Update ParsingGait (#160)

* Update ParsingGait * Clear up the confusion Clear up the confusion about gait3d and gait3d-parsing. * Update 0.get_started.md * Add BaseParsingCuttingTransform * Update gcn.py * Create gaitbase_gait3d_parsing_btz32x2_fixed.yaml * Add gait3d_parsing config file * Update 1.model_zoo.md Update Gait3D-Parsing checkpoints * Update 1.model_zoo.md add configuration * Update 1.model_zoo.md center text --------- Co-authored-by: Junhao Liang <43094337+darkliang@users.noreply.github.com>
2023-10-29 21:53:02 +08:00
parent 44fb2414f2
commit 609aa0e9aa
17 changed files with 1422 additions and 3 deletions
@@ -0,0 +1,109 @@
+data_cfg:
+  dataset_name: Gait3D-Parsing
+  dataset_root: your_path
+  dataset_partition: ./datasets/Gait3D/Gait3D.json # Uses the same Gait3D.json as Gait3D dataset
+  # data_in_use: [true, false]
+  num_workers: 1
+  remove_no_gallery: false # Remove probe if no gallery for it
+  test_dataset_name: Gait3D-Parsing
+
+evaluator_cfg:
+  enable_float16: true
+  restore_ckpt_strict: true
+  restore_hint: 120000
+  save_name: ParsingGait
+  eval_func: evaluate_Gait3D
+  sampler:
+    batch_shuffle: false
+    batch_size: 4
+    sample_type: all_ordered # all indicates whole sequence used to test, while ordered means input sequence by its natural order; Other options:   fixed_unordered
+    frames_all_limit: 720 # limit the number of sampled frames to prevent out of memory
+  metric: euc # cos
+  transform:
+    - type: BaseParsingCuttingTransform
+
+loss_cfg:
+  - loss_term_weight: 1.0
+    margin: 0.2
+    type: TripletLoss
+    log_prefix: triplet
+  - loss_term_weight: 1.0
+    scale: 16
+    type: CrossEntropyLoss
+    log_prefix: softmax
+    log_accuracy: true
+
+model_cfg:
+  model: ParsingGait
+  backbone_cfg:
+    type: ResNet9
+    block: BasicBlock
+    channels: # Layers configuration for automatically model construction
+      - 64
+      - 128
+      - 256
+      - 512
+    layers: 
+      - 1
+      - 1
+      - 1
+      - 1
+    strides:
+      - 1
+      - 2
+      - 2
+      - 1
+    maxpool: false
+  SeparateFCs:
+    in_channels: 512
+    out_channels: 256
+    parts_num: 21
+  SeparateBNNecks:
+    class_num: 3000
+    in_channels: 256
+    parts_num: 21
+  bin_num:
+    - 16
+  gcn_cfg:
+    fine_parts: 11
+    coarse_parts: 5
+    only_fine_graph: false
+    only_coarse_graph: true
+    combine_fine_coarse_graph: false
+
+optimizer_cfg:
+  lr: 0.1
+  momentum: 0.9
+  solver: SGD
+  weight_decay: 0.0005
+
+scheduler_cfg:
+  gamma: 0.1
+  milestones: # Learning Rate Reduction at each milestones
+    - 40000
+    - 80000
+    - 100000
+  scheduler: MultiStepLR
+trainer_cfg:
+  enable_float16: true # half_percesion float for memory reduction and speedup
+  fix_BN: false
+  with_test: True
+  log_iter: 100
+  restore_ckpt_strict: true
+  restore_hint: 0
+  save_iter: 40000
+  save_name: ParsingGait
+  sync_BN: true
+  total_iter: 120000
+  sampler:
+    batch_shuffle: true
+    batch_size:
+      - 32 # TripletSampler, batch_size[0] indicates Number of Identity
+      - 2 #                 batch_size[1] indicates Samples sequqnce for each Identity
+    frames_num_fixed: 30 # fixed frames number for training
+    frames_num_max: 50 # max frames number for unfixed training
+    frames_num_min: 10 # min frames number for unfixed traing
+    sample_type: fixed_unordered # fixed control input frames number, unordered for controlling order of input tensor; Other options: unfixed_ordered or all_ordered
+    type: TripletSampler
+  transform:
+    - type: BaseParsingCuttingTransform