66 lines
2.8 KiB
Bash
Executable File
66 lines
2.8 KiB
Bash
Executable File
#!/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
|