Closed ERGOWHO closed 1 year ago
Hi! I met the same error as you. Could you tell me how can i solve it? Thank you!
@ERGOWHO
Hi! I met the same error as you. Could you tell me how can i solve it? Thank you!
Hi I think the author actually said this in the readme, just set mesh_freq: 40 Then it works perfectly!
Thank you for your suggestion, but when I modify the mesh_ Freq: 40, the same issue still occurs, even adding message resolution according to the author's suggestion, which makes me puzzled. Here are the terminal output and ESLAM.yaml and replica.yaml files I ran. Can you give me some suggestions? Thank you.
For simplicity, I only ran 50 frames.
(eslam) :~/experiment/ESLAM$ python visualizer.py configs/Replica/room0.yaml --output output/Replica/room0 --top_view --save_rendering
Get ckpt : output/Replica/room0/ckpts/01999.tar
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:05<00:00, 9.90it/s]
ffmpeg version 3.4.11-0ubuntu0.1 Copyright (c) 2000-2022 the FFmpeg developers
built with gcc 7 (Ubuntu 7.5.0-3ubuntu1~18.04)
configuration: --prefix=/usr --extra-version=0ubuntu0.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared
libavutil 55. 78.100 / 55. 78.100
libavcodec 57.107.100 / 57.107.100
libavformat 57. 83.100 / 57. 83.100
libavdevice 57. 10.100 / 57. 10.100
libavfilter 6.107.100 / 6.107.100
libavresample 3. 7. 0 / 3. 7. 0
libswscale 4. 8.100 / 4. 8.100
libswresample 2. 9.100 / 2. 9.100
libpostproc 54. 7.100 / 54. 7.100
Input #0, image2, from 'output/Replica/room0/tmp_rendering/*.jpg':
Duration: 00:00:03.57, start: 0.000000, bitrate: N/A
Stream #0:0: Video: mjpeg, yuvj420p(pc, bt470bg/unknown/unknown), 1853x1025 [SAR 1:1 DAR 1853:1025], 30 fps, 30 tbr, 30 tbn, 30 tbc
Stream mapping:
Stream #0:0 -> #0:0 (mjpeg (native) -> h264 (libx264))
Press [q] to stop, [?] for help
[swscaler @ 0x5604f978dae0] deprecated pixel format used, make sure you did set range correctly
[libx264 @ 0x5604f9361b40] using SAR=2292/2293
[libx264 @ 0x5604f9361b40] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512
[libx264 @ 0x5604f9361b40] profile High, level 3.1
[libx264 @ 0x5604f9361b40] 264 - core 152 r2854 e9a5903 - H.264/MPEG-4 AVC codec - Copyleft 2003-2017 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=16 lookahead_threads=2 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=25 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=23.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00
Output #0, mp4, to 'output/Replica/room0/vis.mp4':
Metadata:
encoder : Lavf57.83.100
Stream #0:0: Video: h264 (libx264) (avc1 / 0x31637661), yuvj420p(pc), 926x512 [SAR 474368:474575 DAR 1853:1025], q=-1--1, 30 fps, 15360 tbn, 30 tbc
Metadata:
encoder : Lavc57.107.100 libx264
Side data:
cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: -1
frame= 107 fps=0.0 q=-1.0 Lsize= 36kB time=00:00:03.46 bitrate= 84.3kbits/s speed=6.16x
video:34kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 6.180592%
[libx264 @ 0x5604f9361b40] frame I:1 Avg QP: 7.85 size: 1375
[libx264 @ 0x5604f9361b40] frame P:27 Avg QP:16.91 size: 840
[libx264 @ 0x5604f9361b40] frame B:79 Avg QP:15.84 size: 122
[libx264 @ 0x5604f9361b40] consecutive B-frames: 0.9% 0.0% 5.6% 93.5%
