***************
** Arguments **
***************
backbone: 
config_file: configs/trainers/CoOp/vit_b16_ep50_bs4.yaml
dataset_config_file: configs/datasets/ucf101.yaml
eval_only: True
head: 
load_epoch: None
model_dir: 
no_train: False
opts: ['DATASET.SUBSAMPLE_CLASSES', 'new2']
output_dir: output/new2/ZeroshotCLIP/vit_b16_ep50_bs4/ucf101/3
resume: 
root: /mnt/hdd/DATA
seed: 3
source_domains: None
target_domains: None
trainer: ZeroshotCLIP
transforms: None
************
** Config **
************
DATALOADER:
  K_TRANSFORMS: 1
  NUM_WORKERS: 8
  RETURN_IMG0: False
  TEST:
    BATCH_SIZE: 100
    SAMPLER: SequentialSampler
  TRAIN_U:
    BATCH_SIZE: 32
    N_DOMAIN: 0
    N_INS: 16
    SAME_AS_X: True
    SAMPLER: RandomSampler
  TRAIN_X:
    BATCH_SIZE: 4
    N_DOMAIN: 0
    N_INS: 16
    SAMPLER: RandomSampler
DATASET:
  ALL_AS_UNLABELED: False
  CIFAR_C_LEVEL: 1
  CIFAR_C_TYPE: 
  NAME: UCF101
  NUM_LABELED: -1
  NUM_SHOTS: -1
  ROOT: /mnt/hdd/DATA
  SOURCE_DOMAINS: ()
  STL10_FOLD: -1
  SUBSAMPLE_CLASSES: new2
  TARGET_DOMAINS: ()
  VAL_PERCENT: 0.1
INPUT:
  COLORJITTER_B: 0.4
  COLORJITTER_C: 0.4
  COLORJITTER_H: 0.1
  COLORJITTER_S: 0.4
  CROP_PADDING: 4
  CUTOUT_LEN: 16
  CUTOUT_N: 1
  GB_K: 21
  GB_P: 0.5
  GN_MEAN: 0.0
  GN_STD: 0.15
  INTERPOLATION: bicubic
  NO_TRANSFORM: False
  PIXEL_MEAN: [0.48145466, 0.4578275, 0.40821073]
  PIXEL_STD: [0.26862954, 0.26130258, 0.27577711]
  RANDAUGMENT_M: 10
  RANDAUGMENT_N: 2
  RGS_P: 0.2
  RRCROP_SCALE: (0.08, 1.0)
  SIZE: (224, 224)
  TRANSFORMS: ('random_resized_crop', 'random_flip', 'normalize')
MODEL:
  BACKBONE:
    NAME: ViT-B/16
    PRETRAINED: True
  HEAD:
    ACTIVATION: relu
    BN: True
    DROPOUT: 0.0
    HIDDEN_LAYERS: ()
    NAME: 
  INIT_WEIGHTS: 
OPTIM:
  ADAM_BETA1: 0.9
  ADAM_BETA2: 0.999
  BASE_LR_MULT: 0.1
  GAMMA: 0.1
  LR: 0.002
  LR_SCHEDULER: cosine
  MAX_EPOCH: 50
  MOMENTUM: 0.9
  NAME: sgd
  NEW_LAYERS: ()
  RMSPROP_ALPHA: 0.99
  SGD_DAMPNING: 0
  SGD_NESTEROV: False
  STAGED_LR: False
  STEPSIZE: (-1,)
  WARMUP_CONS_LR: 1e-05
  WARMUP_EPOCH: 1
  WARMUP_MIN_LR: 1e-05
  WARMUP_RECOUNT: True
  WARMUP_TYPE: constant
  WEIGHT_DECAY: 0.0005
OUTPUT_DIR: output/new2/ZeroshotCLIP/vit_b16_ep50_bs4/ucf101/3
RESUME: 
SEED: 3
TEST:
  COMPUTE_CMAT: False
  EVALUATOR: Classification
  FINAL_MODEL: last_step
  NO_TEST: False
  PER_CLASS_RESULT: False
  SPLIT: test
TRAIN:
  CHECKPOINT_FREQ: 0
  COUNT_ITER: train_x
  PRINT_FREQ: 20
TRAINER:
  CDAC:
    CLASS_LR_MULTI: 10
    P_THRESH: 0.95
    RAMPUP_COEF: 30
    RAMPUP_ITRS: 1000
    STRONG_TRANSFORMS: ()
    TOPK_MATCH: 5
  COCOOP:
    CTX_INIT: 
    N_CTX: 16
    PREC: fp16
  COOP:
    CLASS_TOKEN_POSITION: end
    CSC: False
    CTX_INIT: 
    N_CTX: 16
    PREC: fp16
  CROSSGRAD:
    ALPHA_D: 0.5
    ALPHA_F: 0.5
    EPS_D: 1.0
    EPS_F: 1.0
  DAEL:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 0.5
  DAELDG:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 0.5
  DDAIG:
    ALPHA: 0.5
    CLAMP: False
    CLAMP_MAX: 1.0
    CLAMP_MIN: -1.0
    G_ARCH: 
    LMDA: 0.3
    WARMUP: 0
  DOMAINMIX:
    ALPHA: 1.0
    BETA: 1.0
    TYPE: crossdomain
  ENTMIN:
    LMDA: 0.001
  FIXMATCH:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 1.0
  IVLP:
    CTX_INIT: a photo of a
    N_CTX_TEXT: 2
    N_CTX_VISION: 2
    PREC: fp16
    PROMPT_DEPTH_TEXT: 9
    PROMPT_DEPTH_VISION: 9
  M3SDA:
    LMDA: 0.5
    N_STEP_F: 4
  MAPLE:
    CTX_INIT: a photo of a
    N_CTX: 4
    PREC: fp16
    PROMPT_DEPTH: 9
  MCD:
    N_STEP_F: 4
  MEANTEACHER:
    EMA_ALPHA: 0.999
    RAMPUP: 5
    WEIGHT_U: 1.0
  MIXMATCH:
    MIXUP_BETA: 0.75
    RAMPUP: 20000
    TEMP: 2.0
    WEIGHT_U: 100.0
  MME:
    LMDA: 0.1
  NAME: ZeroshotCLIP
  ProDA:
    N_CTX: 16
    N_PROMPT: 32
    PREC: fp16
  SE:
    CONF_THRE: 0.95
    EMA_ALPHA: 0.999
    RAMPUP: 300
  VPT:
    CTX_INIT: a photo of a
    N_CTX_VISION: 2
    PREC: fp16
    PROMPT_DEPTH_VISION: 1
USE_CUDA: True
VERBOSE: True
VERSION: 1
Collecting env info ...
** System info **
PyTorch version: 2.2.1+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

