Develop Reference

How to load a TF Lite Model into Python from a file

I've followed the End-to-End image classification tutorial for tensorflow lite and have created and saved my model as '/path/to/model.tflite'.
What I haven't been able to figure out is how to load it.
I'm looking for some kind of syntax that is similar to this:
from tflite_model_maker import image_classifier
from tflite_model_maker.image_classifier import DataLoader
model = image_classifier.Load('/path/to/model.tflite')
I'm sure I'm missing something obvious here. This is definitely not the first place I've looked at. This seems to be the best place for me to find what I need, but the syntax used confuses me.
What do I want to be able to do with the model?
test = DataLoader.from_folder('/path/to/testImages')
loss, accuracy = model.evaluate(test)
# A helper function that returns 'red'/'black' depending on if its two input
# parameter matches or not.
def get_label_color(val1, val2):
if val1 == val2:
return 'black'
else:
return 'red'
# Then plot 100 test images and their predicted labels.
# If a prediction result is different from the label provided label in "test"
# dataset, we will highlight it in red color.
test_data = data
plt.figure(figsize=(20, 20))
predicts = model.predict_top_k(test_data)
for i, (image, label) in enumerate(test_data.gen_dataset().unbatch().take(100)):
ax = plt.subplot(10, 10, i+1)
plt.xticks([])
plt.yticks([])
plt.grid(False)
plt.imshow(image.numpy(), cmap=plt.cm.gray)
predict_label = predicts[i][0][0]
color = get_label_color(predict_label,
test_data.index_to_label[label.numpy()])
ax.xaxis.label.set_color(color)
plt.xlabel('Predicted: %s' % predict_label)
plt.show()
From the syntax above it seems the model isn't just a file but is a type/class/method depending on what name is most suitable for python.
Feels like this should only take one line of code but I haven't been able to find it anywhere.

Managed to do a simple version of it. The images coming up as a stream doesn't work for me using cv2 with Windows as it does for the pi. So instead I created a webpage in the same directory as this script. This generates an image with the bounding box, using a specified tflite model. This is in no way ideal.
It uses a webcam to get the image and saves the image to the directory the script is run in. It then renames the file so it can be viewed by the webpage I setup to view it.
The majority of this code comes from the TFLite Object Detection Raspberry Pi sample.
import time, os
from PIL import Image
from tflite_support import metadata
import platform
from typing import List, NamedTuple
import json
import cv2 as cv2
import numpy as np
import tensorflow as tf
from matplotlib import pyplot as plt
Interpreter = tf.lite.Interpreter
load_delegate = tf.lite.experimental.load_delegate
class ObjectDetectorOptions(NamedTuple):
"""A config to initialize an object detector."""
enable_edgetpu: bool = False
"""Enable the model to run on EdgeTPU."""
label_allow_list: List[str] = None
"""The optional allow list of labels."""
label_deny_list: List[str] = None
"""The optional deny list of labels."""
max_results: int = -1
"""The maximum number of top-scored detection results to return."""
num_threads: int = 1
"""The number of CPU threads to be used."""
score_threshold: float = 0.0
"""The score threshold of detection results to return."""
class Rect(NamedTuple):
"""A rectangle in 2D space."""
left: float
top: float
right: float
bottom: float
class Category(NamedTuple):
"""A result of a classification task."""
label: str
score: float
index: int
class Detection(NamedTuple):
"""A detected object as the result of an ObjectDetector."""
bounding_box: Rect
categories: List[Category]
def edgetpu_lib_name():
"""Returns the library name of EdgeTPU in the current platform."""
return {
'Darwin': 'libedgetpu.1.dylib',
'Linux': 'libedgetpu.so.1',
'Windows': 'edgetpu.dll',
}.get(platform.system(), None)
class ObjectDetector:
"""A wrapper class for a TFLite object detection model."""
_OUTPUT_LOCATION_NAME = 'location'
_OUTPUT_CATEGORY_NAME = 'category'
_OUTPUT_SCORE_NAME = 'score'
_OUTPUT_NUMBER_NAME = 'number of detections'
def __init__(
self,
model_path: str,
options: ObjectDetectorOptions = ObjectDetectorOptions()
) -> None:
"""Initialize a TFLite object detection model.
Args:
model_path: Path to the TFLite model.
options: The config to initialize an object detector. (Optional)
Raises:
ValueError: If the TFLite model is invalid.
OSError: If the current OS isn't supported by EdgeTPU.
"""
# Load metadata from model.
displayer = metadata.MetadataDisplayer.with_model_file(model_path)
# Save model metadata for preprocessing later.
model_metadata = json.loads(displayer.get_metadata_json())
process_units = model_metadata['subgraph_metadata'][0]['input_tensor_metadata'][0]['process_units']
mean = 0.0
std = 1.0
for option in process_units:
if option['options_type'] == 'NormalizationOptions':
mean = option['options']['mean'][0]
std = option['options']['std'][0]
self._mean = mean
self._std = std
# Load label list from metadata.
file_name = displayer.get_packed_associated_file_list()[0]
label_map_file = displayer.get_associated_file_buffer(file_name).decode()
label_list = list(filter(lambda x: len(x) > 0, label_map_file.splitlines()))
self._label_list = label_list
# Initialize TFLite model.
if options.enable_edgetpu:
if edgetpu_lib_name() is None:
raise OSError("The current OS isn't supported by Coral EdgeTPU.")
interpreter = Interpreter(
model_path=model_path,
experimental_delegates=[load_delegate(edgetpu_lib_name())],
num_threads=options.num_threads)
else:
interpreter = Interpreter(
model_path=model_path, num_threads=options.num_threads)
interpreter.allocate_tensors()
input_detail = interpreter.get_input_details()[0]
# From TensorFlow 2.6, the order of the outputs become undefined.
# Therefore we need to sort the tensor indices of TFLite outputs and to know
# exactly the meaning of each output tensor. For example, if
# output indices are [601, 599, 598, 600], tensor names and indices aligned
# are:
# - location: 598
# - category: 599
# - score: 600
# - detection_count: 601
# because of the op's ports of TFLITE_DETECTION_POST_PROCESS
# (https://github.com/tensorflow/tensorflow/blob/a4fe268ea084e7d323133ed7b986e0ae259a2bc7/tensorflow/lite/kernels/detection_postprocess.cc#L47-L50).
sorted_output_indices = sorted(
[output['index'] for output in interpreter.get_output_details()])
self._output_indices = {
self._OUTPUT_LOCATION_NAME: sorted_output_indices[0],
self._OUTPUT_CATEGORY_NAME: sorted_output_indices[1],
self._OUTPUT_SCORE_NAME: sorted_output_indices[2],
self._OUTPUT_NUMBER_NAME: sorted_output_indices[3],
}
self._input_size = input_detail['shape'][2], input_detail['shape'][1]
self._is_quantized_input = input_detail['dtype'] == np.uint8
self._interpreter = interpreter
self._options = options
def detect(self, input_image: np.ndarray) -> List[Detection]:
"""Run detection on an input image.
Args:
input_image: A [height, width, 3] RGB image. Note that height and width
can be anything since the image will be immediately resized according
to the needs of the model within this function.
Returns:
A Person instance.
"""
image_height, image_width, _ = input_image.shape
input_tensor = self._preprocess(input_image)
self._set_input_tensor(input_tensor)
self._interpreter.invoke()
# Get all output details
boxes = self._get_output_tensor(self._OUTPUT_LOCATION_NAME)
classes = self._get_output_tensor(self._OUTPUT_CATEGORY_NAME)
scores = self._get_output_tensor(self._OUTPUT_SCORE_NAME)
count = int(self._get_output_tensor(self._OUTPUT_NUMBER_NAME))
return self._postprocess(boxes, classes, scores, count, image_width,
image_height)
def _preprocess(self, input_image: np.ndarray) -> np.ndarray:
"""Preprocess the input image as required by the TFLite model."""
