I trained 18 class with darknet but now i want to add 2 new class. How can I add this 2 class without waiting a long time.
Related
I am trying to use DeepLabV3 for image segmentation and object detection/classification on Coral.
I was able to sucessfully run the semantic_segmentation.py example using DeepLabV3 on the coral, but that only shows an image with an object segmented.
I see that it assigns labels to colors - how do i associate the labels.txt file that I made based off of the label info of the model to these colors? (how do i know which color corresponds to which label).
When I try to run the
engine = DetectionEngine(args.model)
using the deeplab model, I get the error
ValueError: Dectection model should have 4 output tensors!This model
has 1.
I guess this way is the wrong approach?
Thanks!
I believe you have reached out to us regarding the same query. I just wanted to paste the answer here for others to reference:
"The detection model usually have 4 output tensors to specifies the locations, classes, scores, and number and detections. You can read more about it here. In contrary, the segmentation model only have a single output tensor, so if you treat it the same way, you'll most likely segfault trying to access the wrong memory region. If you want to do all three tasks on the same image, my suggestion is to create 3 different engines and feed the image into each. The only problem with this is that each time you switch the model, there will likely be data transfer bottleneck for the model to get loaded onto the TPU. We have here an example on how you can run 2 models on a single TPU, you should be able to modify it to take 3 models."
On the last note, I just saw that you added:
how do i associate the labels.txt file that I made based off of the label info of the model to these colors
I just don't think this is something you can do for segmentation model but maybe I'm just confused on your query?
Take object detection model for example, there are 4 output tensors, the second tensor gives you an array of id associates with a certain class that you can map to a a label file. Segmentaion models only give the pixel surrounding an objects.
[EDIT]
Apology, looks like I'm the one confused on segmentation models.
Quote form my college :)
"You are interested to know the name of the label, you can find the corresponding integer to that label from result array in Semantic_segmentation.py. Where result is classification data of each pixel.
For example;
if you print result array in the with bird.jpg as input you would find few pixel's value as 3 which is corresponding 4th label in pascal_voc_segmentation_labels.txt (as indexing starts at 0 )."
Let's say my model has two classes Class 1 and Class 2. Both Class 1 and Class 2 has a equal amount of training and testing data. But I want to penalize the loss of the Class 1 more than Class 2, so that one class has a fewer number of False Positives than the other (I want the model to perform better for one class than the other).
How do I achieve this in Tensorflow?
The thing you are looking for is probably
weighted_cross_entropy.
It is giving a very closely related contextual information, similar to #Sazzad 's answer, but specific to TensorFlow. To quote the documentation:
This is like sigmoid_cross_entropy_with_logits() except that
pos_weight, allows one to trade off recall and precision by up- or
down-weighting the cost of a positive error relative to a negative
error.
It accepts an additional argument pos_weights. Also note that this is only for binary classification, which is the case in the example you described. If there might be other classes besides the two, this would not work.
If I understand your question correctly, this is not a tensorflow concept. you can write your own. for binary classification, the loss is something like this
loss = ylogy + (1-y)log(1-y)
Here class 0 and class 1 have the same weight in the loss. So you can give more give more weight to some portion. for example,
loss = 5 * ylogy + (1-y)log(1-y)
Hope it answers your question.
I want to create my own .tfrecord files using tensorflow object detection API and use them for training. The record will be a subset of original dataset so the model will detect only specific categories.
The thing I dont understand and cant find any information about is, how are id`s assigned to labels in label_map.pbtxt during training.
What I do...
Step 1:
assign label_id during creation of the tfrecord file, where I put my own ids:
'image/object/class/label': dataset_util.int64_list_feature(category_ids)
'image/object/class/text': dataset_util.bytes_list_feature(category_names)
Step 2:
create labels file with e.g. two categories:
item { name: "apple" id: 53 display_name: "apple" }
item { name: "broccoli" id: 56 display_name: "broccoli" }
Step 3:
Train the model
After training, there are some objects detected, but with N/A label. When I set the id`s starting from 1 then it shows correct labels.
My questions are:
Why it did not map correctly to label with custom id?
Can the second id have other value than 2? I'm sure I saw skipped ids in labels file for coco dataset.
How to set the id to have custom value, if possible?
Thanks
I had the same problem with my label map. After Googling a bit, I found your question here and also this excerpt from the TensorFlow Object Detection repository:
Each dataset is required to have a label map associated with it. This label map defines a mapping from string class names to integer class Ids. The label map should be a StringIntLabelMap text protobuf. Sample label maps can be found in object_detection/data. Label maps should always start from id 1.
