I'm a beginner with some programming experince. I'm trying to train darkflow with my own dataset. I'm following these instructions.
https://github.com/thtrieu/darkflow
So far I have done the following steps.
installed darkflow and the relevant modules
created test images and made annotations (Pascal VOC).
https://ibb.co/y4HmtGz
https://ibb.co/GkxLshK
If I have understood correctly the darkflow training requires Pascal VOC?
My problem is that I don't know how to start the training. How can I start the training process and how can I test if the neuralnet is working? Am I supposed to get weights as a result of training?
You can choose to use pre-trained weights from here. Download cfg and weights.
Assuming you have darkflow installed, you can train your network like this:
flow --model cfg/<your-config-filename>.cfg --load bin/<filename>.weights --train --annotation train/Annotations --dataset train/Images --epoch 100 --gpu 1.0
If you want to train your network from scratch w/o using any pre-trained weights,
you can do this:
flow --model cfg/<your-config-filename>.cfg --train --annotation train/Annotations --dataset train/Images --epoch 100 --gpu 1.0
After the training starts, model checkpoints are saved inside ckpt directory. You can load latest checkpoint and test on sample images.
Related
I'm trying to object detection with yolov3 and yolov4 and i just want to train 1 class= person.
I'm using COCO datasets.
After training how i can tested my weight file? I want to test all "test dataset" not only 1 image.
I have train loss graphic but this is not enough.
I want to calculate accuracy, precision, recall etc.
I found this examples : https://darknet.gong.im/
./darknet detector test cfg/coco.data cfg/yolov3.cfg weights/yolov3.weights batch ./in_images/ ./out_images/ >./results.txt
Can you tell me how i can compare with success metric this two algorithm?
How can i test yolov3 and yolov4 weight files ?
There is map function for testing the model.
./darknet detector map cfg/coco.data cfg/yolov3.cfg weights/yolov3.weights
If you label your test dataset and give the path of it to the 'valid' field inside the data file, you can use map function over your dataset.
Also you can use -map flag while training to see the map results on the graph.
If you use -map flag while training darknet also saves best weight file so you don't need to find the best one.
I will describe my intention here. I want to import BERT pretrained model via tf-hub function hub.module(bert_url, trainable = True) and utilize it for text classification task. I plan to use a large corpus to fine-tune weights of BERT as well as a few dense layers whose inputs are the BERT outputs. I would then like to freeze layers of BERT and train only the dense layers following BERT. How can I do this efficiently?
You mention Hub's TF1 API hub.Module, so I suppose you are writing TF1 code and using the TF1-compatible Hub assets google/bert/..., such as https://tfhub.dev/google/bert_cased_L-12_H-768_A-12/1
Are you going to have separate run of your program for the two phases of training? If so, maybe you can just drop trainable=True from the hub.Module call in the second run. This doesn't affect variable names, so you can restore the training result from the first run, including BERT's adjusted weights. (To be clear: the pre-trained weights shipped with the hub.Module are only used for initialization at the very start of training; restoring a checkpoint overrides them.)
I am aiming to inference tensorflow slim model with Intel OpenVINO optimizer. Using open vino docs and slides for inference and tf slim docs for training model.
It's a multi-class classification problem. I have trained tf slim mobilnet_v2 model from scratch (using sript train_image_classifier.py). Evaluation of trained model on test set gives relatively good results to begin with (using script eval_image_classifier.py):
eval/Accuracy[0.8017]eval/Recall_5[0.9993]
However, single .ckpt file is not saved (even though at the end of train_image_classifier.py run there is a message like "model.ckpt is saved to checkpoint_dir"), there are 3 files (.ckpt-180000.data-00000-of-00001, .ckpt-180000.index, .ckpt-180000.meta) instead.
OpenVINO model optimizer requires a single checkpoint file.
According to docs I call mo_tf.py with following params:
python mo_tf.py --input_model D:/model/mobilenet_v2_224.pb --input_checkpoint D:/model/model.ckpt-180000 -b 1
It gives the error (same if pass --input_checkpoint D:/model/model.ckpt):
[ ERROR ] The value for command line parameter "input_checkpoint" must be existing file/directory, but "D:/model/model.ckpt-180000" does not exist.
Error message is clear, there are not such files on disk. But as I know most tf utilities convert .ckpt-????.meta to .ckpt under the hood.
Trying to call:
python mo_tf.py --input_model D:/model/mobilenet_v2_224.pb --input_meta_graph D:/model/model.ckpt-180000.meta -b 1
Causes:
[ ERROR ] Unknown configuration of input model parameters
It doesn't matter for me in which way I will transfer graph to OpenVINO intermediate representation, just need to reach that result.
Thanks a lot.
EDIT
I managed to run OpenVINO model optimizer on frozen graph of tf slim model. However I still have no idea why had my previous attempts (based on docs) failed.
you can try converting the model to frozen format (.pb) and then convert the model using OpenVINO.
.ckpt-meta has the metagraph. The computation graph structure without variable values.
the one you can observe in tensorboard.
.ckpt-data has the variable values,without the skeleton or structure. to restore a model we need both meta and data files.
.pb file saves the whole graph (meta+data)
As per the documentation of OpenVINO:
When a network is defined in Python* code, you have to create an inference graph file. Usually, graphs are built in a form that allows model training. That means that all trainable parameters are represented as variables in the graph. To use the graph with the Model Optimizer, it should be frozen.
https://software.intel.com/en-us/articles/OpenVINO-Using-TensorFlow
the OpenVINO optimizes the model by converting the weighted graph passed in frozen form.
I have a model trained with tf.estimator and it was exported after training as below
serving_input_fn = tf.estimator.export.build_raw_serving_input_receiver_fn(
feature_placeholders)
classifier.export_savedmodel(
r'./path/to/model/trainedModel', serving_input_fn)
This gives me a saved_model.pb and a folder which contains weights as a .data file. I can reload the saved model using
predictor = tf.contrib.predictor.from_saved_model(r'./path/to/model/trainedModel')
I'd like to run this model on android and that requires the model to be in .pb format. How can I freeze this predictor for use on android platform?
I don't deploy to Android, so you might need to customize the steps a bit, but this is how I do this:
Run <tensorflow_root_installation>/python/tools/freeze_graph.py with arguments --input_saved_model_dir=<path_to_the_savedmodel_directory>, --output_node_names=<full_name_of_the_output_node> (you can get the name of the output node from graph.pbtxt, although that's not the most comfortable of ways), --output_graph=frozen_model.pb
(optionally) Run <tensorflow_root_installation>/python/tools/optimize_for_inference.py with adequate arguments. Alternatively you can look up the Graph Transform Tool and selectively apply optimizations.
At the end of step 1 you'll already have a frozen model with no variables left, that you can then deploy to Android.
I'm new to TensorFlow and try to run it in distributed mode. Now I have found its official document in https://github.com/tensorflow/tensorflow/blob/master/tensorflow/g3doc/how_tos/distributed/index.md . But it lacks something in loss function.
Can anyone help to complete that so that I can run with your code?
It not only lacks of loss function, it lacks of the model to train and thus the loss to minimize.
This file is just a template file that you have to complete in order to train your model in distributed mode.
So, when in the template file you find the comment
# Build model...
It means that you have to define a model to train (eg: a convolutional neural network, a simple perceptron...).
Something like the MNIST model that you can find in the tutorial: https://www.tensorflow.org/versions/r0.9/tutorials/mnist/beginners/index.html
Your model ends with a loss function to minimize.
Following the MNIST example, the loss is:
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
loss = cross_entropy
Once you defined the model to train and the loss to minimize, you have filled the template with the missing values and you can now start to train you model in distributed mode.