clementpinard / depthnet Goto Github PK

I am getting an error on the following.

depthnet = DepthNet()
weights = torch.load('DepthNet_elu_bn_512.pth.tar')
depthnet.load_state_dict(weights['state_dict'], strict=False)

RuntimeError: While copying the parameter named conv1.0.weight, whose dimensions in the model are torch.Size([32, 6, 3, 3]) and whose dimensions in the checkpoint are torch.Size([32, 8, 3, 3]).

It seems that the DepthNet512 had 8 channels in the first conv layer, which are not reflected in the model class. Is that so?

Hi, thank you very much for sharing your work. I was wondering if you can explain a bit why are you using ELU+1. And if you have some thoughts about why is performing better.

great job! I tried to download still box dataset through torrent but it is really slow. Do you a faster solution for me to download it? Or just a part of it (like only the 512 set). Thank you so much!

I have tried to download your pretrained weights but the link is broken.

How can I download those files?

Thank you

any other means?

Joe

magnet:?xt=urn:btih:4d3a60ad3c9ceac7662735ba8e90fb467b43a3aa&tr=http%3A%2F%2Facademictorrents.com%2Fannounce.php&tr=udp%3A%2F%2Ftracker.publicbt.com%3A80%2Fannounce&tr=udp%3A%2F%2Ftracker.openbittorrent.com%3A80%2Fannounce

Based on the nvidia-smi, only one graphic card is used when I run

python3 train.py -j8 --lr 0.01 /path/to/still_box/64/ --log-output --activation-function elu --bn

My question is how can I use another graphic card, say I got two 1080Tl

Joe

jc@marvel-001:~$ nvidia-smi
Sun Sep 2 16:26:40 2018
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 396.44 Driver Version: 396.44 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 1080 Off | 00000000:04:00.0 Off | N/A |
| 29% 40C P8 7W / 180W | 2892MiB / 8119MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 1 GeForce GTX 1080 Off | 00000000:08:00.0 Off | N/A |
| 27% 30C P8 6W / 180W | 10MiB / 8119MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 2 GeForce GTX 1080 Off | 00000000:09:00.0 Off | N/A |
| 27% 27C P8 6W / 180W | 10MiB / 8119MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 3 GeForce GTX 1080 Off | 00000000:83:00.0 Off | N/A |
| 27% 29C P8 6W / 180W | 10MiB / 8119MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 4 GeForce GTX 1080 Off | 00000000:84:00.0 Off | N/A |
| 27% 31C P8 6W / 180W | 10MiB / 8119MiB | 0% Default |
+-------------------------------+----------------------+----------------------+
| 5 GeForce GTX 1080 Off | 00000000:88:00.0 Off | N/A |
| 27% 29C P8 6W / 180W | 10MiB / 8119MiB | 0% Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 9275 C python3 497MiB |
| 0 11041 C python3 2383MiB |
+-----------------------------------------------------------------------------+

Pls help

train.py:222: UserWarning: invalid index of a 0-dim tensor. This will be an error in PyTorch 0.5. Use tensor.item() to convert a 0-dim tensor to a Python number
losses.update(loss.data[0], target.size(0))
train.py:223: UserWarning: invalid index of a 0-dim tensor. This will be an error in PyTorch 0.5. Use tensor.item() to convert a 0-dim tensor to a Python number
train_writer.add_scalar('train_loss', loss.data[0], n_iter)
train.py:225: UserWarning: invalid index of a 0-dim tensor. This will be an error in PyTorch 0.5. Use tensor.item() to convert a 0-dim tensor to a Python number
depth2_metric_errors.update(depth2_metric_error.data[0], target.size(0))

• Avg Loss : 8.032, Avg Depth error : 16.633, normalized : 1.154
  100% (2813 of 2813) |########################################| Elapsed Time: 5:35:49 ETA: 00:00:00
  dfdepth2_normalized_errors.update(depth2_norm_error.data[0], target.size(0))
  train.py:239: UserWarning: invalid index of a 0-dim tensor. This will be an error in PyTorch 0.5. UsN/A% (0 of 219) | | Elapsed Time: 0:00:00 ETA: --:--:--
  writer.writerow([loss.data[0], depth2_metric_error.data[0]])
  train.py:269: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
  input_var = torch.autograd.Variable(torch.cat(input_tensors, 1), volatile=True)
  train.py:270: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
  target_var = torch.autograd.Variable(target, volatile=True)
  Traceback (most recent call last):
  File "/home/jc/.local/lib/python3.6/site-packages/PIL/Image.py", line 2460, in fromarray
  mode, rawmode = _fromarray_typemap[typekey]
  KeyError: ((1, 1, 64), '|u1')

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "train.py", line 301, in
main()
File "train.py", line 158, in main
depth_error, normalized = validate(val_loader, model, epoch, term_logger, output_writers)
File "train.py", line 276, in validate
output_writers[i].add_image('GroundTruth', util.tensor2array(target[0].cpu(), max_value=100), 0)
File "/usr/local/lib/python3.6/dist-packages/tensorboardX/writer.py", line 412, in add_image

File "/usr/local/lib/python3.6/dist-packages/tensorboardX/summary.py", line 205, in image
image = make_image(tensor, rescale=rescale)

image = Image.fromarray(tensor)

File "/home/jc/.local/lib/python3.6/site-packages/PIL/Image.py", line 2463, in fromarray

TypeError: Cannot handle this data type