I also checked the source code for label_map_util.py and found this comment:
We only allow class into the list if its id-label_id_offset is
between 0 (inclusive) and max_num_classes (exclusive).
If there are several items mapping to the same id in the label map,
we will only keep the first one in the categories list
So in your example, which only has two classes, valid ID's are 1 and 2. Any higher value will be ignored.
When training a single class object detector in Tensorflow, I am trying to pass instances of images where no signal object exists, such that the model doesn't learn that every image contains at least one instance of that class. E.g. if my signal were cats, id want to pass pictures of other animals/landscapes as background -this could also reduce false positives.
I can see that a class id is reserved in the object detection API (0) for background, but I am unsure how to code this into the TFrecords for my background images - class could be 0 but what would be the bounding box coords? Or do i need a simpler classifier on top of this model to detect if there is a signal in the image or not, prior to detecting position?
Later approach of simple classifier, makes sense. I don't think there is a way to do the first part. You can use check on confidence score as well apart from checking the object is present.
It is good practice to create a dataset with not objects of interest, for the same you need to use the same tools (like - label img) that you have used for adding the boxes, image with no BB wil have xml files with no details of BB but only details of the image. The script create tf record will create the tf record from the xml files, look at the below links for more inforamtion -
Create tf record example -
https://github.com/tensorflow/models/blob/master/research/object_detection/dataset_tools/create_pet_tf_record.py
Using your own dataset-
https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/using_your_own_dataset.md
Consider this problem: select a random number of samples from a random subject in an image dataset (like ImageNet) as an input element for Tensorflow graph which functions as an object set recognizer. For each batch, each class has a same number of samples to facilitate computation. But a different batch would have a different number of images for one class, i.e. batch_0:num_imgs_per_cls=2; batch_1000:num_imgs_per_cls=3.
If there is existing functionality in Tensorflow, explanation for the whole process from scratch (like from directories of images) will be really appreciated.
There is a very similar answer by #mrry here.
Sampling balanced batches
In face recognition we often use triplet loss (or similar losses) to train the model. The usual way to sample triplets to compute the loss is to create a balanced batch of images where we have for instance 10 different classes (i.e. 10 different people) with 5 images each. This gives a total batch size of 50 in this example.
More generally the problem is to sample num_classes_per_batch (10 in the example) classes, and then sample num_images_per_class (5 in the example) images for each class. The total batch size is:
batch_size = num_classes_per_batch * num_images_per_class
Have one dataset for each class
The easiest way to deal with a lot of different classes (100,000 in MS-Celeb) is to create one dataset for each class.
For instance you can have one tfrecord for each class and create the datasets like this:
# Build one dataset per class.
filenames = ["class_0.tfrecords", "class_1.tfrecords"...]
per_class_datasets = [tf.data.TFRecordDataset(f).repeat(None) for f in filenames]
Sample from the datasets
Now we would like to be able to sample from these datasets. For instance we want the following labels in our batch:
1 1 1 3 3 3 9 9 9 4 4 4
This corresponds to num_classes_per_batch=4 and num_images_per_class=3.
To do this we will need to use features that will be released in r1.9. The function should be called tf.contrib.data.choose_from_datasets (see here for a discussion on this).
It should look like:
def choose_from_datasets(datasets, selector):
"""Chooses elements with indices from selector among the datasets in `datasets`."""
So we create this selector which will output 1 1 1 3 3 3 9 9 9 4 4 4 and combine it with datasets to obtain our final dataset that will output balanced batches:
def generator(_):
# Sample `num_classes_per_batch` classes for the batch
sampled = tf.random_shuffle(tf.range(num_classes))[:num_classes_per_batch]
# Repeat each element `num_images_per_class` times
batch_labels = tf.tile(tf.expand_dims(sampled, -1), [1, num_images_per_class])
return tf.to_int64(tf.reshape(batch_labels, [-1]))
selector = tf.contrib.data.Counter().map(generator)
selector = selector.apply(tf.contrib.data.unbatch())
dataset = tf.contrib.data.choose_from_datasets(datasets, selector)
# Batch
batch_size = num_classes_per_batch * num_images_per_class
dataset = dataset.batch(batch_size)
You can test this with the nightly TensorFlow build and by using DirectedInterleaveDataset as a workaround:
# The working option right now is
from tensorflow.contrib.data.python.ops.interleave_ops import DirectedInterleaveDataset
dataset = DirectedInterleaveDataset(selector, datasets)
I also wrote about this workaround here.