# Resize the input
input_tensor = cv2.resize(input_image, self._input_size)
# Normalize the input if it's a float model (aka. not quantized)
if not self._is_quantized_input:
input_tensor = (np.float32(input_tensor) - self._mean) / self._std
# Add batch dimension
input_tensor = np.expand_dims(input_tensor, axis=0)
return input_tensor
def _set_input_tensor(self, image):
"""Sets the input tensor."""
tensor_index = self._interpreter.get_input_details()[0]['index']
input_tensor = self._interpreter.tensor(tensor_index)()[0]
input_tensor[:, :] = image
def _get_output_tensor(self, name):
"""Returns the output tensor at the given index."""
output_index = self._output_indices[name]
tensor = np.squeeze(self._interpreter.get_tensor(output_index))
return tensor
def _postprocess(self, boxes: np.ndarray, classes: np.ndarray,
scores: np.ndarray, count: int, image_width: int,
image_height: int) -> List[Detection]:
"""Post-process the output of TFLite model into a list of Detection objects.
Args:
boxes: Bounding boxes of detected objects from the TFLite model.
classes: Class index of the detected objects from the TFLite model.
scores: Confidence scores of the detected objects from the TFLite model.
count: Number of detected objects from the TFLite model.
image_width: Width of the input image.
image_height: Height of the input image.
Returns:
A list of Detection objects detected by the TFLite model.
"""
results = []
# Parse the model output into a list of Detection entities.
for i in range(count):
if scores[i] >= self._options.score_threshold:
y_min, x_min, y_max, x_max = boxes[i]
bounding_box = Rect(
top=int(y_min * image_height),
left=int(x_min * image_width),
bottom=int(y_max * image_height),
right=int(x_max * image_width))
class_id = int(classes[i])
category = Category(
score=scores[i],
label=self._label_list[class_id], # 0 is reserved for background
index=class_id)
result = Detection(bounding_box=bounding_box, categories=[category])
results.append(result)
# Sort detection results by score ascending
sorted_results = sorted(
results,
key=lambda detection: detection.categories[0].score,
reverse=True)
# Filter out detections in deny list
filtered_results = sorted_results
if self._options.label_deny_list is not None:
filtered_results = list(
filter(
lambda detection: detection.categories[0].label not in self.
_options.label_deny_list, filtered_results))
# Keep only detections in allow list
if self._options.label_allow_list is not None:
filtered_results = list(
filter(
lambda detection: detection.categories[0].label in self._options.
label_allow_list, filtered_results))
# Only return maximum of max_results detection.
if self._options.max_results > 0:
result_count = min(len(filtered_results), self._options.max_results)
filtered_results = filtered_results[:result_count]
return filtered_results
_MARGIN = 10 # pixels
_ROW_SIZE = 10 # pixels
_FONT_SIZE = 1
_FONT_THICKNESS = 1
_TEXT_COLOR = (0, 0, 255) # red
def visualize(
image: np.ndarray,
detections: List[Detection],
) -> np.ndarray:
"""Draws bounding boxes on the input image and return it.
Args:
image: The input RGB image.
detections: The list of all "Detection" entities to be visualize.
Returns:
Image with bounding boxes.
"""
for detection in detections:
# Draw bounding_box
start_point = detection.bounding_box.left, detection.bounding_box.top
end_point = detection.bounding_box.right, detection.bounding_box.bottom
cv2.rectangle(image, start_point, end_point, _TEXT_COLOR, 3)
# Draw label and score
category = detection.categories[0]
class_name = category.label
probability = round(category.score, 2)
result_text = class_name + ' (' + str(probability) + ')'
text_location = (_MARGIN + detection.bounding_box.left,
_MARGIN + _ROW_SIZE + detection.bounding_box.top)
cv2.putText(image, result_text, text_location, cv2.FONT_HERSHEY_PLAIN,
_FONT_SIZE, _TEXT_COLOR, _FONT_THICKNESS)
return image
# ---------------------------------- #
# This is where the custom code starts
# ---------------------------------- #
# Load the TFLite model
TFLITE_MODEL_PATH='object.tflite'
DETECTION_THRESHOLD = 0.5 # 50% threshold required before identifying
options = ObjectDetectorOptions(
num_threads=4,
score_threshold=DETECTION_THRESHOLD,
)
# Close camera if already open
try:
cap.release()
except:
print("",end="") # do nothing
detector = ObjectDetector(model_path=TFLITE_MODEL_PATH, options=options)
cap = cv2.VideoCapture(0) #webcam
counter = 0 # Store many times model has run
while cap.isOpened():
success, image = cap.read()
if not success:
sys.exit(
'ERROR: Unable to read from webcam. Please verify your webcam settings.'
