Comments (9)
wZuck
commented on August 30, 2024
Please ensure that you have pull the latest commit ee25973, we have fix this problem in this version.
from libfewshot.
Aquariuaa
commented on August 30, 2024
在我的版本中已经修改为了
if config["dataloader_num"] == 1 or mode in ["val", "test"]:
但是仍然报此错误：
File "/home/inspur/MAX_SPACE/Jiyu/LibFewShot-main/core/model/finetuning/renet.py", line 416, in set_forward_loss
) = batch # RENet uses both episode and general dataloaders
ValueError: not enough values to unpack (expected 4, got 2)
from libfewshot.
wZuck
commented on August 30, 2024
你的代码应该不是最新的版本，我的意思不是按照 ee25973 修改。你可以比对一下你使用的代码中该片段是否和
Line 170 in ee25973
from libfewshot.
Aquariuaa
commented on August 30, 2024
感谢您的回答！
经过对比，是一致的。同时我也尝试拉取了最新版本的代码，仍然报此错误。在miniImageNet数据集上，我使用5way1shot+resnet18+RENet的方式进行训练，参数参考了reproduce中的参数设置。
我打印了[elem for each_batch in batch for elem in each_batch]中的我的batch，打印结果如下：
batch:([tensor([[[[ 0.4896, 0.9282, 0.9423, ..., -1.3355, -1.6043, -1.3638], trainer.py:375
[ 0.9282, 1.1545, 0.7584, ..., -1.4628, -1.4770, -1.3638],
[ 1.1687, 1.2536, 0.9989, ..., -1.5336, -1.4062, -1.1233],
...,
[-1.0525, -0.9960, -0.9535, ..., -1.0950, -1.0667, -1.0384],
[-0.9535, -1.1091, -1.1940, ..., -1.2648, -1.0384, -1.1516],
[-1.4487, -0.9677, -1.0101, ..., -1.2506, -1.1657, -1.2082]],
[[-0.7703, -0.5506, -1.2390, ..., -0.6385, -0.5506, -0.6385],
[-1.1804, -1.0339, -1.5026, ..., -0.7996, -0.7410, -0.6531],
[-1.2390, -1.5173, -1.3122, ..., -1.0632, -0.9461, -0.1845],
...,
[-0.0819, -0.1845, -0.0966, ..., 0.0352, -0.2430, -0.2870],
[-0.0380, -0.4041, -0.3895, ..., -0.1112, -0.3456, -0.4627],
[-0.6824, -0.4188, -0.3016, ..., 0.1671, -0.0380, 0.0206]],
[[ 0.3923, -0.1866, 0.2958, ..., 0.9437, 0.8472, 0.8885],
[-0.4348, -0.3245, -0.5037, ..., 0.8334, 0.7783, 0.4750],
[-0.4348, -0.2694, -0.6829, ..., 0.6818, 0.7921, 0.9437],
...,
[ 1.1367, 0.8748, 1.0402, ..., 1.0815, 1.0677, 1.1505],
[ 1.2469, 0.7507, 0.8058, ..., 0.8885, 0.9575, 0.8885],
[ 0.7231, 0.8334, 0.9575, ..., 0.9988, 0.9437, 0.9850]]],
[[[-1.7033, -1.7033, -1.7033, ..., -1.7033, -1.7033, -1.7033],
[-1.7033, -1.7033, -1.7033, ..., -1.7033, -1.7033, -1.7033],
[-1.7033, -1.7033, -1.7033, ..., -1.7033, -1.7033, -1.7033],
...,
[-1.7033, -1.7033, -1.7033, ..., -1.7033, -1.7033, -1.7033],
[-1.7033, -1.7033, -1.7033, ..., -1.7033, -1.7033, -1.7033],
[-1.7033, -1.7033, -1.7033, ..., -1.7033, -1.7033, -1.7033]],
[[-1.6930, -1.6930, -1.6930, ..., -1.6930, -1.6930, -1.6930],
