git clone https://github.com/tensorflow/tpu.git
sudo apt-get install -y python-tk
pip install tensorflow-gpu==1.15
pip install --user Cython matplotlib opencv-python-headless pyyaml Pillow
pip install 'git+https://github.com/cocodataset/cocoapi#egg=pycocotools&subdirectory=PythonAPI'
Download any model https://github.com/tensorflow/tpu/blob/master/models/official/detection/MODEL_ZOO.md
Perform inference
1:person
2:bicycle
3:car
category_id: In the form of category If you want to change the class, create a csv file according to the above format
python ~/tpu/models/official/detection/inference.py \
--model="retinanet" \
--image_size=640\
--checkpoint_path="./detection_retinanet_50/model. ckpt" \
--label_map_file="./retinanet/tpu/models/official/ detection/datasets/coco_label_map.csv" \
--image_file_pattern="path/to/input/file" \
--output_html="path/to/output/file" \
--max_boxes_to_draw=10 \
--min_score_threshold=0.05
#!/bin/bash
TRAIN_IMAGE_DIR="path/to/train/images/dir"
TRAIN_OBJ_ANNOTATIONS_FILE="path/to/train/file"
OUTPUT_DIR="path/to/output/dir"
VAL_IMAGE_DIR="path/to/test/images/dir"
VAL_OBJ_ANNOTATIONS_FILE="path/to/test/images/dir"
function create_train_dataset(){
python3 create_coco_tf_record.py \
--logtostderr \
--include_masks \
--image_dir="${TRAIN_IMAGE_DIR}" \
--object_annotations_file="$ {TRAIN_OBJ_ANNOTATIONS_FILE}" \
--output_file_prefix="${OUTPUT_DIR}/train" \
--num_shards=256
}
function create_val_dataset() {
SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
PYTHONPATH="tf-models:tf-models/research"
python3 $SCRIPT_DIR/create_coco_tf_record.py \
--logtostderr \
--include_masks \
--image_dir="${VAL_IMAGE_DIR}" \
--object_annotations_file="$ {VAL_OBJ_ANNOTATIONS_FILE}" \
--output_file_prefix="${OUTPUT_DIR}/val" \
--num_shards=32
}
create_train_dataset
create_val_dataset
3. Perform learning
MODEL_DIR="<path to the directory to store model files>"
TRAIN_FILE_PATTERN="<path to the TFRecord training data>"
EVAL_FILE_PATTERN="<path to the TFRecord validation data>"
VAL_JSON_FILE="<path to the validation annotation JSON file>"
RESNET_CHECKPOINT="<path to trained model>"
python ~/tpu/models/official/detection/main.py \
--model="retinanet" \
--model_dir="${MODEL_DIR?}" \
--mode=train \
--eval_after_training=True \
--use_tpu=False \
--params_override="{train: { checkpoint: { path: ${RESNET_CHECKPOINT?}, prefix: resnet50/ }, train_file_pattern: ${TRAIN_FILE_PATTERN?} }, eval: { val_json_file: ${VAL_JSON_FILE?}, eval_file_pattern: ${EVAL_FILE_PATTERN?} }}"
INFO:tensorflow:examples/sec: 0.622754
INFO:tensorflow:global_step/sec: 0.078258
python ~/tpu/models/official/detection/inference.py \
--model="retinanet" \
--image_size=640\
--checkpoint_path="path/to/input" \
--label_map_file="path/to/label" \
--image_file_pattern="path/to/input/file" \
--output_html="path/to/output/file" \
--max_boxes_to_draw=10 \
--min_score_threshold=0.05
--Model before learning with original data (Inference results will be uploaded) --Model after learning (Inference results will be uploaded)
python ${RETINA_ROOT}/evaluate_model.py\
--model="retinanet"\
--checkpoint_path="path/to/imput/file"\
--config_file="${CONFIG_PATH}"\
--params_override="${PARAMS_PATH}"\
--dump_predictions_only = True\
--predictions_path="path/to/output/file"
Since it's a big deal, I compared it with other models built in the past. All were batch size 8 and were trained and evaluated using the original dataset.
Compare the average time spent on 100 iterations.
time | |
---|---|
retinanet | About 21[min] |
ttfnet | About 228[min] |
Compare the accuracy from the AP and inference results at 2000 iterations.
mAP | |
---|---|
retinanet | 96.35 |
ttfnet | 79.78 |
Recommended Posts