hawkeye-finegrained / hawkeye Goto Github PK

作者您好~

请问有关于库中不同方法的性能比较的表格吗非论文的，指的是基于这个库复现后的希望能进一步研究下，感谢~

I followed the steps inscribed to install it, but there was a problem ：ModuleNotFoundError: No module named 'utils.repository'.
Is there a problem with my path settings?

(hawkeye) root:/tmp/pycharm_project_Hawkeye/Hawkeye# python Examples/APINet.py --config configs/APINet.yaml
Traceback (most recent call last):
File "Examples/APINet.py", line 8, in
from model.loss.APINet_loss import APINetLoss
File "/tmp/pycharm_project_Hawkeye/Hawkeye/model/init.py", line 1, in
from .methods import *
File "/tmp/pycharm_project_Hawkeye/Hawkeye/model/methods/init.py", line 1, in
from .BCNN import BCNN
File "/tmp/pycharm_project_Hawkeye/Hawkeye/model/methods/BCNN.py", line 3, in
from model.backbone import vgg16
File "/tmp/pycharm_project_Hawkeye/Hawkeye/model/backbone/init.py", line 1, in
from .vgg import vgg11, vgg13, vgg16, vgg19, vgg11_bn, vgg13_bn, vgg16_bn, vgg19_bn
File "/tmp/pycharm_project_Hawkeye/Hawkeye/model/backbone/vgg.py", line 7, in
from model.registry import BACKBONE
File "/tmp/pycharm_project_Hawkeye/Hawkeye/model/registry.py", line 1, in
from utils.repository import Repository
ModuleNotFoundError: No module named 'utils.repository'

Thanks for the awosome sharing! Really appearate this work!

While run the testing scripts: python3 test.py --config configs/test.yaml (i have already trained APINet )

experiment: name: test_APINet cuda: [0] dataset: name: cub root_dir: data/bird/CUB_200_2011/images meta_dir: metadata/cub batch_size: 32 num_workers: 4 transformer: resize_size: 448 image_size: 448 model: name: APINet num_classes: 200 load: results/APINet/API_res101_1/best_model.pth

it reports the following message:

Traceback (most recent call last): File "/home/haidongwang/code/Hawkeye/test.py", line 147, in <module> tester.test() File "/home/haidongwang/code/Hawkeye/test.py", line 119, in test self.validate() File "/home/haidongwang/code/Hawkeye/test.py", line 129, in validate self.batch_validate(data) File "/home/haidongwang/code/Hawkeye/test.py", line 135, in batch_validate logits = self.model(images) File "/home/haidongwang/anaconda3/envs/chenli/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/home/haidongwang/code/Hawkeye/model/methods/APINet.py", line 34, in forward intra_pairs, inter_pairs, intra_labels, inter_labels = self.get_pairs(pool_out, targets) File "/home/haidongwang/code/Hawkeye/model/methods/APINet.py", line 77, in get_pairs distance_matrix = pdist(embeddings).detach().cpu().numpy() File "/home/haidongwang/code/Hawkeye/model/methods/APINet.py", line 117, in pdist distance_matrix = -2 * vectors.mm(torch.t(vectors)) + vectors.pow(2).sum(dim=1).view(1, -1) \ **RuntimeError: t() expects a tensor with <= 2 dimensions, but self is 4D**

When I use private data to train the mosquito task. My goal is to both show pictures of mosquitoes and if only use one important part to classify a certain type of mosquito. However, I find it difficult to code the metadata file myself. Do you recommend a solution to manually create the metadata file for custom data?