)
image = cv2.flip(image, 1)
# Convert the image from BGR to RGB as required by the TFLite model.
rgb_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
#image.thumbnail((512, 512), Image.ANTIALIAS)
image_np = np.asarray(image)
# Run object detection estimation using the model.
detections = detector.detect(image_np)
# Draw keypoints and edges on input image
image_np = visualize(image_np, detections)
if counter == 10: # <- Change this to decide how many iterations
cap.release()
break
image_np = cv2.cvtColor(image_np, cv2.COLOR_BGR2RGB)
plt.imsave('tmp.jpg',image_np) # Saves the image
os.replace("tmp.jpg", "web.jpg",) # Renames it for the webpage
counter += 1
print(counter)
cap.release()
Here's the HTML for the document placed in the same directory as the python file, I saved it as index.html and opened in the browser while running the python script above.
<!DOCTYPE html>
<html>
<head>
<title>Object Detection</title>
</head>
<body>
<h1>Object Detection</h1>
<p>This displays images saved during detection process</p>
<canvas id="x" width="700px" height="500px"></canvas>
<script>
var newImage = new Image();
newImage.src = "web.jpg";
var canvas = document.getElementById("x");
var context = canvas.getContext("2d");
newImage.onload = function() {
context.drawImage(newImage, 0, 0);
console.log("trigger")
setTimeout(timedRefresh, 1000);
};
function timedRefresh() {
// just change src attribute, will always trigger the onload callback
try {
newImage.src = ("web.jpg#" + new Date().getTime());
}catch(e){
console.log(e);
}
}
setTimeout(timedRefresh, 100);
</script>
</body>
</html>
It's incredibly slow, not ideal in many ways and probably breaks many good coding conventions. It was only used locally, would definitely not use this for a production environment nor recommend its use. Just needed a quick proof of concept and this worked for that.

changing name of tensorflow log in detectron2 model

I want to change the name of my tensorflow logs (for ex. events.out.tfevents.1649248617.AlienwareArea51R5.51093) to a custom name. The logs are are saved in the cfg.OUTPUT_DIR location but I cannot find where to change the name.. Should I change it somewhere in the cfg settings or is it with setup_logger()?
thank you in advance!
my current function:
'''
from detectron2.utils.logger import setup_logger
setup_logger()
from detectron2.engine.MyTrainer import MyTrainer
from detectron2.config import get_cfg
cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-Detection/faster_rcnn_R_101_FPN_3x.yaml"))
cfg.DATASETS.TRAIN = ("kernel_train_data",)
cfg.DATASETS.TEST = ("kernel_test_data",)
cfg.DATALOADER.NUM_WORKERS = 2
cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-
Detection/faster_rcnn_R_101_FPN_3x.yaml") # Let training initialize from model zoo
cfg.SOLVER.IMS_PER_BATCH = 2
cfg.SOLVER.BASE_LR = 0.00025 # pick a good LR
cfg.SOLVER.MAX_ITER = 6000 # 300 iterations seems good enough for this toy dataset; you
will need to train longer for a practical dataset
cfg.SOLVER.STEPS = [] # do not decay learning rate
cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 64 # faster, and good enough for this toy
dataset (default: 512)
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 1 # only has one class (ballon). (see https://detectron2.readthedocs.io/tutorials/datasets.html#update-the-config-for-new-datasets)
cfg.TEST.EVAL_PERIOD= 500
os.makedirs(cfg.OUTPUT_DIR, exist_ok=True)
trainer = MyTrainer(cfg)
trainer.resume_or_load(resume=False)
trainer.train()'''

How to make sure my code runs in GPU and not CPU?