[-1.6930, -1.6930, -1.6930, ..., -1.6930, -1.6930, -1.6930],
[-1.6930, -1.6930, -1.6930, ..., -1.6930, -1.6930, -1.6930],
...,
[-1.6930, -1.6930, -1.6930, ..., -1.6930, -1.6930, -1.6930],
[-1.6930, -1.6930, -1.6930, ..., -1.6930, -1.6930, -1.6930],
[-1.6930, -1.6930, -1.6930, ..., -1.6930, -1.6930, -1.6930]],
[[-1.4410, -1.4410, -1.4410, ..., -1.4410, -1.4410, -1.4410],
[-1.4410, -1.4410, -1.4410, ..., -1.4410, -1.4410, -1.4410],
[-1.4410, -1.4410, -1.4410, ..., -1.4410, -1.4410, -1.4410],
...,
[-1.4410, -1.4410, -1.4410, ..., -1.4410, -1.4410, -1.4410],
[-1.4410, -1.4410, -1.4410, ..., -1.4410, -1.4410, -1.4410],
[-1.4410, -1.4410, -1.4410, ..., -1.4410, -1.4410, -1.4410]]],
[[[-0.1471, -0.3452, -0.4300, ..., 0.2632, 0.2915, 0.3198],
[-0.4017, -0.4583, -0.4583, ..., 0.3339, 0.3481, 0.3622],
[ 0.2491, -0.3734, -0.1188, ..., 0.3764, 0.3905, 0.4047],
...,
[-0.7696, -0.7696, -0.7696, ..., -0.0763, -0.0339, -0.0763],
[-0.7837, -0.7837, -0.7837, ..., -0.0622, -0.0763, -0.0905],
[-0.8120, -0.8120, -0.7979, ..., -0.0905, -0.1046, -0.1188]],
[[ 0.0352, -0.1991, -0.3163, ..., 0.5332, 0.5625, 0.5625],
[-0.2577, -0.3309, -0.3602, ..., 0.6065, 0.6211, 0.6065],
[ 0.3868, -0.2723, -0.0233, ..., 0.6504, 0.6650, 0.6504],
...,
[-0.4188, -0.4188, -0.4041, ..., 0.3868, 0.4307, 0.3868],
[-0.3895, -0.3895, -0.3895, ..., 0.4161, 0.4014, 0.3868],
[-0.4188, -0.4188, -0.4041, ..., 0.3868, 0.3721, 0.3575]],
[[-0.3107, -0.4486, -0.4072, ..., 0.0477, 0.0753, 0.1028],
[-0.4210, -0.4348, -0.3658, ..., 0.1166, 0.1304, 0.1304],
[ 0.3923, -0.2004, 0.0615, ..., 0.1580, 0.1718, 0.1718],
...,
[-0.6415, -0.6415, -0.6415, ..., -0.0764, -0.0212, -0.0626],
[-0.6553, -0.6553, -0.6553, ..., 0.0063, -0.0212, -0.0350],
[-0.6829, -0.6829, -0.6691, ..., -0.0212, -0.0488, -0.0626]]],
...,
[[[ 0.0510, 0.4613, 0.4330, ..., -0.0763, 0.6311, 1.1970],
[-0.1612, 0.1925, 0.2632, ..., -0.0197, 0.5745, 1.0979],
[-0.1188, 0.1925, 0.6169, ..., -0.2744, 0.1359, 0.5037],
...,
[ 0.0793, 0.2632, 0.5320, ..., 0.7584, 0.4896, 0.4754],
[-0.0056, 0.1783, 0.4754, ..., 0.8574, 0.6028, 0.5745],
[ 0.0793, 0.1925, 0.4188, ..., 0.8008, 0.6311, 0.6028]],
[[-0.4627, 0.0060, 0.0938, ..., -0.9607, -0.2870, 0.2403],
[-0.5213, -0.1112, 0.0645, ..., -0.9168, -0.3749, 0.1231],
[-0.1991, 0.1524, 0.6650, ..., -1.2243, -0.8582, -0.5067],
...,
[-1.0046, -0.8142, -0.5653, ..., -0.5653, -0.8582, -0.8875],
[-1.0779, -0.8875, -0.6092, ..., -0.4627, -0.7410, -0.7996],
