nVidia.app.box.com

wget https://nvidia.box.com/shared/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth -O models/mobilenet-v1-ssd-mp-0_675.pth wget https://nvidia.box.com/shared/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth -O models/mobilenet-v1-ssd-mp-0_675.pth
–2021-09-26 02:51:17-- https://nvidia.box.com/shared/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth
正在解析主机 nvidia.box.com (nvidia.box.com)… 103.116.4.197
正在连接 nvidia.box.com (nvidia.box.com)|103.116.4.197|:443… 已连接。
已发出 HTTP 请求,正在等待回应… 301 Moved Permanently
位置:/public/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth [跟随至新的 URL]
–2021-09-26 02:51:18-- https://nvidia.box.com/public/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth
再次使用存在的到 nvidia.box.com:443 的连接。
已发出 HTTP 请求,正在等待回应… 301 Moved Permanently
位置:https://nvidia.app.box.com/public/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth [跟随至新的 URL]
–2021-09-26 02:51:18-- https://nvidia.app.box.com/public/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth
正在解析主机 nvidia.app.box.com (nvidia.app.box.com)… 203.98.7.65, 2001::45ab:e644
正在连接 nvidia.app.box.com (nvidia.app.box.com)|203.98.7.65|:443… 失败:连接超时。
正在连接 nvidia.app.box.com (nvidia.app.box.com)|2001::45ab:e644|:443… 失败:网络不可达。
–2021-09-26 02:53:33-- http://wget/
正在解析主机 wget (wget)… 失败:未知的名称或服务。
wget: 无法解析主机地址 “wget”
–2021-09-26 02:53:33-- https://nvidia.box.com/shared/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth
正在连接 nvidia.box.com (nvidia.box.com)|103.116.4.197|:443… 已连接。
已发出 HTTP 请求,正在等待回应… 301 Moved Permanently
位置:/public/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth [跟随至新的 URL]
–2021-09-26 02:53:33-- https://nvidia.box.com/public/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth
再次使用存在的到 nvidia.box.com:443 的连接。
已发出 HTTP 请求,正在等待回应… 301 Moved Permanently
位置:https://nvidia.app.box.com/public/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth [跟随至新的 URL]
–2021-09-26 02:53:34-- https://nvidia.app.box.com/public/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth
正在连接 nvidia.app.box.com (nvidia.app.box.com)|203.98.7.65|:443… 失败:连接超时。
正在连接 nvidia.app.box.com (nvidia.app.box.com)|2001::45ab:e644|:443… 失败:网络不可达。

EOFError: Ran out of input

Hi junxing.liang,

Please check below topic to see if can help:
connecting to nvidia.app.box.com |8.7.198.45|:443 failed: connection time out, How to resolve the p… - Jetson & Embedded Systems / Jetson TX2 - NVIDIA Developer Forums

Thanks for your help. I have setup a vpn connection, sloved the download problem. In China, make a vpn conneciton on linux is getting harder and harder( I set up a vpn conneciton using macbook, then setup a http proxy server for my jetson nanno) Besides this, can you teach me how to set up VPN? Thank you very much

Or can you download it for me? I can’t download it for a week

wget https://nvidia.box.com/shared/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth -O 型号/移动网-v1-ssd-mp-0_675.pth wget https://nvidia.box.com/shared/static/djf5w54rjvpqocsiztzaandq1m3avr7c.pth -O 型号/移动网-v1-ssd-mp-0_675.pth

Hi @junxing.liang, can you try downloading the file from this URL?

https://storage.googleapis.com/models-hao/mobilenet-v1-ssd-mp-0_675.pth

It is from the upstream pytorch-ssd repo here: https://github.com/qfgaohao/pytorch-ssd

