Skip to content

Instantly share code, notes, and snippets.

@gvanhorn38
Created March 10, 2017 16:18
Show Gist options
  • Save gvanhorn38/597f9202e4890ae37d08f0696397c5b1 to your computer and use it in GitHub Desktop.
Save gvanhorn38/597f9202e4890ae37d08f0696397c5b1 to your computer and use it in GitHub Desktop.
commands for the CUB-200 whole image experiment using tf_classification
export DATASET_DIR=/media/drive2/tensorflow_datasets/cub/with_200_val_split
export EXPERIMENT_DIR=/media/drive2/tensorflow_experiments/ebird/cub_image_experiment
export IMAGENET_PRETRAINED_MODEL=/media/drive3/tensorflow_models/inception_v3.ckpt
# Visualize the inputs to the network
CUDA_VISIBLE_DEVICES=1 python visualize_train_inputs.py \
--tfrecords $DATASET_DIR/train* \
--config $EXPERIMENT_DIR/config_train.yaml \
--text_labels
# Warm up training phase
CUDA_VISIBLE_DEVICES=0 python train.py \
--tfrecords $DATASET_DIR/train* \
--logdir $EXPERIMENT_DIR/logdir/finetune \
--config $EXPERIMENT_DIR/config_train.yaml \
--pretrained_model $IMAGENET_PRETRAINED_MODEL \
--trainable_scopes InceptionV3/Logits InceptionV3/AuxLogits \
--checkpoint_exclude_scopes InceptionV3/Logits InceptionV3/AuxLogits \
--learning_rate_decay_type fixed \
--lr 0.01
# Evaluate the finetuned model with the validation data
CUDA_VISIBLE_DEVICES=1 python test.py \
--tfrecords $DATASET_DIR/val* \
--save_dir $EXPERIMENT_DIR/logdir/finetune/val_summaries \
--checkpoint_path $EXPERIMENT_DIR/logdir/finetune \
--config $EXPERIMENT_DIR/config_test.yaml \
--batch_size 20 \
--batches 30 \
--eval_interval_secs 180
# Train all of the weigths, using the finetuned model as a starting point
CUDA_VISIBLE_DEVICES=0 python train.py \
--tfrecords $DATASET_DIR/train* \
--logdir $EXPERIMENT_DIR/logdir \
--config $EXPERIMENT_DIR/config_train.yaml \
--pretrained_model $EXPERIMENT_DIR/logdir/finetune
# Evaluate the model using the validation data
CUDA_VISIBLE_DEVICES=1 python test.py \
--tfrecords $DATASET_DIR/val* \
--save_dir $EXPERIMENT_DIR/logdir/val_summaries \
--checkpoint_path $EXPERIMENT_DIR/logdir \
--config $EXPERIMENT_DIR/config_test.yaml \
--batch_size 20 \
--batches 30 \
--eval_interval_secs 180
# Evaluate the model using the test data
CUDA_VISIBLE_DEVICES=1 python test.py \
--tfrecords $DATASET_DIR/test* \
--save_dir $EXPERIMENT_DIR/logdir/test_summaries \
--checkpoint_path $EXPERIMENT_DIR/logdir \
--config $EXPERIMENT_DIR/config_test.yaml \
--batch_size 1 \
--batches 5794
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment