Unstable loss SSD-300 due to which mAP is low

Question

I am training my SSD-300 model for which I have resized images to 300x300. I am using the default settings as mentioned in github repo:https://github.com/balancap/SSD-Tensorflow

The loss is unstable while training. I tried training it till 50,000 training steps. The current mAP that I am getting is 0.26(VOC 2007) and 0.24 (VOC 2012)

Train set: 1500 images Test: 300 images

Current parameters:

!python train_ssd_network.py --dataset_name=pascalvoc_2007 --dataset_split_name=train --model_name=ssd_300_vgg --save_summaries_secs=60 --save_interval_secs=600 --weight_decay=0.00004 --optimizer=adam --learning_rate=0.01 --batch_size=2 --gpu_memory_fraction=0.9 --learning_rate_decay_factor=0.94 -num_classes=3  --checkpoint_exclude_scopes =ssd_300_vgg/conv6,ssd_300_vgg/conv7,ssd_300_vgg/block8,ssd_300_vgg/block9,ssd_300_vgg/block10,ssd_300_vgg/block11,ssd_300_vgg/block4_box,ssd_300_vgg/block7_box,ssd_300_vgg/block8_box,ssd_300_vgg/block9_box,ssd_300_vgg/block10_box,ssd_300_vgg/block11_box --eval_training_data=True

What can I do so that I get a good accuracy (mAP)?

Example of loss, the loss even reached to 80:

W1024 13:57:41.660651 140239494461312 deprecation.py:323] From train_ssd_network.py:256: batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.batch(batch_size)` (or `padded_batch(...)` if `dynamic_pad=True`).
WARNING:tensorflow:From train_ssd_network.py:292: The name tf.get_collection is deprecated. Please use tf.compat.v1.get_collection instead.

W1024 13:57:41.676577 140239494461312 module_wrapper.py:139] From train_ssd_network.py:292: The name tf.get_collection is deprecated. Please use tf.compat.v1.get_collection instead.

WARNING:tensorflow:From train_ssd_network.py:292: The name tf.GraphKeys is deprecated. Please use tf.compat.v1.GraphKeys instead.

W1024 13:57:41.676797 140239494461312 module_wrapper.py:139] From train_ssd_network.py:292: The name tf.GraphKeys is deprecated. Please use tf.compat.v1.GraphKeys instead.

WARNING:tensorflow:From /content/gdrive/MyDrive/Training_SSD/SSD-1/deployment/model_deploy.py:194: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.

W1024 13:57:41.677163 140239494461312 module_wrapper.py:139] From /content/gdrive/MyDrive/Training_SSD/SSD-1/deployment/model_deploy.py:194: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.

WARNING:tensorflow:From /content/gdrive/MyDrive/Training_SSD/SSD-1/deployment/model_deploy.py:194: The name tf.get_variable_scope is deprecated. Please use tf.compat.v1.get_variable_scope instead.

W1024 13:57:41.677324 140239494461312 module_wrapper.py:139] From /content/gdrive/MyDrive/Training_SSD/SSD-1/deployment/model_deploy.py:194: The name tf.get_variable_scope is deprecated. Please use tf.compat.v1.get_variable_scope instead.

WARNING:tensorflow:From /usr/local/lib/python3.7/dist-packages/tensorflow_core/contrib/layers/python/layers/layers.py:1057: Layer.apply (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `layer.__call__` method instead.
W1024 13:57:41.679852 140239494461312 deprecation.py:323] From /usr/local/lib/python3.7/dist-packages/tensorflow_core/contrib/layers/python/layers/layers.py:1057: Layer.apply (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `layer.__call__` method instead.
WARNING:tensorflow:From /content/gdrive/MyDrive/Training_SSD/SSD-1/nets/ssd_vgg_300.py:476: dropout (from tensorflow.python.layers.core) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.dropout instead.
W1024 13:57:41.998192 140239494461312 deprecation.py:323] From /content/gdrive/MyDrive/Training_SSD/SSD-1/nets/ssd_vgg_300.py:476: dropout (from tensorflow.python.layers.core) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.dropout instead.
WARNING:tensorflow:From /content/gdrive/MyDrive/Training_SSD/SSD-1/nets/ssd_vgg_300.py:642: The name tf.losses.add_loss is deprecated. Please use tf.compat.v1.losses.add_loss instead.

W1024 13:57:42.408573 140239494461312 module_wrapper.py:139] From /content/gdrive/MyDrive/Training_SSD/SSD-1/nets/ssd_vgg_300.py:642: The name tf.losses.add_loss is deprecated. Please use tf.compat.v1.losses.add_loss instead.

WARNING:tensorflow:From train_ssd_network.py:307: The name tf.summary.histogram is deprecated. Please use tf.compat.v1.summary.histogram instead.

W1024 13:57:42.419716 140239494461312 module_wrapper.py:139] From train_ssd_network.py:307: The name tf.summary.histogram is deprecated. Please use tf.compat.v1.summary.histogram instead.

WARNING:tensorflow:From train_ssd_network.py:308: The name tf.summary.scalar is deprecated. Please use tf.compat.v1.summary.scalar instead.

W1024 13:57:42.420833 140239494461312 module_wrapper.py:139] From train_ssd_network.py:308: The name tf.summary.scalar is deprecated. Please use tf.compat.v1.summary.scalar instead.

WARNING:tensorflow:From /content/gdrive/MyDrive/Training_SSD/SSD-1/tf_utils.py:105: The name tf.train.exponential_decay is deprecated. Please use tf.compat.v1.train.exponential_decay instead.

W1024 13:57:42.625701 140239494461312 module_wrapper.py:139] From /content/gdrive/MyDrive/Training_SSD/SSD-1/tf_utils.py:105: The name tf.train.exponential_decay is deprecated. Please use tf.compat.v1.train.exponential_decay instead.

WARNING:tensorflow:From /content/gdrive/MyDrive/Training_SSD/SSD-1/tf_utils.py:144: The name tf.train.AdamOptimizer is deprecated. Please use tf.compat.v1.train.AdamOptimizer instead.

W1024 13:57:42.629828 140239494461312 module_wrapper.py:139] From /content/gdrive/MyDrive/Training_SSD/SSD-1/tf_utils.py:144: The name tf.train.AdamOptimizer is deprecated. Please use tf.compat.v1.train.AdamOptimizer instead.

WARNING:tensorflow:From /content/gdrive/MyDrive/Training_SSD/SSD-1/tf_utils.py:245: The name tf.trainable_variables is deprecated. Please use tf.compat.v1.trainable_variables instead.

W1024 13:57:42.630920 140239494461312 module_wrapper.py:139] From /content/gdrive/MyDrive/Training_SSD/SSD-1/tf_utils.py:245: The name tf.trainable_variables is deprecated. Please use tf.compat.v1.trainable_variables instead.

WARNING:tensorflow:From train_ssd_network.py:367: The name tf.summary.merge is deprecated. Please use tf.compat.v1.summary.merge instead.

W1024 13:57:43.817304 140239494461312 module_wrapper.py:139] From train_ssd_network.py:367: The name tf.summary.merge is deprecated. Please use tf.compat.v1.summary.merge instead.

WARNING:tensorflow:From train_ssd_network.py:372: The name tf.GPUOptions is deprecated. Please use tf.compat.v1.GPUOptions instead.

W1024 13:57:43.820022 140239494461312 module_wrapper.py:139] From train_ssd_network.py:372: The name tf.GPUOptions is deprecated. Please use tf.compat.v1.GPUOptions instead.

WARNING:tensorflow:From train_ssd_network.py:373: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.

W1024 13:57:43.820249 140239494461312 module_wrapper.py:139] From train_ssd_network.py:373: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.

WARNING:tensorflow:From train_ssd_network.py:375: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.

W1024 13:57:43.820408 140239494461312 module_wrapper.py:139] From train_ssd_network.py:375: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.

WARNING:tensorflow:From /content/gdrive/MyDrive/Training_SSD/SSD-1/tf_utils.py:226: The name tf.gfile.IsDirectory is deprecated. Please use tf.io.gfile.isdir instead.

W1024 13:57:43.963253 140239494461312 module_wrapper.py:139] From /content/gdrive/MyDrive/Training_SSD/SSD-1/tf_utils.py:226: The name tf.gfile.IsDirectory is deprecated. Please use tf.io.gfile.isdir instead.

WARNING:tensorflow:From /content/gdrive/MyDrive/Training_SSD/SSD-1/tf_utils.py:230: The name tf.logging.info is deprecated. Please use tf.compat.v1.logging.info instead.

W1024 13:57:43.963784 140239494461312 module_wrapper.py:139] From /content/gdrive/MyDrive/Training_SSD/SSD-1/tf_utils.py:230: The name tf.logging.info is deprecated. Please use tf.compat.v1.logging.info instead.

