search

alexgkendall / SegNet-Tutorial

Files for a tutorial to train SegNet for road scenes using the CamVid dataset
http://mi.eng.cam.ac.uk/projects/segnet/tutorial.html
851 stars 518 forks source link

about driving.caffemodel fetch #11

Closed killerjian007 closed 8 years ago

killerjian007 commented 8 years ago

Hi, @alexgkendall Thanks for your excellent work! Now I want to download the driving.caffemodel in Example_Models/driving_web_demo/, but find the lfs data quota is exceeded, Is there any alternative way to access the model file?

Here is what I've got after running git lfs fetch/pull:

Git LFS: (0 of 1 files) 0 B / 112.35 MB This repository is over its data quota. Purchase more data packs to restore access. Docs: https://help.github.com/articles/purchasing-additional-storage-and-bandwidth-for-a-personal-account/

Thanks.

alexgkendall commented 8 years ago

@killerjian007,

Sorry, I'm aware of this issue and will fix it when I am back in the office next week (January 11).

Alex

killerjian007 commented 8 years ago

@alexgkendall i am sorry to interrupt you , about the problem mentioned above, have you already solved it? i really need your help. really appreciate if you can reply soon.

alexgkendall commented 8 years ago

Hi @killerjian007

I've just created a SegNet Model Zoo!

https://github.com/alexgkendall/SegNet-Tutorial/blob/master/Example_Models/segnet_model_zoo.md

You will now be able to download the model, and future models which I release, from here. Sorry for unexpectedly running over my LFS data quota!

Alex

amiltonwong commented 8 years ago

Hi, @alexgkendall , If I use the following command to compute BN statistics: python /SegNet/Scripts/compute_bn_statistics.py /SegNet/Example_Models/segnet_model_driving_webdemo.prototxt /SegNet/Example_Models/segnet_weights_driving_webdemo.caffemodel /SegNet/Models/Inference/

I came across the following error :

Building BN calc net... Traceback (most recent call last): File "/SegNet/Scripts/compute_bn_statistics.py", line 171, in testable_msg = make_testable(args.train_model) File "/SegNet/Scripts/compute_bn_statistics.py", line 35, in make_testable text_format.Merge(train_str, train_net) File "/root/anaconda/lib/python2.7/site-packages/google/protobuf/text_format.py", line 265, in Merge return MergeLines(text.split('\n'), message) File "/root/anaconda/lib/python2.7/site-packages/google/protobuf/text_format.py", line 298, in MergeLines _ParseOrMerge(lines, message, True) File "/root/anaconda/lib/python2.7/site-packages/google/protobuf/text_format.py", line 229, in _ParseOrMerge _MergeField(tokenizer, message, allow_multiple_scalars) File "/root/anaconda/lib/python2.7/site-packages/google/protobuf/text_format.py", line 382, in _MergeField _MergeField(tokenizer, sub_message, allow_multiple_scalars) File "/root/anaconda/lib/python2.7/site-packages/google/protobuf/text_format.py", line 382, in _MergeField _MergeField(tokenizer, sub_message, allow_multiple_scalars) File "/root/anaconda/lib/python2.7/site-packages/google/protobuf/text_format.py", line 356, in _MergeField message_descriptor.full_name, name)) google.protobuf.text_format.ParseError: 1605:5 : Message type "caffe.ArgMaxParameter" has no field named "axis".

Any suggestion?

alexgkendall commented 8 years ago

Hi @amiltonwong , you don't need to compute bn statistics for the demo model, it's already done. As for the error it looks like you are not running the SegNet version of caffe in your python script?