Closed smalltingting closed 5 months ago
configs and weights are updated
how to download weights? thanks
It is starting a baiduNetdiskHost program and asking for username and password, i don't know Chinese, I suppose that is what it is asking. I don't have a password...
On Tue, Apr 16, 2024 at 3:22 PM Yuxuan Li @.***> wrote:
If you can get access to BaiduDisk, here is the link https://pan.baidu.com/s/1SuEOl_ImqjoT5Y3pYxZt4w?pwd=c6fo
— Reply to this email directly, view it on GitHub https://github.com/zcablii/SARDet_100K/issues/6#issuecomment-2058961106, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO3HQPTNO5NRTH4XFURDS7DY5UJZJAVCNFSM6AAAAABFRHLADOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANJYHE3DCMJQGY . You are receiving this because you commented.Message ID: @.***>
No worries, give me a second, I will upload everything to OneDrive
thanks a lot
On Tue, Apr 16, 2024 at 3:49 PM Yuxuan Li @.***> wrote:
— Reply to this email directly, view it on GitHub https://github.com/zcablii/SARDet_100K/issues/6#issuecomment-2059015110, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO3HQPUPIGQFJTCLMEWN4PLY5UM63AVCNFSM6AAAAABFRHLADOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANJZGAYTKMJRGA . You are receiving this because you commented.Message ID: @.***>
additional question => in onedrive for images =>
[image: image.png]
in train there are only 663 images: [image: image.png] and not 94K as mentioned:
[image: image.png]
May I have all the training please?
On Tue, Apr 16, 2024 at 3:52 PM Inga Paster @.***> wrote:
thanks a lot
On Tue, Apr 16, 2024 at 3:49 PM Yuxuan Li @.***> wrote:
— Reply to this email directly, view it on GitHub https://github.com/zcablii/SARDet_100K/issues/6#issuecomment-2059015110, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO3HQPUPIGQFJTCLMEWN4PLY5UM63AVCNFSM6AAAAABFRHLADOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANJZGAYTKMJRGA . You are receiving this because you commented.Message ID: @.***>
Make sure you are using this link for dataset downloading, as given in the README.
ok, thanks,
another question, please => in "Annotations" file, I see only the boundary box definition, but there is no label id: car, ship, etc. where is the information please?
On Tue, Apr 16, 2024 at 4:37 PM Yuxuan Li @.***> wrote:
Make sure you are using this link https://liveuclac-my.sharepoint.com/:f:/g/personal/zcablii_ucl_ac_uk/EutczQ-0LB5BmQ1BEguS-PAB8mLXUChRWPVY2Bn5X4-0_w?e=bxPZij for dataset downloading, as given in the README.
— Reply to this email directly, view it on GitHub https://github.com/zcablii/SARDet_100K/issues/6#issuecomment-2059114745, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO3HQPTZYQHCUF67CC5C2TTY5USQPAVCNFSM6AAAAABFRHLADOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANJZGEYTINZUGU . You are receiving this because you commented.Message ID: @.***>
category labels are denoted as "category_id".
i see, ok, thanks for quick response
the last question in the checkpoint data you sent me to download, I have weights and config =>
[image: image.png]
but how I know to connect each of them with table?
[image: image.png]
for example for yellow config =>
[image: image.png] the name of config file is fg_frcnn_IN_sup_sar_r50.py which is not in checkpoint link you sent me? maybe the name there is different?
On Tue, Apr 16, 2024 at 5:53 PM Yuxuan Li @.***> wrote:
category labels are denoted as "category_id".
— Reply to this email directly, view it on GitHub https://github.com/zcablii/SARDet_100K/issues/6#issuecomment-2059289348, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO3HQPX6BOY66E7G3R2WFFLY5U3NFAVCNFSM6AAAAABFRHLADOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANJZGI4DSMZUHA . You are receiving this because you commented.Message ID: @.***>
yes, some names are different
thanks, now additional question, please.
