pytorch
MultilabelAccuracy belong criteria considers no class predictions as correct when ground truth expects one/more
🐛 Describe the bug
Hi. I might have found a bug with the "belong" criteria of the multilabel metrics. The docs say that the "belong" criteria requires all the predicted labels to fully belong to the target label set. However, when the predicted labels are all 0 (one-hot-encoded) or when no class is predicted, the metric calculation still considers the prediction for the sample as correct. I have tested this on both torcheval.metrics.functional.MultilabelAccuracy and torcheval.metrics.MultilabelAccuracy with the same outcome. I haven't tested with other multilabel metrics but the source code seems to have one multilabel update code so other metrics might be affected too.
Here's a sample snippet extending the example from the documentation:
import torch
from torcheval.metrics.functional import multilabel_accuracy
#Samples from https://docs.pytorch.org/torcheval/main/generated/torcheval.metrics.functional.multilabel_accuracy.html
input = torch.tensor([[0, 1], [1, 1], [0, 0], [0, 1]])
target = torch.tensor([[0, 1], [1, 0], [0, 0], [1, 1]])
#Add case if nothing is predicted but something is expected
input = torch.concat([input, torch.tensor([[0,0]])])
target = torch.concat([target, torch.tensor([[1,0]])])
print("Target\tInput\tScore")
for i, t in zip(input, target):
score = multilabel_accuracy(i.view(1,-1), t.view(1,-1), criteria="belong")
print("%s\t%s\t%.f" % (t.tolist(), i.tolist(), score))
This prints out:
Target Input Score
[0, 1] [0, 1] 1
[1, 0] [1, 1] 0
[0, 0] [0, 0] 1
[1, 1] [0, 1] 1
[1, 0] [0, 0] 1
I understand that empty sets are subsets of a set by definition but it seems counter intuitive in a performance metric since predicting no classes for an entire dataset will output 100% accuracy regardless of labels.
That said, in the examples in the documentation, the correct input samples are shown as input[0],input[1],input[3] which I think should be 0, 2, and 3.
Versions
PyTorch version: 2.7.1+cu126 Is debug build: False CUDA used to build PyTorch: 12.6 ROCM used to build PyTorch: N/A
OS: Red Hat Enterprise Linux 9.4 (Plow) (x86_64) GCC version: (GCC) 11.4.1 20231218 (Red Hat 11.4.1-3) Clang version: Could not collect CMake version: Could not collect Libc version: glibc-2.34
Python version: 3.11.11 (main, Dec 11 2024, 16:28:39) [GCC 11.2.0] (64-bit runtime) Python platform: Linux-5.14.0-427.42.1.el9_4.x86_64-x86_64-with-glibc2.34 Is CUDA available: False CUDA runtime version: No CUDA CUDA_MODULE_LOADING set to: N/A GPU models and configuration: No CUDA Nvidia driver version: No CUDA cuDNN version: No CUDA HIP runtime version: N/A MIOpen runtime version: N/A Is XNNPACK available: True
CPU: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 46 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 128 On-line CPU(s) list: 0-127 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) Gold 6448H CPU family: 6 Model: 143 Thread(s) per core: 1 Core(s) per socket: 32 Socket(s): 4 Stepping: 8 CPU(s) scaling MHz: 100% CPU max MHz: 4100.0000 CPU min MHz: 800.0000 BogoMIPS: 4800.00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hfi vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities