How to visualize the test result ? about bayesian-crowd-counting HOT 4 OPEN

Hi! Here is my codes to visualize the estimated density map:

dm = outputs.squeeze().detach().cpu().numpy()
plt.imshow(dm, cmap=CM.jet)
plt.savefig(save_path)

from bayesian-crowd-counting.

The visualization code is right, but in the paper, we normalize output by its max value for better visualization.

from bayesian-crowd-counting.

你好，这样可视化是否正确？
dm = outputs.squeeze().detach().cpu().numpy()

dm_normalized = dm / np.max(dm)

plt.imshow(dm_normalized, cmap=cm.jet, vmin=0, vmax=1)

i += 1

plt.savefig("./image/{}.png".format(i))

from bayesian-crowd-counting.

你好！这是我可视化估计密度图的代码：

dm = outputs.squeeze().detach().cpu().numpy()
plt.imshow(dm, cmap=CM.jet)
plt.savefig(save_path)

你好！请问这段代码是加在test.py后面吗

from bayesian-crowd-counting.