after downloading the weights and config files from onedrive you have sent me => I ran the next simple code test:
from mmengine.utils import get_git_hash from mmengine.utils.dl_utils import collect_env as collect_base_env import mmdet from mmdet.apis import DetInferencer config_path_2 = './SAR_Yuxuan_weights/r101_sar.py' checkpoint_2 = './SAR_Yuxuan_weights/r101_sar_epoch_100.pth' inferencer_2 = DetInferencer(model=config_path_2, weights=checkpoint_2)
and got the next error => KeyError: 'ImageClassifier is not in the
mmdet::model registry. Please check whether the value of ImageClassifier
is correct or it was registered as expected :
KeyError Traceback (most recent call last) Input In [28], in <cell line: 7>
() 5 config_path_2 = './SAR_Yuxuan_weights/r101_sar.py
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/SAR_Yuxuan_weights/r101_sar.py
' 6 checkpoint_2 = './SAR_Yuxuan_weights/r101_sar_epoch_100.pth
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/SAR_Yuxuan_weights/r101_sar_epoch_100.pth
' ----> 7 inferencer_2 = DetInferencer(model=config_path_2,
weights=checkpoint_2)
File
~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmdet/apis/det_inferencer.py:98
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmdet/apis/det_inferencer.py:98,
in DetInferencer.init(self, model, weights, device, scope, palette,
show_progress) 96
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmdet/apis/det_inferencer.py:96
self.palette = palette 97
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmdet/apis/det_inferencer.py:97
init_default_scope(scope) ---> 98
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmdet/apis/det_inferencer.py:98
super().init( 99
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmdet/apis/det_inferencer.py:99
model=model, weights=weights, device=device, scope=scope) 100
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmdet/apis/det_inferencer.py:100
self.model = revert_sync_batchnorm(self.model) 101
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmdet/apis/det_inferencer.py:101
self.show_progress = show_progress File
~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/infer/infer.py:180
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/infer/infer.py:180,
in BaseInferencer.init(self, model, weights, device, scope,
show_progress) 177
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/infer/infer.py:177
if device is None: 178
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/infer/infer.py:178
device = get_device() --> 180
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/infer/infer.py:180
self.model = self._init_model(cfg, weights, device) # type: ignore 181
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/infer/infer.py:181
self.pipeline = self._init_pipeline(cfg) 182
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/infer/infer.py:182
self.collate_fn = self._init_collate(cfg) File
~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/infer/infer.py:483
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/infer/infer.py:483,
in BaseInferencer._init_model(self, cfg, weights, device) 480
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/infer/infer.py:480
if cfg.model.get('pretrained') is not None: 481
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/infer/infer.py:481
del cfg.model.pretrained
...
106
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/registry/build_functions.py:106
) 107
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/registry/build_functions.py:107
#
this will include classes, functions, partial functions and more 108
https://file+.vscode-resource.vscode-cdn.net/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/~/anaconda3/envs/MSFA/lib/python3.8/site-packages/mmengine/registry/build_functions.py:108
elif callable(obj_type): KeyError: 'ImageClassifier is not in the
mmdet::model registry. Please check whether the value of ImageClassifier
is correct or it was registered as expected. More details can be found at
https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#import-the-custom-module
'
Output is truncated. View as a scrollable element or open in a text editor.
Adjust cell output settings...
Could you advise how to fix it please?
thanks
On Tue, Apr 16, 2024 at 6:29 PM Yuxuan Li @.***> wrote:
yes, some names are different
— Reply to this email directly, view it on GitHub https://github.com/zcablii/SARDet_100K/issues/6#issuecomment-2059368074, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO3HQPQNWC737VNQS4OVUCTY5U7UFAVCNFSM6AAAAABFRHLADOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANJZGM3DQMBXGQ . You are receiving this because you commented.Message ID: @.***>
It is because you load a config and model weight for classification, but use a detection environment(mmdet). You can go to mmpretrain for classification model verification.
I see, my curiosity is to check object detection and not classification. from the config files which you sent me above which one is for detection? thanks
On Thu, Apr 18, 2024 at 7:13 PM Yuxuan Li @.***> wrote:
It is because you load a config and model weight for classification, but use a detection environment(mmdet). You can go to mmpretrain https://github.com/open-mmlab/mmpretrain for classification model verification.
