Initialization of get_trellis dynamic programming #3166
Description
🐛 Describe the bug
trellis[1:, 0] = torch.cumsum(emission[:, 0], 0)
is based on blank_id=0. If the prediction does not start with 0, the aligner gets the starting frame wrong. For example, when blank_id=29([PAD]), and the model outputs pred_id=[29,29,29,1,29]. Then the trellis will be liketrellis[0]=[0, -inf, -inf, -inf, -inf, -inf] and trellis[1]=[emission[1,0], emission[1,1], -inf, -inf, -inf] where emission[1,1] might be greater than emission[1,0] because 0 is not the starting id. In this way, the aligner assumes label 1 starts at frame 0 when it actually starts at frame 3.
Changing the line to
trellis[1:, 0] = torch.cumsum(emission[:, blank_id], 0)
works for me.
Versions
Collecting environment information...
PyTorch version: 1.13.1+cu117
Is debug build: False
CUDA used to build PyTorch: 11.7
ROCM used to build PyTorch: N/A
OS: Arch Linux (x86_64)
GCC version: (GCC) 12.2.1 20230201
Clang version: 15.0.7
CMake version: version 3.25.2
Libc version: glibc-2.17
Python version: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] (64-bit runtime)
Python platform: Linux-5.15.94-1-lts-x86_64-with-arch
Is CUDA available: True
CUDA runtime version: 11.8.89
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA GeForce RTX 2080 Ti
GPU 1: NVIDIA GeForce RTX 2080 Ti
GPU 2: NVIDIA GeForce RTX 2080 Ti
GPU 3: NVIDIA GeForce RTX 2080 Ti
GPU 4: NVIDIA GeForce GTX 1080 Ti
GPU 5: NVIDIA GeForce GTX 1080 Ti
GPU 6: NVIDIA GeForce GTX 1080 Ti
GPU 7: NVIDIA GeForce GTX 1080 Ti
Nvidia driver version: 525.89.02
cuDNN version: Probably one of the following:
/usr/lib/libcudnn.so.8.6.0
/usr/lib/libcudnn_adv_infer.so.8.6.0
/usr/lib/libcudnn_adv_train.so.8.6.0
/usr/lib/libcudnn_cnn_infer.so.8.6.0
/usr/lib/libcudnn_cnn_train.so.8.6.0
/usr/lib/libcudnn_ops_infer.so.8.6.0
/usr/lib/libcudnn_ops_train.so.8.6.0
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, 48 bits virtual
Byte Order: Little Endian
CPU(s): 48
On-line CPU(s) list: 0-47
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Gold 5118 CPU @ 2.30GHz
CPU family: 6
Model: 85
Thread(s) per core: 2
Core(s) per socket: 12
Socket(s): 2
Stepping: 4
CPU(s) scaling MHz: 80%
CPU max MHz: 3200.0000
CPU min MHz: 1000.0000
BogoMIPS: 4600.00
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 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 cdp_l3 invpcid_single pti intel_ppin ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke flush_l1d
Virtualization: VT-x
L1d cache: 768 KiB (24 instances)
L1i cache: 768 KiB (24 instances)
L2 cache: 24 MiB (24 instances)
L3 cache: 33 MiB (2 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-11,24-35
NUMA node1 CPU(s): 12-23,36-47
Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled
Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable
Vulnerability Mds: Vulnerable: Clear CPU buffers attempted, no microcode; SMT vulnerable
Vulnerability Meltdown: Mitigation; PTI
Vulnerability Mmio stale data: Vulnerable: Clear CPU buffers attempted, no microcode; SMT vulnerable
Vulnerability Retbleed: Mitigation; IBRS
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Vulnerable: Clear CPU buffers attempted, no microcode; SMT vulnerable
Versions of relevant libraries:
[pip3] numpy==1.21.6
[pip3] torch==1.13.1
[pip3] torchaudio==0.13.1
[conda] numpy 1.21.6 pypi_0 pypi
[conda] torch 1.13.1 pypi_0 pypi
[conda] torchaudio 0.13.1 pypi_0 pypi