((x.norm(dim=1)).squeeze()).cpu()
plt.imshow(t, cmap=plt.get_cmap('gist_rainbow'))
plt.show()
# plt.imsave(f"didi/{time.strftime('%Y%m%d-%H%M%S', time.localtime())}.jpg",t, cmap=plt.get_cmap('gist_rainbow'))
1. matplotlib > hist
參考：176:hxm/wetectron-master/proposal/
package:
.pkl文件：pickle--python對象的持久化存儲
import pickle
plt.figure(dpi=200)
plt.hist([0.5], bins=50) # orange
plt.hist(p2b_2, bins=len(_p2b_2[_p2b_2 > 0]), alpha = 0.7, label='P2BNet')
plt.hist([0.5], bins=50) # green
plt.hist(match_iou, bins=50, alpha = 0.5, label='UFO$^2$')
plt.xlim(0, 1)
plt.ylim(1, 150000)
plt.legend(fontsize=18)
plt.tick_params(labelsize=20)
plt.ticklabel_format(style='sci',scilimits=(-1,2),axis='y')
plt.xlabel("Mean IoU", fontsize=21)
plt.savefig("ufo-p2b.png",dpi=200, bbox_inches='tight')
2. MMDetection > image_demo
- 參考：mmdetection/demo/image_demo.py
- 基礎代碼：
img = '000000001639.jpg'
config_file = '../configs/faster_rcnn_r50_fpn_1x_coco.py'
checkpoint_file = 'epoch_12.pth'
model = init_detector(config_file, checkpoint_file, device='cuda:0')
result = inference_detector(model, img)
show_result_pyplot(model, img, result, score_thr=0.8)
- 擴展1：批量圖片/指定圖片集合 ---> for
- 擴展2：保存可視化圖片 ---> out_file參數(shù)
# show_result_pyplot(model, img, result, score_thr=0.8)
model.show_result(
img,
result,
score_thr=0.8,
show=False, # True
wait_time=0,
win_name='result',
bbox_color=(72, 101, 241),
text_color=(72, 101, 241),
out_file= {OUT_DIR}) # add
# api: mmdet.models.detectors.base.BaseDetector.show_result()
- 擴展3：可視化gt ---> in: 標注文件
- 擴展4：可視化點