— Reply to this email directly, view it on GitHub https://github.com/zcablii/SARDet_100K/issues/6#issuecomment-2064402256, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO3HQPRNHG5LZHEGVMO2EQDY57WLLAVCNFSM6AAAAABFRHLADOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANRUGQYDEMRVGY . You are receiving this because you commented.Message ID: @.***>
by the way, I took another config file (hope it is detection) =>
from mmengine.utils import get_git_hash from mmengine.utils.dl_utils import collect_env as collect_base_env import mmdet from mmdet.apis import DetInferencer
def collect_env(): """Collect the information of the running environments.""" env_info = collect_base_env() env_info['MMDetection'] = f'{mmdet.version}+{get_git_hash()[:7]}' return env_info
def main():
config_file = './mmdetection/SAR_Yuxuan_weights/fg_frcnn_dota_pretrain_sar_wavelet_r50/fg_frcnn_dota_pretrain_sar_wavelet_r50.py' checkpoint_file = './mmdetection/SAR_Yuxuan_weights/fg_frcnn_dota_pretrain_sar_wavelet_r50/best_coco_bbox_mAP_epoch_12.pth'
inferencer_2 = DetInferencer(model=config_file, weights=checkpoint_file)
if name == 'main': main()
the error is: KeyError: 'Self_features_model is not in the mmdet::model
registry. Please check whether the value of Self_features_model
is
correct or it was registered as expected
Loads checkpoint by local backend from path:
./mmdetection/SAR_Yuxuan_weights/fg_frcnn_dota_pretrain_sar_wavelet_r50/best_coco_bbox_mAP_epoch_12.pth
Traceback (most recent call last):
File "/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/test_2.py",
line 23, in Self_features_model
is correct or it was
registered as expected. More details can be found at
https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#import-the-custom-module
'
On Thu, Apr 18, 2024 at 8:07 PM Inga Paster @.***> wrote:
I see, my curiosity is to check object detection and not classification. from the config files which you sent me above which one is for detection? thanks
On Thu, Apr 18, 2024 at 7:13 PM Yuxuan Li @.***> wrote:
It is because you load a config and model weight for classification, but use a detection environment(mmdet). You can go to mmpretrain https://github.com/open-mmlab/mmpretrain for classification model verification.
— Reply to this email directly, view it on GitHub https://github.com/zcablii/SARDet_100K/issues/6#issuecomment-2064402256, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO3HQPRNHG5LZHEGVMO2EQDY57WLLAVCNFSM6AAAAABFRHLADOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANRUGQYDEMRVGY . You are receiving this because you commented.Message ID: @.***>
please use the configs I provided in the repo. The configs with the weight files are a bit out of date because I made some code refactory and renaming.
I see thanks.. but i took the config file from your repository and weights from Onefrove you sent me and still it is not working:
rom mmengine.utils import get_git_hash from mmengine.utils.dl_utils import collect_env as collect_base_env import mmdet from mmdet.apis import DetInferencer
def collect_env(): """Collect the information of the running environments.""" env_info = collect_base_env() env_info['MMDetection'] = f'{mmdet.version}+{get_git_hash()[:7]}' return env_info
def main():
config_file = './local_configs/SARDet/other_backbones/fg_frcnn_dota_pretrain_sar_r101_wavelet.py' checkpoint_file = './mmdetection/SAR_Yuxuan_weights/fg_frcnn_dota_pretrain_sar_r101_wavelet/best_coco_bbox_mAP_epoch_12.pth'
inferencer_2 = DetInferencer(model=config_file, weights=checkpoint_file)
if name == 'main': main()
error: KeyError: 'MSFA is not in the mmdet::model registry. Please check
whether the value of MSFA
is correct or it was registered as expected.
Loads checkpoint by local backend from path:
./mmdetection/SAR_Yuxuan_weights/fg_frcnn_dota_pretrain_sar_r101_wavelet/best_coco_bbox_mAP_epoch_12.pth
Traceback (most recent call last):
File "/home/paster/Documents/SAR_inference/SARDet_100K/MSFA/test_2.py",
line 23, in MSFA
is correct or it was registered as expected. More
details can be found at
https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#import-the-custom-module
'
(base) **@.***:~/Documents/SAR_inference/SARDet_100K/MSFA$
thank you very much for help
On Thu, Apr 18, 2024 at 11:59 PM Yuxuan Li @.***> wrote:
please use the configs I provided in the repo. The configs with the weight files are a bit out of date because I made some code refractory and renaming.