OS: Debian GNU/Linux 12 (bookworm) (x86_64)
GCC version: (Debian 12.2.0-14) 12.2.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.36

Python version: 3.11.2 (main, Mar 13 2023, 12:18:29) [GCC 12.2.0] (64-bit runtime)
Python platform: Linux-6.5.13-3-pve-x86_64-with-glibc2.36
Is CUDA available: True
CUDA runtime version: 11.8.89
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: 
GPU 0: NVIDIA A800 80GB PCIe
GPU 1: NVIDIA A800 80GB PCIe

Nvidia driver version: 525.147.05
cuDNN version: Could not collect
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):                             64
On-line CPU(s) list:                18,20,22,23,25-27,29,31,32,34,37,46-49
Off-line CPU(s) list:               0-17,19,21,24,28,30,33,35,36,38-45,50-63
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz
CPU family:                         6
Model:                              106
Thread(s) per core:                 2
Core(s) per socket:                 16
Socket(s):                          2
Stepping:                           6
CPU(s) scaling MHz:                 97%
CPU max MHz:                        3500.0000
CPU min MHz:                        800.0000
BogoMIPS:                           5800.00
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 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 invpcid_single intel_ppin 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 wbnoinvd dtherm ida arat pln pts vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
Virtualization:                     VT-x
L1d cache:                          1.5 MiB (32 instances)
L1i cache:                          1 MiB (32 instances)
L2 cache:                           40 MiB (32 instances)
L3 cache:                           48 MiB (2 instances)
NUMA node(s):                       2
NUMA node0 CPU(s):                  0-15,32-47
NUMA node1 CPU(s):                  16-31,48-63
Vulnerability Gather data sampling: Vulnerable: No microcode
Vulnerability Itlb multihit:        Not affected
Vulnerability L1tf:                 Not affected
Vulnerability Mds:                  Not affected
Vulnerability Meltdown:             Not affected
Vulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable
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
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Not affected

Versions of relevant libraries:
[pip3] flake8==3.7.9
[pip3] flake8==3.7.9
[pip3] numpy==1.26.4
[pip3] torch==2.2.1
[pip3] torchaudio==2.2.1
[pip3] torchvision==0.17.1
[pip3] triton==2.2.0
[conda] Could not collect
        Pillow (10.2.0)