[-0.9900, -0.8728, -0.6531, ..., -0.5360, -0.7264, -0.7557]],
[[-0.5588, -0.0902, -0.0074, ..., -0.8621, -0.2418, 0.2545],
[-0.6277, -0.2280, -0.0488, ..., -0.8345, -0.3245, 0.1304],
[-0.3521, -0.0074, 0.4888, ..., -1.1516, -0.8207, -0.5037],
...,
[-1.3583, -1.1929, -0.9448, ..., -0.9172, -1.1516, -1.1653],
[-1.4410, -1.3032, -1.0413, ..., -0.8345, -1.0826, -1.1102],
[-1.4273, -1.3170, -1.1102, ..., -0.9034, -1.0689, -1.0964]]],
[[[ 0.5603, 0.6028, 0.6311, ..., -1.0950, -1.0950, -1.0950],
[ 0.5745, 0.5886, 0.6028, ..., -1.0667, -1.0667, -1.0808],
[ 0.5886, 0.5886, 0.5745, ..., -1.0808, -1.0950, -1.0950],
...,
[-1.0667, -1.0384, -1.0384, ..., -1.4345, -1.4345, -1.4345],
[-1.0808, -1.0667, -1.0808, ..., -1.4204, -1.4345, -1.4345],
[-1.0242, -1.0101, -1.0384, ..., -1.4487, -1.4487, -1.4487]],
[[ 0.0499, 0.0938, 0.1231, ..., -1.1950, -1.1804, -1.1658],
[ 0.0645, 0.0792, 0.0938, ..., -1.1658, -1.1658, -1.1511],
[ 0.0792, 0.0792, 0.0645, ..., -1.1950, -1.1950, -1.1950],
...,
[-1.1218, -1.1072, -1.1072, ..., -1.4294, -1.4294, -1.4294],
[-1.1072, -1.1365, -1.1511, ..., -1.4147, -1.4294, -1.4294],
[-1.0486, -1.0779, -1.1072, ..., -1.4440, -1.4440, -1.4440]],
[[-1.0275, -0.9999, -0.9724, ..., -1.0689, -1.0689, -1.0826],
[-1.0275, -1.0137, -0.9999, ..., -1.0137, -1.0413, -1.0689],
[-1.0137, -1.0275, -1.0413, ..., -1.0275, -1.0551, -1.0689],
...,
[-0.9999, -0.9724, -0.9861, ..., -1.2205, -1.2205, -1.2205],
[-1.0137, -1.0275, -1.0413, ..., -1.2067, -1.2205, -1.2205],
[-0.9586, -0.9724, -0.9999, ..., -1.2343, -1.2343, -1.2343]]],
[[[ 0.5745, 0.0085, -0.1188, ..., 0.3905, 0.7442, 0.6452],
[ 0.5745, 0.2208, -0.0763, ..., 0.3764, 0.7159, 0.6028],
[ 0.6028, 0.4188, -0.0622, ..., 0.3764, 0.6876, 0.5603],
...,
[ 1.0838, 1.4799, 1.5082, ..., -0.4442, -0.5715, -0.5715],
[ 0.8008, 1.1262, 1.5365, ..., -0.5998, -0.4017, -0.5149],
[ 0.8433, 0.8150, 1.2677, ..., -0.9818, -0.4725, -0.4300]],
[[ 0.1964, -0.3895, -0.4774, ..., -0.0673, 0.1671, 0.0499],
[ 0.1964, -0.1698, -0.4334, ..., -0.0819, 0.1378, 0.0060],
[ 0.1964, 0.0206, -0.4481, ..., -0.0673, 0.1231, -0.0233],
...,
[ 0.4746, 0.8994, 1.0019, ..., -0.7557, -0.8435, -0.8289],
[ 0.1231, 0.4746, 0.9726, ..., -0.8289, -0.6678, -0.7850],
[ 0.1085, 0.1231, 0.6504, ..., -1.0925, -0.6824, -0.6531]],
[[-0.3107, -0.7656, -0.7380, ..., -0.5726, -0.3796, -0.5175],
[-0.2969, -0.5726, -0.7105, ..., -0.5864, -0.4210, -0.5588],
[-0.3107, -0.4210, -0.7518, ..., -0.5313, -0.4486, -0.5864],