[libx264 @ 0x5604f9361b40] mb I I16..4: 99.1% 0.0% 0.9%
[libx264 @ 0x5604f9361b40] mb P I16..4: 0.0% 0.0% 0.0% P16..4: 0.6% 0.4% 0.2% 0.0% 0.0% skip:98.7%
[libx264 @ 0x5604f9361b40] mb B I16..4: 0.0% 0.0% 0.0% B16..8: 0.5% 0.1% 0.0% direct: 0.0% skip:99.4% L0:47.2% L1:46.7% BI: 6.1%
[libx264 @ 0x5604f9361b40] 8x8 transform intra:1.2% inter:21.4%
[libx264 @ 0x5604f9361b40] coded y,uvDC,uvAC intra: 1.2% 2.8% 2.6% inter: 0.2% 0.4% 0.4%
[libx264 @ 0x5604f9361b40] i16 v,h,dc,p: 97% 0% 3% 0%
[libx264 @ 0x5604f9361b40] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 14% 0% 79% 5% 1% 0% 0% 0% 0%
[libx264 @ 0x5604f9361b40] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 20% 22% 40% 5% 4% 3% 3% 3% 1%
[libx264 @ 0x5604f9361b40] i8c dc,h,v,p: 96% 2% 2% 0%
[libx264 @ 0x5604f9361b40] Weighted P-Frames: Y:74.1% UV:44.4%
[libx264 @ 0x5604f9361b40] ref P L0: 60.6% 4.8% 18.4% 9.9% 6.4%
[libx264 @ 0x5604f9361b40] ref B L0: 87.7% 7.8% 4.5%
[libx264 @ 0x5604f9361b40] ref B L1: 99.2% 0.8%
[libx264 @ 0x5604f9361b40] kb/s:75.61
ESLAM.yaml scale: 1 verbose: False device: "cuda:0" keyframe_device: "cuda:0" ## Change this to "cpu" to reduce GPU memory usage planes_res: coarse: 0.24 fine: 0.06 bound_dividable: 0.24 c_planes_res: coarse: 0.24 fine: 0.03 meshing: level_set: 0 resolution: 0.05 # Increase this number to speed up meshing algorithm eval_rec: False mesh_bound_scale: 1.02 tracking: ignore_edge_W: 75 ignore_edge_H: 75 vis_freq: 4000 vis_inside_freq: 400 const_speed_assumption: True no_vis_on_first_frame: True gt_camera: False lr_T: 0.001 lr_R: 0.001 pixels: 2000 iters: 8 w_sdf_fs: 10 w_sdf_center: 200 w_sdf_tail: 50 w_depth: 1 w_color: 5 mapping: every_frame: 4 joint_opt: True joint_opt_cam_lr: 0.001 no_vis_on_first_frame: True no_mesh_on_first_frame: True no_log_on_first_frame: True vis_freq: 4000 vis_inside_freq: 400 #each iteration mesh_freq: 40 #4000 ckpt_freq: 500 keyframe_every: 4 mapping_window_size: 20 keyframe_selection_method: 'overlap' lr_first_factor: 5 lr_factor: 1 pixels: 4000 iters_first: 1000 iters: 15 w_sdf_fs: 5 w_sdf_center: 200 w_sdf_tail: 10 w_depth: 0.1 w_color: 5 lr: decoders_lr: 0.001 planes_lr: 0.005 c_planes_lr: 0.005 cam: H: 680 W: 1200 fx: 600.0 fy: 600.0 cx: 599.5 cy: 339.5 png_depth_scale: 6553.5 #for depth image in png format crop_edge: 0 rendering: n_stratified: 32 n_importance: 8 perturb: True learnable_beta: True model: c_dim: 32 truncation: 0.06
replica.yaml dataset: 'replica' meshing: resolution: 0.05 # Increase this number to speed up meshing algorithm eval_rec: True tracking: ignore_edge_W: 75 ignore_edge_H: 75 lr_T: 0.002 lr_R: 0.001 pixels: 2000 iters: 8 mapping: pixels: 4000 iters: 15 cam: H: 680 W: 1200 fx: 600.0 fy: 600.0 cx: 599.5 cy: 339.5 png_depth_scale: 6553.5 #for depth image in png format crop_edge: 0 rendering: n_stratified: 32 n_importance: 8 learnable_beta: True
I do not have any errors or working in the previews steps, but after I run python visualizer.py configs/Replica/room0.yaml --output output/Replica/room0 --top_view --save_rendering
I only got this red line and green line moving video, the background, which is supposed to be the room0, is just white color.
Is this the same for everyone?