Hi! I have questions to disturb you. When trying to run train_net.py, I have no way to solve 'from config import config'.when the error exists'no mudule named ''config',I try to 'pip install config'.But there are still errors.I have searched for some way,but no way works.Can you help me ?

Hi, author, I have the following problems in running your model

Traceback (most recent call last): File "/DATA/xiexu/yolo/cvpods/tools/train_net.py", line 109, in args=(args,), File "/home/xiexu/.local/lib/python3.7/site-packages/cvpods/engine/launch.py", line 56, in launch main_func(*args) File "/DATA/xiexu/yolo/cvpods/tools/train_net.py", line 74, in main runner = runner_decrator(RUNNERS.get(cfg.TRAINER.NAME))(cfg, build_model) File "/home/xiexu/.local/lib/python3.7/site-packages/cvpods/engine/runner.py", line 86, in init self.data_loader = self.build_train_loader(cfg) File "/home/xiexu/.local/lib/python3.7/site-packages/cvpods/engine/runner.py", line 307, in build_train_loader return build_train_loader(cfg) File "/home/xiexu/.local/lib/python3.7/site-packages/cvpods/data/build.py", line 130, in build_train_loader transform_gens = build_transform_gens(cfg.INPUT.AUG.TRAIN_PIPELINES) File "/home/xiexu/.local/lib/python3.7/site-packages/cvpods/data/build.py", line 69, in build_transform_gens return build(pipelines) File "/home/xiexu/.local/lib/python3.7/site-packages/cvpods/data/build.py", line 58, in build tfm = TRANSFORMS.get(aug)(**args) File "/home/xiexu/.local/lib/python3.7/site-packages/cvpods/utils/registry.py", line 66, in get "No object named '{}' found in '{}' registry!".format(name, self._name) KeyError: "No object named 'RandomShift' found in 'transforms' registry!"

I follow the instructions and install dependencies, cd /YOLOF/playground/detection/coco/yolof/yolof.res50.C5.1x But when I input: pods_train --num-gpus 2 I get a problem: python3: can't open file '/tmp/pip-req-build-6jhijoew/tools/train_net.py': [Errno 2] No such file or directory this what happen?

Hello! I'm trying to re-train this YOLOF in a single 3090 GPU with the batchsize of 32. However, even though I tried to modify some of the parameters like base-lr, steps and something else, the best AP I can get is 35.7688, which is much worse than the AP of 37.7 in your paper. Do you have any suggestions about how to modify base-learning rate, steps and warmup settings? Thank you!

Hi! I really appreciate the authors for doing such an inspiring job and sharing the code.

Somehow, I am kind of confused by the Sec. 4.1 of the paper. In my understanding, comparing MiMo, SiSo using C5 may cause some problems in detecting small object (High level feature with low resolution is preferred for large scale objects). To bridge the gap between SiSo and MiMo, why should we focus on larger objects? Fig 4 discusses about receptive fields. However, receptive fields of low level feature is smaller than C5, if SiSo has the receptive field problem, MiMo should have too!

So, I don't really understand this part. I will be glad if you point me out the problem.

Thanks in advance.

Hi. In your paper, Fig 1 shows SiMo style can get competitively good results, but I am wondering about the detailed architecture during experiments. How do you generate multiple outputs with a single input? Do you pick up outputs from the deeper layers to make predictions like how SSD has done?

https://github.com/megvii-model/YOLOF/blob/6189487b80601dfeda89302c22abac060f977785/playground/detection/coco/yolof/yolof_base/encoder.py#L64-L78

Why the weight initialization method for lateral_conv and fpn_conv is different from the weight initialization method for conv layer in dilated_encoder_blocks?

How to use pretraining weights for training? After downloading the pretraining weight, which folder should I put it in? How to call the pretraining weight file?

