> For the complete documentation index, see [llms.txt](https://bhabs.gitbook.io/allsetup/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://bhabs.gitbook.io/allsetup/ssd-work.md).

# SSD work

Replicating: SSD from <https://github.com/balancap/SSD-Tensorflow>

According to the page, in order to run the minimal SSD example, we found that there is a fundamental file missing

This fundamental problem is in the **notebooks/** directory

```
__init__.py
```

is missing. This caused error when the iPython notebook: ssd\_notebook.ipynb is executed. Without this init file in the respective

directory, the "from notebooks import visualization" won't work. It will say "module not found"

Solution: I copied this init file from nets/ directory to the notebooks/ directory

## Dataset:

1. Created a directory called VOC2007\_DOWNLOADED/ and then make 2 sub-directories 'train\_val' and 'test'
2. Invoke the following
3. ```
   cd VOC2007_DOWNLOADED/train_val
   wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar

   cd VOC2007_DOWNLOADED/test
   wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar

   # not needed
   wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCdevkit_08-Jun-2007.tar (mainly .m files)
   ```
4. Then untar all these files.
5. ~~Go to main dir: /tf\_files/SSD-Tensorflow and then make another directory called VOC2007. Copy over the JPEGImages and Annotations files to VOC2007/~~:
6. ```
   // NOT NEEDED ANY MORE
   /// cp -a VOC2007_DOWNLOADED/VOCdevkit/VOC2007/JPEGImages VOC2007/
   /// cp -a VOC2007_DOWNLOADED/VOCdevkit/VOC2007/Annotations VOC2007/

   THIS IS NOT NEEDED ANY MORE. The train_val and test are extracted separately and DATASET_DIR is
   modified to point to the correct location. This took care of the copying of data problem
   ```
7. Next run the conversion script to convert the images and Annotations to tf\_record format. Keep the train and test in separate directories '/tmp/train\_val\_TFRECORDS', and '/tmp/test\_TFRECORDS'

```python
 mkdir /tmp/train_val_TFRECORDS
 DATASET_DIR=./VOC2007_DOWNLOADED/train_val/VOCdevkit/VOC2007/
 OUTPUT_DIR=/tmp/train_val_TFRECORDS/
 python tf_convert_data.py \
    --dataset_name=pascalvoc \
    --dataset_dir=${DATASET_DIR} \
    --output_name=voc_2007_train \
    --output_dir=${OUTPUT_DIR}

 mkdir /tmp/test_TFRECORDS
 DATASET_DIR=./VOC2007_DOWNLOADED/test/VOCdevkit/VOC2007/
 OUTPUT_DIR=/tmp/test_TFRECORDS/
 python tf_convert_data.py \
    --dataset_name=pascalvoc \
    --dataset_dir=${DATASET_DIR} \
    --output_name=voc_2007_test \
    --output_dir=${OUTPUT_DIR}
```

Run evaluation

```python
 DATASET_DIR=/tmp/test_TFRECORDS/
 python eval_ssd_network.py     --eval_dir=${EVAL_DIR}     --dataset_dir=${DATASET_DIR}     --dataset_name=pascalvoc_2007
--dataset_split_name=test     --model_name=ssd_300_vgg     --checkpoint_path=${CHECKPOINT_PATH}     --batch_size=1
```

Training (fine tuning)

```python
 DATASET_DIR=/tmp/train_val_TFRECORDS
 TRAIN_DIR=/tmp/SSD_LOGS/
 CHECKPOINT_PATH=./checkpoints/ssd_300_vgg.ckpt
 python train_ssd_network.py \
    --train_dir=${TRAIN_DIR} \
    --dataset_dir=${DATASET_DIR} \
    --dataset_name=pascalvoc_2007 \
    --dataset_split_name=train \
    --model_name=ssd_300_vgg \
    --checkpoint_path=${CHECKPOINT_PATH} \
    --save_summaries_secs=60 \
    --save_interval_secs=600 \
    --weight_decay=0.0005 \
    --optimizer=adam \
    --learning_rate=0.001 \
    --batch_size=32

 # Note: for cpu, change DATA_FORMAT to NHWC instead of NCHW in train_ssd_network.py
 #       Also, for medium ec2 instance with mem of 4GB, reduce batch_size to 1
```