Question about "Ld_value" and configuration

[AlKitChung]

Hi! Thank you for sharing the code. I attempted to train it using the Dr. Johnson dataset, but encountered an error." [ITER 1000] Evaluating train: L1 0.07388863191008568 PSNR 19.659012985229495 [02/05 16:00:35] Traceback (most recent call last): File "train.py", line 328, in training(lp.extract(args), op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint, args.debug_from) File "train.py", line 189, in training training_report(tb_writer, iteration, Ll1, Ln, loss, l1_loss, iter_start.elapsed_time(iter_end), testing_iterations, scene, render, (pipe, background), Ld_value/(viewpoint_cam.image_height * viewpoint_cam.image_width), gradnorm) File "train.py", line 298, in training_report tb_writer.add_histogram("scene/opacity_histogram", scene.gaussians.get_opacity, iteration) File "/home/xxxx/anaconda3/envs/gs/lib/python3.8/site-packages/torch/utils/tensorboard/writer.py", line 485, in add_histogram histogram(tag, values, bins, max_bins=max_bins), global_step, walltime File "/home/xxxx/anaconda3/envs/gs/lib/python3.8/site-packages/torch/utils/tensorboard/summary.py", line 358, in histogram hist = make_histogram(values.astype(float), bins, max_bins) File "/home/xxxx/anaconda3/envs/gs/lib/python3.8/site-packages/torch/utils/tensorboard/summary.py", line 386, in make_histogram cum_counts = np.cumsum(np.greater(counts, 0, dtype=np.int32)) TypeError: No loop matching the specified signature and casting was found for ufunc greater Could you provide some additional guidelines on adjusting the weights and configuration settings?

[TimSong412]

It seems to be the problem of "add_histogram". Would you please try removing this line? We didn't run into this problem before.