Add no-box full-frame Qwen AV baselines

2026-09-17 02:51:26 +08:00
parent a9f748d6a6
commit 62134a0fa0
10 changed files with 1164 additions and 17 deletions
@@ -0,0 +1,65 @@
+#!/usr/bin/env bash
+# Foreground only. Usage: bash run_easycom_fullframe_qwen_av.sh [all|f2|f3] [seed ...]
+set -euo pipefail
+cd "$(dirname "$0")"
+
+FEATURE_ROOT=${FEATURE_ROOT:-/data1/yfzx/wangx/Datasets/easycom/omni_features/open_stream_2fps_8s_last4_stack}
+TARGET_ROOT=${TARGET_ROOT:-/data1/yfzx/wangx/Datasets/easycom/easycom_target_frame}
+FULLFRAME_ROOT=${FULLFRAME_ROOT:-/data1/yfzx/wangx/Datasets/easycom/omni_features/fullframe_qwen_av_2fps_224}
+CHECKPOINT_ROOT=${CHECKPOINT_ROOT:-checkpoints/easycom_fullframe_qwen_av}
+RESULT_ROOT=${RESULT_ROOT:-results/easycom_fullframe_qwen_av}
+LOCAL_PROJECTION_DIM=${LOCAL_PROJECTION_DIM:-256}
+ATTENTION_DIM=${ATTENTION_DIM:-256}
+ATTENTION_HEADS=${ATTENTION_HEADS:-4}
+HISTORY_FRAMES=${HISTORY_FRAMES:-2}
+HISTORY_MAX_GAP_SECONDS=${HISTORY_MAX_GAP_SECONDS:-0.75}
+TRAIN_BATCH_SIZE=${TRAIN_BATCH_SIZE:-64}
+INFER_BATCH_SIZE=${INFER_BATCH_SIZE:-128}
+export OMP_NUM_THREADS=${OMP_NUM_THREADS:-4}
+export MKL_NUM_THREADS=${MKL_NUM_THREADS:-4}
+export OPENBLAS_NUM_THREADS=${OPENBLAS_NUM_THREADS:-4}
+
+variant=${1:-all}
+if (( $# )); then shift; fi
+if (( $# )); then seeds=("$@"); else seeds=(0 1 2); fi
+case "$variant" in
+  all) variants=(f2 f3) ;;
+  f2|f3) variants=("$variant") ;;
+  *) echo "Expected all, f2, or f3" >&2; exit 2 ;;
+esac
+
+for variant in "${variants[@]}"; do
+  case "$variant" in
+    f2) fusion=fullframe-spatial-attention ;;
+    f3) fusion=fullframe-spatiotemporal-attention ;;
+  esac
+  for seed in "${seeds[@]}"; do
+    checkpoint="$CHECKPOINT_ROOT/${variant}_seed${seed}.pth"
+    result="$RESULT_ROOT/${variant}_seed${seed}"
+    if [[ -e "$checkpoint" || -e "$result" ]]; then
+      echo "Refusing to overwrite $checkpoint or $result; select new output roots." >&2
+      exit 1
+    fi
+    python train_turn_head.py \
+      --feature-root "$FEATURE_ROOT" --target-root "$TARGET_ROOT" \
+      --local-feature-root "$FULLFRAME_ROOT" --local-modalities av \
+      --local-fusion "$fusion" \
+      --local-projection-dim "$LOCAL_PROJECTION_DIM" \
+      --person-attention-dim "$ATTENTION_DIM" \
+      --person-attention-heads "$ATTENTION_HEADS" \
+      --person-history-frames "$HISTORY_FRAMES" \
+      --person-track-max-gap-seconds "$HISTORY_MAX_GAP_SECONDS" \
+      --output "$checkpoint" --sessions 4 5 6 7 8 9 10 11 12 \
+      --epochs 4 --batch-size "$TRAIN_BATCH_SIZE" \
+      --learning-rate 7e-5 --weight-decay 5e-5 \
+      --warmup-epochs 1.6 --warmup-factor 0.3 --dropout 0.2 \
+      --loss lstr-mce --transition-objective none --layer-fusion concat-mlp \
+      --expected-mode open-stream-replay --seed "$seed" --device cuda:0
+    python infer_turn_head.py \
+      --feature-root "$FEATURE_ROOT" --target-root "$TARGET_ROOT" \
+      --local-feature-root "$FULLFRAME_ROOT" \
+      --checkpoint "$checkpoint" --output-dir "$result" --sessions 3 2 1 \
+      --batch-size "$INFER_BATCH_SIZE" \
+      --expected-mode open-stream-replay --device cuda:0
+  done
+done