INFO:tensorflow:Fine-tuning from /content/gdrive/MyDrive/Training_SSD/SSD-1/checkpoints/ssd_300_vgg.ckpt/ssd_300_vgg.ckpt. Ignoring missing vars: False
I1024 13:57:43.963922 140239494461312 tf_utils.py:230] Fine-tuning from /content/gdrive/MyDrive/Training_SSD/SSD-1/checkpoints/ssd_300_vgg.ckpt/ssd_300_vgg.ckpt. Ignoring missing vars: False
WARNING:tensorflow:From /usr/local/lib/python3.7/dist-packages/tensorflow_core/contrib/slim/python/slim/learning.py:742: Supervisor.__init__ (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.MonitoredTrainingSession
W1024 13:57:44.120857 140239494461312 deprecation.py:323] From /usr/local/lib/python3.7/dist-packages/tensorflow_core/contrib/slim/python/slim/learning.py:742: Supervisor.__init__ (from tensorflow.python.training.supervisor) is deprecated and will be removed in a future version.
Instructions for updating:
Please switch to tf.train.MonitoredTrainingSession
2021-10-24 13:57:44.436826: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 AVX512F FMA
2021-10-24 13:57:44.440876: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2000170000 Hz
2021-10-24 13:57:44.441070: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x56449f9cb9c0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2021-10-24 13:57:44.441100: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
2021-10-24 13:57:44.442817: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1
2021-10-24 13:57:44.554870: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-10-24 13:57:44.555802: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x56449f9cb640 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
2021-10-24 13:57:44.555833: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Tesla P100-PCIE-16GB, Compute Capability 6.0
2021-10-24 13:57:44.556006: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-10-24 13:57:44.556564: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: 
name: Tesla P100-PCIE-16GB major: 6 minor: 0 memoryClockRate(GHz): 1.3285
pciBusID: 0000:00:04.0
2021-10-24 13:57:44.556867: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2021-10-24 13:57:44.558049: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
2021-10-24 13:57:44.559113: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10.0
2021-10-24 13:57:44.559464: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10.0
2021-10-24 13:57:44.560805: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10.0
2021-10-24 13:57:44.561773: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10.0
2021-10-24 13:57:44.564919: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
2021-10-24 13:57:44.565038: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-10-24 13:57:44.565658: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-10-24 13:57:44.566169: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0
2021-10-24 13:57:44.566234: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.0
2021-10-24 13:57:44.567361: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:
2021-10-24 13:57:44.567389: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165]      0 
2021-10-24 13:57:44.567399: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0:   N 
2021-10-24 13:57:44.567544: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-10-24 13:57:44.568127: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-10-24 13:57:44.568645: W tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:39] Overriding allow_growth setting because the TF_FORCE_GPU_ALLOW_GROWTH environment variable is set. Original config value was 0.
2021-10-24 13:57:44.568687: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 14652 MB memory) -> physical GPU (device: 0, name: Tesla P100-PCIE-16GB, pci bus id: 0000:00:04.0, compute capability: 6.0)
INFO:tensorflow:Restoring parameters from /content/gdrive/MyDrive/Training_SSD/SSD-1/checkpoints/ssd_300_vgg.ckpt/ssd_300_vgg.ckpt
I1024 13:57:45.783673 140239494461312 saver.py:1284] Restoring parameters from /content/gdrive/MyDrive/Training_SSD/SSD-1/checkpoints/ssd_300_vgg.ckpt/ssd_300_vgg.ckpt
INFO:tensorflow:Running local_init_op.
I1024 13:57:46.017776 140239494461312 session_manager.py:500] Running local_init_op.
INFO:tensorflow:Done running local_init_op.
I1024 13:57:46.075058 140239494461312 session_manager.py:502] Done running local_init_op.
INFO:tensorflow:Starting Session.
I1024 13:57:47.806292 140239494461312 learning.py:754] Starting Session.
INFO:tensorflow:Saving checkpoint to path /content/gdrive/MyDrive/Training_SSD/SSD-1/log_30000/model.ckpt
I1024 13:57:47.882676 140237141432064 supervisor.py:1117] Saving checkpoint to path /content/gdrive/MyDrive/Training_SSD/SSD-1/log_30000/model.ckpt
INFO:tensorflow:Starting Queues.
I1024 13:57:47.896139 140239494461312 learning.py:768] Starting Queues.
INFO:tensorflow:global_step/sec: 0
I1024 13:57:51.071433 140237149824768 supervisor.py:1099] global_step/sec: 0
2021-10-24 13:57:51.662253: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
2021-10-24 13:57:52.787163: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
INFO:tensorflow:Recording summary at step 1.
I1024 13:57:55.259541 140235672987392 supervisor.py:1050] Recording summary at step 1.
INFO:tensorflow:global step 10: loss = 9.6467 (0.115 sec/step)
I1024 13:57:56.277639 140239494461312 learning.py:507] global step 10: loss = 9.6467 (0.115 sec/step)
INFO:tensorflow:global step 20: loss = 0.7245 (0.106 sec/step)
I1024 13:57:57.399851 140239494461312 learning.py:507] global step 20: loss = 0.7245 (0.106 sec/step)
INFO:tensorflow:global step 30: loss = 9.5159 (0.109 sec/step)
I1024 13:57:58.544558 140239494461312 learning.py:507] global step 30: loss = 9.5159 (0.109 sec/step)
INFO:tensorflow:global step 40: loss = 0.6637 (0.106 sec/step)
I1024 13:57:59.686780 140239494461312 learning.py:507] global step 40: loss = 0.6637 (0.106 sec/step)
INFO:tensorflow:global step 50: loss = 0.7424 (0.140 sec/step)
I1024 13:58:00.898716 140239494461312 learning.py:507] global step 50: loss = 0.7424 (0.140 sec/step)
INFO:tensorflow:global step 60: loss = 21.9683 (0.141 sec/step)
I1024 13:58:02.276094 140239494461312 learning.py:507] global step 60: loss = 21.9683 (0.141 sec/step)
INFO:tensorflow:global step 70: loss = 0.6486 (0.132 sec/step)
I1024 13:58:03.593588 140239494461312 learning.py:507] global step 70: loss = 0.6486 (0.132 sec/step)
INFO:tensorflow:global step 80: loss = 9.6484 (0.135 sec/step)
I1024 13:58:04.992696 140239494461312 learning.py:507] global step 80: loss = 9.6484 (0.135 sec/step)
INFO:tensorflow:global step 90: loss = 0.6877 (0.114 sec/step)
I1024 13:58:06.135541 140239494461312 learning.py:507] global step 90: loss = 0.6877 (0.114 sec/step)
INFO:tensorflow:global step 100: loss = 4.4349 (0.116 sec/step)
I1024 13:58:07.301742 140239494461312 learning.py:507] global step 100: loss = 4.4349 (0.116 sec/step)

