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
add self supervised depth completion. #711
add self supervised depth completion. #711
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
linter test failed, please merge master and refer to https://github.com/modelscope/modelscope/blob/master/docs/source/develop_cn.md#1-%E4%BB%A3%E7%A0%81%E9%A3%8E%E6%A0%BC to format your code
@@ -0,0 +1,34 @@ | |||
calib_time: 09-Jan-2012 13:57:47 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this file should be added to model directory rather than code library, even though this is data releated, which probably on fit for kitti dataset?
Tasks.self_supervised_depth_completion, module_name=Models.self_supervised_depth_completion) | ||
class SelfSupervisedDepthCompletion(TorchModel): | ||
"""SelfSupervisedDepthCompletion Class""" | ||
def __init__(self, model_dir: str, *args, **kwargs): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
model is expected to be a subclass of TorchModel which should have init func to initiate the network of model, and call function which implements the forward process of the model. it seems this model implementation is more like a trainer
model_dir = inputs['model_dir'] | ||
source_dir = inputs['source_dir'] | ||
self.model.run(model_dir, source_dir) | ||
return {OutputKeys.OUTPUT: 'Done'} |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
|
||
@PIPELINES.register_module( | ||
Tasks.self_supervised_depth_completion, module_name=Pipelines.self_supervised_depth_completion) | ||
class SelfSupervisedDepthCompletionPipeline(Pipeline): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
please refer to https://github.com/modelscope/modelscope/blob/master/modelscope/pipelines/cv/card_detection_correction_pipeline.py#L36 to add more docstr for pipeline
"output": { | ||
"type": "object", | ||
"properties": { | ||
"output": { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
the key str and type should be the same as declared in outputs.py
7730714
to
756a87a
Compare
No description provided.