I am new to deep learning and tensorflow. I have a following code. Whenever I run this code my system administrator notifies me that my code is running in CPU and not GPU even thought we have GPU in the system and I have only installed tensorflow-gpu. What changes should I make to my code so that it runs in GPU and not CPU?
import math
import tempfile
import numpy as np
from tensorflow.python.keras.layers import BatchNormalization, Conv2D, Dense, Flatten, MaxPooling2D
from tensorflow.python.keras.models import Sequential
import fastestimator as fe
from fastestimator.dataset.data import cifair10
from fastestimator.architecture.tensorflow import WideResidualNetwork
from fastestimator.op.numpyop.meta import Sometimes
from fastestimator.op.numpyop.multivariate import HorizontalFlip, PadIfNeeded, RandomCrop
from fastestimator.op.numpyop.univariate import CoarseDropout, Normalize
from fastestimator.op.tensorop.loss import CrossEntropy, SuperLoss
from fastestimator.op.tensorop.model import ModelOp, UpdateOp
from fastestimator.trace.io import BestModelSaver
from fastestimator.trace.metric import MCC, Accuracy
from fastestimator.trace.xai import LabelTracker
#training parameters
epochs = 100
batch_size = 128
max_train_steps_per_epoch = None
max_eval_steps_per_epoch = None
save_dir = tempfile.mkdtemp()
train_data, eval_data = cifair10.load_data()
test_data = eval_data.split(0.5)
def corrupt_dataset(dataset, n_classes=10, corruption_fraction=0.4):
# Keep track of which samples were corrupted for visualization later
corrupted = [0 for _ in range(len(dataset))]
# Perform the actual label corruption
n_samples_per_class = len(dataset) // n_classes # dataset size 50000
# n_classes - 100
# n_samples_per_class - 500
n_to_corrupt_per_class = math.floor(corruption_fraction * n_samples_per_class) # 200
n_corrupted = [0] * n_classes
i = 0
while any([elem < n_to_corrupt_per_class for elem in n_corrupted]): # while any class is left to be corrupted
current_class = dataset[i]['y'].item()
if n_corrupted[current_class] < n_to_corrupt_per_class: #check the number of corrupted data of a particular class has reached 200 or not
dataset[i]['y'] = (dataset[i]['y'] + np.random.randint(1, n_classes)) % n_classes # change the y value of a dataset
n_corrupted[current_class] += 1
corrupted[i] = 1
i += 1
# Put the corruption labels into the dataset for visualization
dataset['data_labels'] = np.array(corrupted, dtype=np.int).reshape((len(dataset), 1))
corrupt_dataset(train_data)
def get_wrn():
return WideResidualNetwork((32, 32, 3))
def build_estimator(loss_op):
pipeline = fe.Pipeline(train_data=train_data,
eval_data=eval_data,
test_data=test_data,
batch_size=batch_size,
ops=[Normalize(inputs="x", outputs="x", mean=(0.4914, 0.4822, 0.4465), std=(0.2471, 0.2435, 0.2616)),
PadIfNeeded(min_height=40, min_width=40, image_in="x", image_out="x", mode="train"),
RandomCrop(32, 32, image_in="x", image_out="x", mode="train"),
Sometimes(HorizontalFlip(image_in="x", image_out="x", mode="train")),
CoarseDropout(inputs="x", outputs="x", max_holes=1, mode="train"),
])
model = fe.build(model_fn=get_wrn, optimizer_fn='adam')
network = fe.Network(ops=[
ModelOp(model=model, inputs="x", outputs="y_pred"),
loss_op, # <<<----------------------------- This is where the secret sauce will go
UpdateOp(model=model, loss_name="ce")
])
traces = [
Accuracy(true_key="y", pred_key="y_pred"),
MCC(true_key="y", pred_key="y_pred"),
BestModelSaver(model=model, save_dir=save_dir, metric="mcc", save_best_mode="max", load_best_final=True),
# We will also visualize the difference between the normal and corrupted image confidence scores. You could follow this with an