evaluation:

AP_VOC07/mAP[5.1152988357579853e-06]
AP_VOC12/mAP[2.170187439798707e-06]
INFO:tensorflow:Finished evaluation at 2021-10-25-17:40:59
I1025 17:40:59.709131 140242808874880 evaluation.py:275] Finished evaluation at 2021-10-25-17:40:59
Time spent : 20.097 seconds.
Time spent per BATCH: 0.120 seconds.

Answer 1

When loss varies and doesn't converge to a desired minimum, there are a few situations you can check, for object detection.

I'm assuming you are fine-tuning to a specific dataset with your own custom objects/classes.

1. Make sure your bounding boxes are well fitted to the object. From past experiences, this is a key point for a proper training. Spend as much time as you can building a robust dataset with good annotations.
2. What are the dimensions of your bounding boxes compared to the image? Too large or too small bounding boxes sometimes are difficult to detect, depending on the chosen hyperparameters, my workaround on this is to vary the aspect ratios and scales of the bounding box generator of the model.
3. Is your dataset similar across all frames? Do you have on average the same amount of bounding boxes in each frame? Increased variability in your dataset makes your model susceptible to weak training. So if this is your situation, you should consider enlarging your dataset with more data to decrease variability, or choose only similar frames by removing "outliers".
4. Does your number of classes/objects correspond to the number classes configured in the model? If you only have 10 classes and the model is built for 100, this may lead to you situation.
5. Check your learning rate. For pre-trained models, start of with a very small learning rate (1e-4 or 1e-5). With a large learning rate your model may end just bouncing between the same local minima (unstable loss). Try to implement a scheduler as well, reducing the learning rate every X steps.

Also take in consideration that your dataset is "small", which makes training much harder and sometimes requires a lot of hyperparameter tuning, nonetheless, you should be capable to achieve much higher mAP, mAR and decreased loss with some of the default config.

Bonus tip, that repo is a bit old, consider taking a look at the Tensorflow Object Detection API here and here. It provides a wider range of models including SOTA ones, and the configuration is quite similar to what you are already doing.