zw

Finetuneing a pretrained ResNet50_v1d in gluoncv

2

Hi, there! Environment: `Ubuntu 18.04, MXNet-cu92 1.3.1, Gluon-Cv 0.4 (Master)` I'm trying to finetuneing a gluoncv pretrained `ResNet50_v1d` classification model. But there is something strange going on. When I finetuned...

How to debug internal function and variable in gluoncv

2

For example, I want to use pdb to set a breakpoint at hybrid_forward function of class RPN > b /home/user/.local/lib/python3.6/site-packages/gluoncv-0.3.0-py3.6.egg/gluoncv/model_zoo/rpn/rpn.py:95 And yet I find program stop at a strange place:...

As the title implies, it would be great to see the training log of convmixer.

RuntimeError: Expected to mark a variable ready only once.

5

**Checklist** 1. I have searched related issues but cannot get the expected help. 2. The bug has not been fixed in the latest version. **Describe the bug** The code runs...

Inveption V3 weights loading problem

4

this code: ` model=InceptionV3(include_top=False, weights='imagenet', input_tensor=None, input_shape=None, pooling=None)` always return this error > Exception: URL fetch failure on https://github.com/fchollet/deep-learning-models/releases/download/v0.5/inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5: None -- [Errno 10060] So I want to manully download the...

Questions about experimental results

2

Hi, I have some questions regarding the performance of your code. The original paper's performance ( using the Cityscapes training set as the source domain and the Foggy Cityscapes validation...

[BUG] CPU Memory Leakage on TPU

3

**Describe the bug** I find strange memory behaviour with `bits_and_tpu` timm code on tpu. If the layer decay learning rate is set (`--layer-decay`), the memory usage just keep going up....

CPU Memory Leakage on TPU

7

**Description** I find strange memory behaviour with updating layer wise learning rate decay on tpu. If the layer decay learning rate is set (`--layer-decay`), the memory usage just keep going...

Multi-frame Fusion

6

Hi, I have been reading this code for some time, but I fail to find any multi-frame fusion config. All I have found is num_sweeps=1: https://github.com/Megvii-BaseDetection/BEVDepth/blob/16d7854156efcc9353ab5a45d3250e5f1ab0fd76/exps/bev_depth_lss_r50_256x704_128x128_24e.py#L222 Does it mean that...

Training and evaluation on Waymo open dataset

2

Hi, Yinhao, thanks for the great work. Sorry to bother you. I wonder if the code support or will support to do training and evaluation on Waymo dataset.. Could you...