-
Notifications
You must be signed in to change notification settings - Fork 1.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
load a caffe pre-trained model? #49
Comments
It is possible, but it's not well documented. On the "New Image Classification Model" page, under the "Custom Network" tab, you have two form fields:
|
I see. Thank you. But how about loading a prebuilt data db? |
You can definitely import your pretrained model and fine-tune it in DIGITS on other images. If you want to use the CIFAR10 dataset again, you'll have to extract the images from the distributed binary format into a folder of folders of images, like DIGITS expects, and create a dataset in DIGITS. |
Fair enough. Thank you lukeyeager for the prompt response. I appreciate if you consider adding an option in the future to import prebuilt leveldb data for instance. |
Will do, thanks for the suggestion! |
Hi, I've got an additional question on this topic. I would like to create a model using custom network + pretrained model, but without having to specify a dataset. Since the model is already pretrained, I would like to be able to run the "Classify one image" or "classify many images" without having to train the network again. |
DIGITS is not a deployment solution, it is a training system. As such, it has been designed assuming that datasets are created and models are trained within DIGITS. Also, the emphasis has been on making training efficient, not inference. That being said, if you want to still use DIGITS to test a model, you can hack it together.
Now, you have your "dummy dataset". Then, to create your model:
|
Thanks. This worked out really well! |
@lukeyeager I followed your comments on May 6 and my custom image dataset have been working just fine. However, I would like to make sure a thing about synset_word.txt (Labels). My own data path is like this. Is my synset_word.txt correct? train.txt val.txt my own synset_word.txt for my train.txt and val.txt I followed synset_word.txt from ilsvrc12, is below. n01440764 tench, Tinca tinca In caffe, I do not have to set synset_word.txt unless you are going to classify images with classify command with synset_word.txt. However, DIGITS required label file. Why does DIGITS require Label file? |
That should work fine. Is it not working for you?
For classification models, you need some sort of mapping from number to string. The network only outputs numbers and probabilities like:
With a
|
@lukeyeager Yes, my dataset works fine. I just wanna make sure about it. I am pretty much sure about that the label file is used for only classifying image files by applying a trained caffe model like AlexNet because caffe FT or Training do not require me the label file while I am creating my dataset. I can create it later. Am I correct? Therefore, I thought the label file was not necessary for DIGITS to creating dataset. However, DIGITS required me to upload the label file before I created my datasets. It is a good habit for me to create the label file before creating dataset. |
Yes. DIGITS wants all the information about your dataset all at once - you can't edit it after the fact. I'm contemplating ways to make that more flexible. Would it really be a big help to you to be able to add the labels file after the fact? |
Hello @lukeyeager I have just started working with digits 2.0 and I am not being able to train the model using AlexNet for the CIFAR10 data set. it gives me the following error and training gets aborted: ERROR: error code -8 relu4 -> conv4 (in-place) Kindly help..Thanks |
@krishhtof look at the "Raw caffe output" to see if you get more information. If you still need help, please open a new issue rather than adding to this unrelated discussion. |
Thank you, yes I have also joined another Group at G+ for Digits and put my query there too.. |
@lukeyeager I am trying to load the VGG 19-layer model from here on DIGITS 2. When I try to start the training it gives me the following error: `` Traceback (most recent call last): What am I missing here? I tried to add a loss layer at the end but the same error. I am wondering if you can load it on your DIGITS. Thanks! |
Hello,
I start training, but it stops because of an error : "file not found" When I look at the command line that it generates during training, I see that the weight file was not composed as it should : So, for some reason, the path that I provided was not used, but the 'job path' was added as a prefix, and my model path was splitted. So, the weight parameter should be as follows : How can I make this work, anyone an idea? |
Oh, that's unfortunate, DIGITS is confusing the colon in args.append('--weights=%s' % ','.join(map(lambda x: self.path(x), self.pretrained_model.split('|')))) |
Thanks. Changed it in : That seems to work ... |
@Dexter123193 did you find a solution to this? |
Yes,
To include the pretrained models you dont have to upload them. Just put
them in the said repository and they will be available under the
‘pretrained models’ label on DIGITS.
I hope it makes sense. Otherwise I’ll send you snaps later to make the
instructions clear.
Regards.
…On Tue, 26 Jun 2018 at 4:17 AM, Sanket ***@***.***> wrote:
@Dexter123193 <https://github.com/Dexter123193> did you find a solution
to this?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#49 (comment)>, or mute
the thread
<https://github.com/notifications/unsubscribe-auth/AdZam3_f-0r9k34npHMm8HYMzlN-5FC5ks5uAW-KgaJpZM4D7gj6>
.
|
@Dexter123193 Hi,When I upload the Pretrained Models on Digits 5.0.0 (installed by deb file). I got the same error page says "BadRequestKeyError ...". I am not quite clear about what you did. Can you tell me what files and where you put them? thanks |
It is not an issue per se.
Is it possible to load a pre-trained model from caffe (still nvidia branch) command line? For instance, if I want to start from the imagenet model (and weights) and modify/train the last layer, etc... or load something from the zoo.
Thanks,
The text was updated successfully, but these errors were encountered: