updated

Author: yanghlll

eval_encoder/shells_eval_ap/eval_siglip2_large_patch16_256_1frames.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+# Get the directory where this script is located
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+source "${SCRIPT_DIR}/common.sh"
+
+# Model configuration
+MODEL_FAMILY="siglip2"
+MODEL_NAME="siglip2_large_patch16_256"
+FRAMES_TOKEN_NUM=256
+EMBEDDING_SIZE=1024
+INPUT_SIZE=256
+NUM_FRAMES=1
+REPORT_DIR_SUFFIX="_1frames"
+
+DATASETS=(
+    # "ssv2"
+    # "diving48"
+    "perception_test"
+    # "epic_verb"
+    # "epic_noun"
+    # "hmdb51"
+    # "k400"
+    # "charadesego"
+)
+
+# Run evaluation
+run_attentive_probe

pages/images/example.gif

@@ -12,6 +12,7 @@ docker run \
     --ulimit stack=67108864 \
     --rm \
     -v "$(pwd)":/workspace/OneVision-Encoder \
+    -v /data_3:/data_3 \
     -w /workspace/OneVision-Encoder \
     -e NCCL_TIMEOUT=1800 \
     -e CUDA_DEVICE_MAX_CONNECTIONS=1 \
@@ -27,4 +28,4 @@ docker run \
     -e NCCL_MIN_NCHANNELS=${NCCL_MIN_NCHANNELS:-8} \
     -e NCCL_MAX_NCHANNELS=${NCCL_MAX_NCHANNELS:-16} \
     llava_vit:25.11.22 \
-    bash -c "service ssh restart; bash"
+    bash -c "service ssh restart; bash"