Leo Xiong

Results 6 issues of Leo Xiong

- [ ] add support to multi-GPU training by wrapping the model with `DtataParallel` - [ ] add function to automatically save the best checkpoint

enhancement

The shape of `conv_layer_output_value` is (1, 14, 14, 512), and the shape of `pooled_grads_value` is (512, ). So it will cause IndexError when multiple `conv_layer_output_value[:, :, i]` with `pooled_grads_value[i]` in...

This issue occurred when I tried to visualize heatmaps of class activation. First, I copied the sample code on the e-book and got this error: ``` IndexError Traceback (most recent...

First of all, thank authors for the neat repo! When I tested "type": "UNetResnet" and "backbone": "resnet50", there is a bug caused by bad url in [this line]( https://gitlab.liu.se/zilxi06/tsbb19_semantic_segmentation/-/blob/master/models/resnet.py?ref_type=heads#L24) I...

Firstly, thank you for this inspiring work and for publishing the code of CDN-PSMNet and CDN-SDN. Second, can you please be so kind also to provide the code for the...

Congratulations on this great work! (深受启发) For my current work, I am trying to understand motion prediction and tracking prediction. 1. In the multimodality motion/trajactory prediction, the prediction is in...