Loading trainer: ZeroshotCLIP
Loading dataset: UCF101
Reading split from /mnt/hdd/DATA/ucf101/split_zhou_UCF101.json
Loading preprocessed few-shot data from /mnt/hdd/DATA/ucf101/split_fewshot/shot_-1_shuffled-seed_3.pkl
SUBSAMPLE NEW2 CLASSES!
Building transform_train
+ random resized crop (size=(224, 224), scale=(0.08, 1.0))
+ random flip
+ to torch tensor of range [0, 1]
+ normalization (mean=[0.48145466, 0.4578275, 0.40821073], std=[0.26862954, 0.26130258, 0.27577711])
Building transform_test
+ resize the smaller edge to 224
+ 224x224 center crop
+ to torch tensor of range [0, 1]
+ normalization (mean=[0.48145466, 0.4578275, 0.40821073], std=[0.26862954, 0.26130258, 0.27577711])
---------  ------
Dataset    UCF101
# classes  72
# train_x  5,444
# val      1,351
# test     2,695
---------  ------
Loading CLIP (backbone: ViT-B/16)
Prompts: ['a photo of a person doing Hammer Throw.', 'a photo of a person doing Hula Hoop.', 'a photo of a person doing Playing Guitar.', 'a photo of a person doing Balance Beam.', 'a photo of a person doing Tai Chi.', 'a photo of a person doing Blow Dry Hair.', 'a photo of a person doing Apply Eye Makeup.', 'a photo of a person doing Playing Piano.', 'a photo of a person doing Playing Tabla.', 'a photo of a person doing Billiards.', 'a photo of a person doing Skijet.', 'a photo of a person doing Volleyball Spiking.', 'a photo of a person doing Basketball.', 'a photo of a person doing Javelin Throw.', 'a photo of a person doing Playing Flute.', 'a photo of a person doing Bowling.', 'a photo of a person doing Playing Sitar.', 'a photo of a person doing Diving.', 'a photo of a person doing Bench Press.', 'a photo of a person doing Mixing.', 'a photo of a person doing Sky Diving.', 'a photo of a person doing Pizza Tossing.', 'a photo of a person doing Nunchucks.', 'a photo of a person doing Military Parade.', 'a photo of a person doing Horse Riding.', 'a photo of a person doing Pommel Horse.', 'a photo of a person doing Kayaking.', 'a photo of a person doing Breast Stroke.', 'a photo of a person doing Playing Daf.', 'a photo of a person doing Surfing.', 'a photo of a person doing Yo Yo.', 'a photo of a person doing Push Ups.', 'a photo of a person doing Biking.', 'a photo of a person doing Boxing Speed Bag.', 'a photo of a person doing Rock Climbing Indoor.', 'a photo of a person doing Cliff Diving.', 'a photo of a person doing Body Weight Squats.', 'a photo of a person doing High Jump.', 'a photo of a person doing Juggling Balls.', 'a photo of a person doing Handstand Walking.', 'a photo of a person doing Pole Vault.', 'a photo of a person doing Cricket Bowling.', 'a photo of a person doing Writing On Board.', 'a photo of a person doing Soccer Penalty.', 'a photo of a person doing Golf Swing.', 'a photo of a person doing Drumming.', 'a photo of a person doing Salsa Spin.', 'a photo of a person doing Horse Race.', 'a photo of a person doing Fencing.', 'a photo of a person doing Ice Dancing.', 'a photo of a person doing Walking With Dog.', 'a photo of a person doing Blowing Candles.', 'a photo of a person doing Front Crawl.', 'a photo of a person doing Playing Cello.', 'a photo of a person doing Archery.', 'a photo of a person doing Baseball Pitch.', 'a photo of a person doing Cricket Shot.', 'a photo of a person doing Parallel Bars.', 'a photo of a person doing Rafting.', 'a photo of a person doing Field Hockey Penalty.', 'a photo of a person doing Handstand Pushups.', 'a photo of a person doing Lunges.', 'a photo of a person doing Jumping Jack.', 'a photo of a person doing Skate Boarding.', 'a photo of a person doing Mopping Floor.', 'a photo of a person doing Throw Discus.', 'a photo of a person doing Trampoline Jumping.', 'a photo of a person doing Hammering.', 'a photo of a person doing Baby Crawling.', 'a photo of a person doing Head Massage.', 'a photo of a person doing Band Marching.', 'a photo of a person doing Clean And Jerk.']
Loading evaluator: Classification
Note that load_model() is skipped as no pretrained model is given (ignore this if it's done on purpose)
Evaluate on the *test* set
=> result
* total: 2,695
* correct: 1,972
* accuracy: 73.17%
* error: 26.83%
* macro_f1: 71.54%