— Reply to this email directly, view it on GitHub https://github.com/zcablii/SARDet_100K/issues/6#issuecomment-2065313931, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO3HQPSVQC7DA2X3BALECADY6AX47AVCNFSM6AAAAABFRHLADOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANRVGMYTGOJTGE . You are receiving this because you commented.Message ID: @.***>
Your environment is not properly installed.
I see... I did exactly according to repo instructions:
cd MSFA
conda create -y -n MSFA python=3.8 conda activate MSFA
conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.8 -c pytorch -c nvidia
pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 --index-url https://download.pytorch.org/whl/cu118
pip install -U openmim mim install "mmengine==0.8.4" mim install "mmcv==2.0.1" mim install "mmdet==3.1.0"
pip install -r requirements.txt
pip install -v -e .
The conda list is:
#
_libgcc_mutex 0.1 conda_forge conda-forge
_openmp_mutex 4.5 2_gnu conda-forge
addict 2.4.0 pypi_0 pypi
aliyun-python-sdk-core 2.15.1 pypi_0 pypi
aliyun-python-sdk-kms 2.16.2 pypi_0 pypi
appdirs 1.4.4 pypi_0 pypi
asttokens 2.4.1 pyhd8ed1ab_0 conda-forge
backcall 0.2.0 pyh9f0ad1d_0 conda-forge
blas 1.0 mkl
brotli-python 1.0.9 py38heb0550a_2
bzip2 1.0.8 h7b6447c_0
ca-certificates 2024.2.2 hbcca054_0 conda-forge
certifi 2024.2.2 py38h06a4308_0
cffi 1.16.0 pypi_0 pypi
charset-normalizer 2.0.4 pyhd3eb1b0_0
click 8.1.7 pypi_0 pypi
colorama 0.4.6 pypi_0 pypi
comm 0.2.2 pypi_0 pypi
configparser 7.0.0 pypi_0 pypi
contourpy 1.1.1 pypi_0 pypi
crcmod 1.7 pypi_0 pypi
cryptography 42.0.5 pypi_0 pypi
cuda-cudart 11.8.89 0 nvidia
cuda-cupti 11.8.87 0 nvidia
cuda-libraries 11.8.0 0 nvidia
cuda-nvrtc 11.8.89 0 nvidia
cuda-nvtx 11.8.86 0 nvidia
cuda-runtime 11.8.0 0 nvidia
cycler 0.12.1 pypi_0 pypi
debugpy 1.8.1 py38h17151c0_0 conda-forge
decorator 5.1.1 pyhd8ed1ab_0 conda-forge
executing 2.0.1 pyhd8ed1ab_0 conda-forge
ffmpeg 4.3 hf484d3e_0 pytorch
filelock 3.13.1 py38h06a4308_0
fonttools 4.51.0 pypi_0 pypi
freetype 2.11.0 h70c0345_0
giflib 5.2.1 h7b6447c_0
gmp 6.2.1 h295c915_3
gmpy2 2.1.2 py38heeb90bb_0
gnutls 3.6.15 he1e5248_0
idna 3.4 py38h06a4308_0
importlib-metadata 7.1.0 pyha770c72_0 conda-forge
importlib-resources 6.4.0 pypi_0 pypi
importlib_metadata 7.1.0 hd8ed1ab_0 conda-forge
intel-openmp 2021.4.0 h06a4308_3561
ipykernel 6.14.0 py38h7f3c49e_0 conda-forge
ipython 8.4.0 py38h578d9bd_0 conda-forge
ipywidgets 8.1.2 pypi_0 pypi
jedi 0.19.1 pyhd8ed1ab_0 conda-forge
jinja2 3.1.3 py38h06a4308_0
jmespath 0.10.0 pypi_0 pypi
jpeg 9e h7f8727e_0
jupyter_client 8.6.1 pyhd8ed1ab_0 conda-forge
jupyter_core 5.7.2 py38h578d9bd_0 conda-forge
jupyterlab-widgets 3.0.10 pypi_0 pypi
kiwisolver 1.4.5 pypi_0 pypi
kymatio 0.3.0 pypi_0 pypi
lame 3.100 h7b6447c_0
lcms2 2.12 h3be6417_0
ld_impl_linux-64 2.38 h1181459_1
libcublas 11.11.3.6 0 nvidia
libcufft 10.9.0.58 0 nvidia
libcufile 1.9.1.3 0 nvidia
libcurand 10.3.5.147 0 nvidia
libcusolver 11.4.1.48 0 nvidia
libcusparse 11.7.5.86 0 nvidia
libffi 3.3 he6710b0_2
libgcc-ng 13.2.0 h807b86a_5 conda-forge
libgomp 13.2.0 h807b86a_5 conda-forge
libiconv 1.16 h7f8727e_2
libidn2 2.3.2 h7f8727e_0
libnpp 11.8.0.86 0 nvidia
libnvjpeg 11.9.0.86 0 nvidia
libpng 1.6.37 hbc83047_0
libsodium 1.0.18 h36c2ea0_1 conda-forge