Thank you very much. At present, we have encountered new problems

ljx@ljx-desktop:~/jetson-inference/python/training/detection/ssd$ python3 train_ssd.py --data=data/fruit --model-dir=models/fruit --batch-size=4 --epochs=30
2021-09-29 08:52:44 - Using CUDA…
2021-09-29 08:52:44 - Namespace(balance_data=False, base_net=None, base_net_lr=0.001, batch_size=4, checkpoint_folder=‘models/fruit’, dataset_type=‘open_images’, datasets=[‘data/fruit’], debug_steps=10, extra_layers_lr=None, freeze_base_net=False, freeze_net=False, gamma=0.1, lr=0.01, mb2_width_mult=1.0, milestones=‘80,100’, momentum=0.9, net=‘mb1-ssd’, num_epochs=30, num_workers=2, pretrained_ssd=‘models/mobilenet-v1-ssd-mp-0_675.pth’, resume=None, scheduler=‘cosine’, t_max=100, use_cuda=True, validation_epochs=1, weight_decay=0.0005)
2021-09-29 08:52:44 - Prepare training datasets.
2021-09-29 08:52:44 - loading annotations from: data/fruit/sub-train-annotations-bbox.csv
2021-09-29 08:52:44 - annotations loaded from: data/fruit/sub-train-annotations-bbox.csv
num images: 5145
2021-09-29 08:53:05 - Dataset Summary:Number of Images: 5145
Minimum Number of Images for a Class: -1
Label Distribution:
Apple: 3622
Banana: 1574
Grape: 2560
Orange: 6186
Pear: 757
Pineapple: 534
Strawberry: 7553
Watermelon: 753
2021-09-29 08:53:05 - Stored labels into file models/fruit/labels.txt.
2021-09-29 08:53:05 - Train dataset size: 5145
2021-09-29 08:53:05 - Prepare Validation datasets.
2021-09-29 08:53:05 - loading annotations from: data/fruit/sub-test-annotations-bbox.csv
2021-09-29 08:53:05 - annotations loaded from: data/fruit/sub-test-annotations-bbox.csv
num images: 930
2021-09-29 08:53:09 - Dataset Summary:Number of Images: 930
Minimum Number of Images for a Class: -1
Label Distribution:
Apple: 329
Banana: 132
Grape: 446
Orange: 826
Pear: 107
Pineapple: 105
Strawberry: 754
Watermelon: 125
2021-09-29 08:53:09 - Validation dataset size: 930
2021-09-29 08:53:09 - Build network.
2021-09-29 08:53:09 - Init from pretrained ssd models/mobilenet-v1-ssd-mp-0_675.pth
2021-09-29 08:53:09 - Took 0.55 seconds to load the model.
2021-09-29 08:53:21 - Learning rate: 0.01, Base net learning rate: 0.001, Extra Layers learning rate: 0.01.
2021-09-29 08:53:21 - Uses CosineAnnealingLR scheduler.
2021-09-29 08:53:21 - Start training from epoch 0.
/home/ljx/.local/lib/python3.6/site-packages/torch/optim/lr_scheduler.py:123: UserWarning: Detected call of lr_scheduler.step() before optimizer.step(). In PyTorch 1.1.0 and later, you should call them in the opposite order: optimizer.step() before lr_scheduler.step(). Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at torch.optim — PyTorch 1.9.1 documentation
torch.optim — PyTorch 1.9.1 documentation”, UserWarning)
/home/ljx/.local/lib/python3.6/site-packages/torch/nn/_reduction.py:44: UserWarning: size_average and reduce args will be deprecated, please use reduction=‘sum’ instead.
warnings.warn(warning.format(ret))
THCudaCheck FAIL file=/local/jetbot/pytorch/aten/src/THCUNN/generic/SpatialDepthwiseConvolution.cu line=202 error=701 : too many resources requested for launch
Traceback (most recent call last):
File “train_ssd.py”, line 343, in
device=DEVICE, debug_steps=args.debug_steps, epoch=epoch)
File “train_ssd.py”, line 123, in train
loss.backward()
File “/home/ljx/.local/lib/python3.6/site-packages/torch/tensor.py”, line 185, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File “/home/ljx/.local/lib/python3.6/site-packages/torch/autograd/init.py”, line 127, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: cuda runtime error (701) : too many resources requested for launch at /local/jetbot/pytorch/aten/src/THCUNN/generic/SpatialDepthwiseConvolution.cu:202

Please open a new topic about this unrelated issue.

How did you install PyTorch?

size_average and reduce args will be deprecated, please use reduction=‘sum’ instead.

You can ignore this warning. Locking this thread now since it has become off-topic.