# ImageViewer trace, but we will get the data out of the system summary instead later for viewing.
LabelTracker(metric="confidence", label="data_labels", label_mapping={"Normal": 0, "Corrupted": 1}, mode="train", outputs="label_confidence"),
]
estimator = fe.Estimator(pipeline=pipeline,
network=network,
epochs=epochs,
traces=traces,
train_steps_per_epoch=max_train_steps_per_epoch,
eval_steps_per_epoch=max_eval_steps_per_epoch,
log_steps=300)
return estimator
loss = SuperLoss(CrossEntropy(inputs=("y_pred", "y"), outputs="ce"), output_confidence="confidence") # The output_confidence arg is only needed if you want to visualize
estimator_super = build_estimator(loss)
superL = estimator_super.fit("SuperLoss")
print("before test")
summary = estimator_super.test()
print("after test")
print(summary.history["test"])

Opencv DNN set different Input on YoloV3

I'm using the common implementation from YoloV3 to do some inference. Which works fine using the regular in- and output.
modelWeightPath = r"./yolov3.weights"
modelPath = r"./yolov3.cfg"
network = cv2.dnn.readNetFromDarknet(modelPath,modelWeightPath)
Since we are using some edge devices which often cannot "convert" the last few layers, I m about to use the original implementation to do only the inference on the last few layers.
I know how the layers are named (network.getLayerNames()) and I know how de data from the previous layer looks like since I saved them to do the testing. (see input data -> inputScale1 from conv_81 Layer)
inputLayers = ['permute_82','permute_94','permute_106']
inputData = [cv2.UMat(inputScale1),cv2.UMat(inputScale2),cv2.UMat(inputScale3)]
Now I m not sure how I should use that knowledge to do the inference since I only get exceptions from all my attempts.
network.setInput(blob=inputData[0],name=inputLayers[0]) - throws
outs = network.forward(outputlayers[0])
throws the following exception :OpenCV(4.0.1) C:\ci\opencv-suite_1573470242804\work\modules\dnn\src\dnn.cpp:2929: error: (-204:Requested object was not found) Requested blob "permute_82" not found in function 'cv::dnn::dnn4_v20181221::Net::setInput'
network.setInputsNames(inputLayers)
network.setInput(inputData[0],name=inputLayers[0])
network.setInput(inputData[1],name=inputLayers[1])
network.setInput(inputData[2],name=inputLayers[2])
outs = network.forward() -> throws
Will throw: cv2.error: OpenCV(4.0.1) C:\ci\opencv-suite_1573470242804\work\modules\dnn\src\dnn.cpp:686: error: (-215:Assertion failed) inputs.size() == requiredOutputs in function 'cv::dnn::dnn4_v20181221::DataLayer::getMemoryShapes'
EDIT:
But the thing is, that this example works:
imgPath = r'./frame_93.png'
image = cv2.imread(imgPath);
blobInputimage = cv2.dnn.blobFromImage(image,1.0 / 255.0,(416,416),(0, 0, 0))
network.setInputsNames(['conv_0'])
network.setInput(blobInputimage,name='conv_0')
output = network.forward('conv_81')
but still you cannot do the forwarding only from the permute layer to the yolo layer.
Does someone know a solution?