Thanks！

Hello, I'm debugging the train under the tools folder 'train_net.py'.But in the cvpods folder, on line 11 of the deform_conv script : from cvpods import C. report an error here: cannot import name ' C 'from' cvpods'

Why is this? Do I need to install any plug-ins? Thanks！

Env:

1. OS version：CentOS 7
2. Environment version: Python 3.6.13 / PyTorch 1.8.0 / CUDA 11.0 / cuDNN version
3. cvpods version：commit id : 82374a1fe5c83e16bdd4d07adae2545d51138ef8_

I ran the following command：

cd playground/detection/coco/yolof/yolof.cspdarknet53.DC5.3x
pods_train --num-gpus 8

Actual results：

Traceback (most recent call last):
  File "/ssd/serser/cvpods/tools/train_net.py", line 109, in <module>
    args=(args,),
  File "/ssd/serser/cvpods/cvpods/engine/launch.py", line 53, in launch
    daemon=False,
  File "/ssd/serser/venv/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 230, in spawn
    return start_processes(fn, args, nprocs, join, daemon, start_method='spawn')
  File "/ssd/serser/venv/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 188, in start_processes
    while not context.join():
  File "/ssd/serser/venv/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 150, in join
    raise ProcessRaisedException(msg, error_index, failed_process.pid)
torch.multiprocessing.spawn.ProcessRaisedException: 

-- Process 0 terminated with the following error:
Traceback (most recent call last):
  File "/ssd/serser/venv/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 59, in _wrap
    fn(i, *args)
  File "/ssd/serser/cvpods/cvpods/engine/launch.py", line 88, in _distributed_worker
    main_func(*args)
  File "/ssd/serser/cvpods/tools/train_net.py", line 74, in main
    runner = runner_decrator(RUNNERS.get(cfg.TRAINER.NAME))(cfg, build_model)
  File "/ssd/serser/cvpods/cvpods/engine/runner.py", line 86, in __init__
    self.data_loader = self.build_train_loader(cfg)
  File "/ssd/serser/cvpods/cvpods/engine/runner.py", line 307, in build_train_loader
    return build_train_loader(cfg)
  File "/ssd/serser/cvpods/cvpods/data/build.py", line 130, in build_train_loader
    transform_gens = build_transform_gens(cfg.INPUT.AUG.TRAIN_PIPELINES)
  File "/ssd/serser/cvpods/cvpods/data/build.py", line 69, in build_transform_gens
    return build(pipelines)
  File "/ssd/serser/cvpods/cvpods/data/build.py", line 58, in build
    tfm = TRANSFORMS.get(aug)(**args)
  File "/ssd/serser/cvpods/cvpods/utils/registry.py", line 66, in get
    "No object named '{}' found in '{}' registry!".format(name, self._name)
KeyError: "No object named 'JitterCrop' found in 'transforms' registry!"

The paper points out the importance of balance matching of label assign, but actually in the code you ignores the anchor(pred) whose iou>NEG_IGNORE_THRESHOLD or < POS_IGNORE_THRESHOLD, which may break the balance?

Also, it seems you ignore the anchor(pred) whose iou > NEG_IGNORE_THRESHOLD only make sense with max-iou label assign, why you use the the anchor(pred) whose iou is maxium or between NEG_IGNORE_THRESHOLD and NEG_IGNORE_THRESHOLD ?

https://github.com/megvii-model/YOLOF/blob/86288132be25f0fc54d3c4b35c97a774222c12fc/playground/detection/coco/yolof/yolof_base/yolof.py#L186-L231

Hello,

You're listing the models on onedrive and baidu. Sadly the link on onedrive is dead and I can't create a baidu account in the US. Can you reupload the models please ?

In the class loss, you use the sigmoid focal loss with the binary cross-entropy loss， why not choose the softmax focal loss? And what may be the reason why the multi-classes loss doesn't converge？

dear author:
your paper writes "Adopting the K nearest anchor as positive anchors for each ground-truth box", but when reading your code, I saw that you selected K nearest positive samples from pred boxes and anchors respectively. In fact, the number of positive samples corresponding to each GT box is 2k. Is this a later improvement? we also attention that uniform matching ignore the positive samples which IoU<0.15.does this will cause some very small targets have none positive samples?

Dear author, when I try to run 'pods_train --num-gpus 1', There are some errors:

ImportError: /home/dl/deep/aqyu/YOLOF/cvpods/_C.cpython-39-x86_64-linux-gnu.so: undefined symbol: _ZN6cvpods26psroi_pooling_forward_cudaERN2at6TensorES2_S2_iifii

hi, I follow the installation instruction, and everything is ok until comes to "Train" part. After cd into playground/detection/coco/yolof/yolof.res50.C5.1x, I run the shell script pods_train --num_gpus 1, and get pods_train: command not found

looking forward to your reply, thanks