Virtualization: VT-x L1d cache: 6 MiB (128 instances) L1i cache: 4 MiB (128 instances) L2 cache: 256 MiB (128 instances) L3 cache: 240 MiB (4 instances) NUMA node(s): 4 NUMA node0 CPU(s): 0,4,8,12,16,20,24,28,32,36,40,44,48,52,56,60,64,68,72,76,80,84,88,92,96,100,104,108,112,116,120,124 NUMA node1 CPU(s): 1,5,9,13,17,21,25,29,33,37,41,45,49,53,57,61,65,69,73,77,81,85,89,93,97,101,105,109,113,117,121,125 NUMA node2 CPU(s): 2,6,10,14,18,22,26,30,34,38,42,46,50,54,58,62,66,70,74,78,82,86,90,94,98,102,106,110,114,118,122,126 NUMA node3 CPU(s): 3,7,11,15,19,23,27,31,35,39,43,47,51,55,59,63,67,71,75,79,83,87,91,95,99,103,107,111,115,119,123,127 Vulnerability Gather data sampling: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Reg file data sampling: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected
Versions of relevant libraries: [pip3] mypy_extensions==1.1.0 [pip3] numpy==1.24.4 [pip3] nvidia-cublas-cu11==11.11.3.6 [pip3] nvidia-cublas-cu12==12.6.4.1 [pip3] nvidia-cuda-cupti-cu11==11.8.87 [pip3] nvidia-cuda-cupti-cu12==12.6.80 [pip3] nvidia-cuda-nvrtc-cu11==11.8.89 [pip3] nvidia-cuda-nvrtc-cu12==12.6.77 [pip3] nvidia-cuda-runtime-cu11==11.8.89 [pip3] nvidia-cuda-runtime-cu12==12.6.77 [pip3] nvidia-cudnn-cu11==8.9.6.50 [pip3] nvidia-cudnn-cu12==9.5.1.17 [pip3] nvidia-cufft-cu11==10.9.0.58 [pip3] nvidia-cufft-cu12==11.3.0.4 [pip3] nvidia-curand-cu11==10.3.0.86 [pip3] nvidia-curand-cu12==10.3.7.77 [pip3] nvidia-cusolver-cu11==11.4.1.48 [pip3] nvidia-cusolver-cu12==11.7.1.2 [pip3] nvidia-cusparse-cu11==11.7.5.86 [pip3] nvidia-cusparse-cu12==12.5.4.2 [pip3] nvidia-cusparselt-cu12==0.6.3 [pip3] nvidia-nccl-cu11==2.19.3 [pip3] nvidia-nccl-cu12==2.26.2 [pip3] nvidia-nvjitlink-cu12==12.6.85 [pip3] nvidia-nvtx-cu11==11.8.86 [pip3] nvidia-nvtx-cu12==12.6.77 [pip3] torch==2.7.1 [pip3] torcheval==0.0.7 [pip3] torchmetrics==1.7.2 [pip3] triton==3.3.1 [conda] numpy 1.24.4 pypi_0 pypi [conda] nvidia-cublas-cu11 11.11.3.6 pypi_0 pypi [conda] nvidia-cublas-cu12 12.6.4.1 pypi_0 pypi [conda] nvidia-cuda-cupti-cu11 11.8.87 pypi_0 pypi [conda] nvidia-cuda-cupti-cu12 12.6.80 pypi_0 pypi [conda] nvidia-cuda-nvrtc-cu11 11.8.89 pypi_0 pypi [conda] nvidia-cuda-nvrtc-cu12 12.6.77 pypi_0 pypi [conda] nvidia-cuda-runtime-cu11 11.8.89 pypi_0 pypi [conda] nvidia-cuda-runtime-cu12 12.6.77 pypi_0 pypi [conda] nvidia-cudnn-cu11 8.9.6.50 pypi_0 pypi [conda] nvidia-cudnn-cu12 9.5.1.17 pypi_0 pypi [conda] nvidia-cufft-cu11 10.9.0.58 pypi_0 pypi [conda] nvidia-cufft-cu12 11.3.0.4 pypi_0 pypi [conda] nvidia-curand-cu11 10.3.0.86 pypi_0 pypi [conda] nvidia-curand-cu12 10.3.7.77 pypi_0 pypi [conda] nvidia-cusolver-cu11 11.4.1.48 pypi_0 pypi [conda] nvidia-cusolver-cu12 11.7.1.2 pypi_0 pypi [conda] nvidia-cusparse-cu11 11.7.5.86 pypi_0 pypi [conda] nvidia-cusparse-cu12 12.5.4.2 pypi_0 pypi [conda] nvidia-cusparselt-cu12 0.6.3 pypi_0 pypi [conda] nvidia-nccl-cu11 2.19.3 pypi_0 pypi [conda] nvidia-nccl-cu12 2.26.2 pypi_0 pypi [conda] nvidia-nvjitlink-cu12 12.6.85 pypi_0 pypi [conda] nvidia-nvtx-cu11 11.8.86 pypi_0 pypi [conda] nvidia-nvtx-cu12 12.6.77 pypi_0 pypi [conda] torch 2.7.1 pypi_0 pypi [conda] torcheval 0.0.7 pypi_0 pypi [conda] torchmetrics 1.7.2 pypi_0 pypi [conda] triton 3.3.1 pypi_0 pypi