...,
[-0.2142, 0.1855, 0.2958, ..., -0.9310, -0.9861, -0.9724],
[-0.4899, -0.1591, 0.3234, ..., -0.9172, -0.8207, -0.9310],
[-0.4348, -0.4348, 0.0615, ..., -1.1102, -0.7794, -0.7794]]]]), tensor([ 6, 43, 47, 63, 37, 28, 25, 60, 30, 40, 47, 44, 29,
53, 17, 62, 31, 52,
40, 33, 29, 29, 48, 61, 10, 8, 21, 10, 24, 35, 2, 22, 0, 47, 22, 2,
38, 8, 57, 39, 7, 38, 61, 22, 60, 1, 1, 33, 33, 51, 20, 61, 46, 24,
50, 52, 37, 29, 37, 25, 27, 62, 13, 32, 48, 40, 7, 37, 48, 33, 61, 5,
3, 19, 28, 21, 56, 32, 27, 40, 9, 38, 7, 33, 7, 48, 48, 33, 59, 18,
59, 37, 39, 56, 26, 7, 10, 48, 46, 30, 63, 28, 49, 54, 10, 38, 35, 47,
14, 2, 52, 59, 8, 21, 49, 40, 34, 18, 20, 58, 18, 27, 4, 63, 57, 36,
24, 63])],)
from libfewshot.
wZuck
commented on August 30, 2024
你好，我按照下面的步骤尝试训练renet，但没有报错，或许可以供你参考：
git clone https://github.com/RL-VIG/LibFewShot.git LibFewShot_ee25973
cd LibFewShot_ee25973
# 修改renet.config 和 run_trainer.pyfrom libfewshot.
Aquariuaa
commented on August 30, 2024
十分感谢，未找到renet.config，请问是config/classifiers/RENet.yaml吗？
from libfewshot.
wZuck
commented on August 30, 2024
是config/renet.yaml，刚刚写错了，抱歉。
from libfewshot.
Aquariuaa
commented on August 30, 2024
非常感谢，经过多次尝试，使用Conv64F可以正常使用，但是使用resnet18无法跑通。感谢帮助
from libfewshot.
wZuck
commented on August 30, 2024
换Backbone的话需要对应修改分类头参数，分类头参数可以推导或者参考原文，可以附上更详细的报错信息供我们提供解决方案。
from libfewshot.
Related Issues (20)
- ImportError: cannot import name 'Iterable' from 'collections' HOT 1
- RuntimeError: shape '[-1, 3, 16]' is invalid for input of size 30 HOT 2
- train，val和test类别问题 HOT 7
- How to use this code into open-set recognition? HOT 1
- 使用自己数据集的时候会卡在加载训练数据集这一步 HOT 1
- https://github.com/RL-VIG/LibFewShot.git
- The computer does not have cuda, and it will report an error when running. HOT 1
- 5way-5shot报错 HOT 9
- 报错：/LibFewShot/core/data/samplers.py", line 111, in __iter__ batch = torch.stack(batch).reshape(-1) RuntimeError: stack expects each tensor to be equal size, but got [16] at entry 0 and [7] at entry 2 HOT 14
- 不管怎么搭配，程序都报错啊 HOT 1
- 请问怎么可以对一张图片进行分类？ HOT 2
- 使用miniImageNet--ravi数据集，然后ACC值为什么这么低？ HOT 5
- RENet HOT 1
- renet.yaml的backbone为ViT时的报错解决 HOT 1
- 训练日志与run_test的test数据差距过大 HOT 2
- 关于deepbdc方法的咨询 HOT 2
- use_logger() got an unexpected keyword argument 'file' HOT 1
- 使用时报错too many values to unpack
- 在复现文件夹`reproduce/`中缺失部分 method 的 config，详情见图 HOT 5
- 论文复现成功后，提交pr会同意吗QAQ HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from libfewshot.