libstdcxx-ng 13.2.0 h7e041cc_5 conda-forge
libtasn1 4.16.0 h27cfd23_0
libtiff 4.2.0 h2818925_1
libunistring 0.9.10 h27cfd23_0
libwebp 1.2.2 h55f646e_0
libwebp-base 1.2.2 h7f8727e_0
lz4-c 1.9.3 h295c915_1
markdown 3.6 pypi_0 pypi
markdown-it-py 3.0.0 pypi_0 pypi
markupsafe 2.1.1 py38h7f8727e_0
matplotlib 3.7.5 pypi_0 pypi
matplotlib-inline 0.1.7 pyhd8ed1ab_0 conda-forge
mdurl 0.1.2 pypi_0 pypi
mkl 2021.4.0 h06a4308_640
mkl-service 2.4.0 py38h7f8727e_0
mkl_fft 1.3.1 py38hd3c417c_0
mkl_random 1.2.2 py38h51133e4_0
mmcv 2.0.1 pypi_0 pypi
mmdet 3.1.0 pypi_0 pypi
mmengine 0.8.4 pypi_0 pypi
model-index 0.1.11 pypi_0 pypi
mpc 1.1.0 h10f8cd9_1
mpfr 4.0.2 hb69a4c5_1
mpmath 1.3.0 py38h06a4308_0
msfa 3.1.0 dev_0
Could you send me one config file and one weight file (doesn't matter at this stage the model) which you are sure that are updated and working and exact python code to see detection please ?
On Fri, Apr 19, 2024 at 2:11 PM Yuxuan Li @.***> wrote:
Your environment is not properly installed.
— Reply to this email directly, view it on GitHub https://github.com/zcablii/SARDet_100K/issues/6#issuecomment-2066351911, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO3HQPVFV7ATGFVYVT4GWALY6D3WNAVCNFSM6AAAAABFRHLADOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANRWGM2TCOJRGE . You are receiving this because you commented.Message ID: @.***>
Please use the provided code and weights for model training and testing, as we verified they are working well. I am not sure why you try to run MSFA code under mmdet repo. But I think you should at lease include import msfa
for using msfa models.
Your environment looks fine. I can give you some debugging advice: prepare the dataset and change the dataset paths accordingly in the configuration, then run (for example) python test.py ./local_configs/SARDet/other_backbones/fg_frcnn_dota_pretrain_sar_r101_wavelet.py SOME_PATH/fg_frcnn_dota_pretrain_sar_r101_wavelet/best_coco_ bbox_mAP_epoch_12.pth
to check if you get a valid result. If you encounter some general errors, you can look them up on Google. If the error is related to the mmdet framework, you can go to the "Issues" on the official mmdetection github and search for a solution. It's also possible to drill down to where the error is occurring and trace it back to the code to figure out the underlying problem (most likely some file path issue).
it is working. thanks a lot
On Fri, Apr 19, 2024 at 3:47 PM Yuxuan Li @.***> wrote:
Please use the provided code and weights for model training and testing, as we verified they are working well. I am not sure why you try to run MSFA code under mmdet repo. But I think you should at lease include import msfa for using msfa models.
— Reply to this email directly, view it on GitHub https://github.com/zcablii/SARDet_100K/issues/6#issuecomment-2066503100, or unsubscribe https://github.com/notifications/unsubscribe-auth/AO3HQPWWYW7HCFIIL4OBFODY6EG6RAVCNFSM6AAAAABFRHLADOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANRWGUYDGMJQGA . You are receiving this because you commented.Message ID: @.***>
I can't find and download configs and weights of Single Stage models and End to End models such as DETR and FCOS. Could you please tell me how to solve this problem?Thanks you in advance.