Request for fine-tune details~ about i3d-tensorflow HOT 3 OPEN

# Script for training videos in TensorFlow

now=$(date +"%Y%m%d_%H%M%S")
python=/mnt/lustre/DATAshare/zhouyao/anaconda3/bin/python
export LD_LIBRARY_PATH=/mnt/lustre/share/cuda-8.0-cudnn6/lib64/:$LD_LIBRARY_PATH
export LD_LIBRARY_PATH=/mnt/lustre/share/mvapich2-2.2b-cuda8.0/lib/:$LD_LIBRARY_PATH
if [ ! -d "../log" ]; then
  mkdir "../log"
fi

num_gpus=4
machines=GTX1080

# Dataset setting
subset=train
data_dir=/mnt/lustre/DATAshare/ucf101_tfrecord/split1/train
data_set=UCF101Data_1

# Input setting
input_type=RGB
crop_fn=TSNCrop
num_segments=2
num_length=16
max_distort=1
more_crop=True
frame_size=224
data_format="NHWC"

# Model setting
# SenseTime_I3D model
net=i3d_v1
model=C3DModel

# Training setting
batch_size=8
optimizer=momentum
learning_rate=0.001
learning_rate_decay_factor=0.1
max_steps=25000
num_steps_per_decay=10000
weight_decay=0.0005
label_loss=CrossEntropyLoss #CrossEntropyLoss, FocalCELoss
dropout_keep=0.5

# Special training
pretrain_dir=/mnt/lustre/DATAshare/model-zoo/zhouyao/i3dkinetics50000
checkpoint_exclude_scopes=v/SenseTime_I3D/Logits
special_layer=Logits
layerwise_lr_ratio=10

# Logging
tf_summary_image=True 
jobname=I3D-UCF
train_dir=../log/${data_set}-${input_type}-$model-${net}-train_dir

srun -p ${machines} --job-name=${jobname} --gres=gpu:${num_gpus} \
${python} -u ../train_val.py --local_parameter_device=cpu --num_gpus=${num_gpus} \
    --data_set=${data_set} --subset=$subset --data_dir=${data_dir} --num_steps_per_decay=$num_steps_per_decay\
    --num_segments=${num_segments} --data_format=${data_format} --optimizer=${optimizer}\
    --pretrain_dir=${pretrain_dir} --checkpoint_exclude_scopes=${checkpoint_exclude_scopes}\
    --model=$model --variable_update=parameter_server --special_layer=${special_layer} \
    --base_model_name=${net} --weight_decay=${weight_decay} --layerwise_lr_ratio=${layerwise_lr_ratio} \
    --batch_size=${batch_size} --input_type=${input_type} --label_loss=$label_loss \
    --learning_rate=${learning_rate} --learning_rate_decay_factor=${learning_rate_decay_factor} \
    --num_length=${num_length} --max_distort=${max_distort} --more_crop=${more_crop} --max_steps=${max_steps} \
    --frame_size=${frame_size} --raw_video_short_side=${raw_video_short_side} --train_dir=${train_dir} \
    --num_preprocess_threads=16 --num_readers=10 --dropout_keep=${dropout_keep}\
    2>&1|tee ../log/tf-train-$data_set-${input_type}-$model-${net}.log &\

# Script for evaluating videos in TensorFlow

now=$(date +"%Y%m%d_%H%M%S")
python=/mnt/lustre/DATAshare/zhouyao/anaconda3/bin/python
export LD_LIBRARY_PATH=/mnt/lustre/share/cuda-8.0-cudnn6/lib64/:$LD_LIBRARY_PATH
export LD_LIBRARY_PATH=/mnt/lustre/share/mvapich2-2.2b-cuda8.0/lib/:$LD_LIBRARY_PATH
if [ ! -d "../log" ]; then
  mkdir "../log"
fi

num_gpus=4
machines=GTX1080

# Dataset setting
subset=validation
data_dir=/mnt/lustre/DATAshare/ucf101_tfrecord/split1/validation
data_set=UCF101Data_1

# Input setting
input_type=RGB
crop_fn=TSNCrop
num_length=32
max_distort=1
more_crop=True
frame_size=224
num_segments=3
data_format="NHWC"

# Model setting
net=i3d_v1
model=C3DModel

# Eval setting
batch_size=2
max_steps=25000

# Logging
tf_summary_image=True 
jobname=eval-${data_set}
train_dir=../log/${data_set}-${input_type}-$model-${net}-train_dir
eval_dir=../log/${data_set}-${input_type}-$model-${net}-eval_dir

# Slurm running
srun -p ${machines} --job-name=${jobname} --gres=gpu:${num_gpus} \
${python} -u ../train_val.py --local_parameter_device=cpu --num_gpus=${num_gpus} \
    --data_set=${data_set} --subset=$subset --data_dir=${data_dir} --top_k=5 \
    --num_segments=${num_segments} --data_format=${data_format} \
    --pretrain_dir=${pretrain_dir} --checkpoint_exclude_scopes=${checkpoint_exclude_scopes}\
    --model=$model --variable_update=parameter_server --eval=True \
    --base_model_name=${net} \
    --batch_size=${batch_size} --input_type=${input_type} --max_steps=${max_steps} \
    --num_length=${num_length} --max_distort=${max_distort} --more_crop=${more_crop} \
    --frame_size=${frame_size} --train_dir=${train_dir} --eval_dir=${eval_dir}\
    2>&1|tee ../log/tf-eval-$data_set-${input_type}-$model-${net}.log &\