So far I was able to get the same result as if I would to it by inferencing the regular network. Therefore I created per scale a "new" network from the .cfg file by removing all entries except the yolo entrie, as example yolov3_scale_1.cfg looks like:
[net]
# Testing
# batch=1
# subdivisions=1
# Training
batch=64
subdivisions=16
width=255
height=13
channels=13
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1
learning_rate=0.001
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1
[yolo]
mask = 6,7,8
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=80
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1
The code verify the output looks like:
def getOutputLayerNames(network):
layer_names = network.getLayerNames()
outputlayers=[layer_names[i[0] - 1] for i in network.getUnconnectedOutLayers()]
return outputlayers
# Load Network
modelWeightPath = r".\yolov3.weights"
modelPath_scale_1 = r".\yolov3_scale_1.cfg"
network_scale_1 = cv2.dnn.readNetFromDarknet(modelPath_scale_1,modelWeightPath)
modelPath_scale_2 = r".\yolov3_scale_2.cfg"
network_scale_2 = cv2.dnn.readNetFromDarknet(modelPath_scale_2,modelWeightPath)
modelPath_scale_3 = r".\yolov3_scale_3.cfg"
network_scale_3 = cv2.dnn.readNetFromDarknet(modelPath_scale_3,modelWeightPath)
networks = [network_scale_1,network_scale_2,network_scale_3]
outputLayers1 = getOutputLayerNames(network_scale_1)
outputLayers2 = getOutputLayerNames(network_scale_2)
outputLayers3 = getOutputLayerNames(network_scale_3)
## Read FileStorage - Network input
pathToFile = r'.\previousLayerOutput.yml'
s = cv2.FileStorage()
s.open(pathToFile, cv2.FileStorage_READ)
# Get outputs to verify behaviour
inputScale1 = s.getNode('conv_81').mat()
inputScale2 = s.getNode('conv_93').mat()
inputScale3 = s.getNode('conv_105').mat()
ouputOfYoloScale1 = s.getNode('yolo_82').mat()
ouputOfYoloScale2 = s.getNode('yolo_94').mat()
ouputOfYoloScale3 = s.getNode('yolo_106').mat()
correctOutputs = [ouputOfYoloScale1,ouputOfYoloScale2,ouputOfYoloScale3]
inputs = [inputScale1,inputScale2,inputScale3]
outputs = []
for network_with_different_scales,imageInputScaled in zip(networks,inputs):
network_with_different_scales.setInputsNames('permute_0')
network_with_different_scales.setInput(imageInputScaled)
outputs.append(network_with_different_scales.forward('yolo_0'))
strides = [32,16,8] # need to do it manually
for outputIdx,stride in zip(range(0,len(outputs)),strides):
outputs[outputIdx][:,3] = outputs[outputIdx][:,3]/stride
outputs[outputIdx][:,2] = outputs[outputIdx][:,2]/stride
for output, correctOutput in zip(outputs,correctOutputs):
print(np.array_equal(output,correctOutput))
The console output:
True
True
True

KeyError: 'data' in Caffe

While I was following the deepdream iPython notebook which is here: https://github.com/google/deepdream/blob/master/dream.ipynb, I successfully ran the code and initialized the network until i get this error:
I0218 20:53:01.108750 12174 net.cpp:283] Network initialization done.
I0218 20:53:06.017426 12174 net.cpp:816] Ignoring source layer data
I0218 20:53:06.139768 12174 net.cpp:816] Ignoring source layer loss
Traceback (most recent call last):
File "/home/andrew/PycharmProjects/deepmeme/deepmeme.py", line 122, in <module>
<IPython.core.display.Image object>
frame = deepdream(net, frame)
File "/home/andrew/PycharmProjects/deepmeme/deepmeme.py", line 78, in deepdream
octaves = [preprocess(net, base_img)]
File "/home/andrew/PycharmProjects/deepmeme/deepmeme.py", line 43, in preprocess
return np.float32(np.rollaxis(img, 2)[::-1]) - net.transformer.mean['data']
KeyError: 'data'
This is my code for the python file:
import sys
sys.path.append("/home/andrew/caffe/python")
from cStringIO import StringIO
import numpy as np
import scipy.ndimage as nd
import PIL.Image
from IPython.display import clear_output, Image, display
from google.protobuf import text_format
import caffe
# If your GPU supports CUDA and Caffe was built with CUDA support,
# uncomment the following to run Caffe operations on the GPU.
# caffe.set_mode_gpu()
# caffe.set_device(0) # select GPU device if multiple devices exist
def showarray(a, fmt='jpeg'):
a = np.uint8(np.clip(a, 0, 255))
f = StringIO()
PIL.Image.fromarray(a).save(f, fmt)
display(Image(data=f.getvalue()))
model_path = '/home/andrew/caffe/models/bvlc_reference_caffenet/' # substitute your path here
net_fn = model_path + 'deploy.prototxt'
param_fn = model_path + 'caffe_train_iter_500.caffemodel'
# Patching model to be able to compute gradients.
# Note that you can also manually add "force_backward: true" line to "deploy.prototxt".
model = caffe.io.caffe_pb2.NetParameter()
text_format.Merge(open(net_fn).read(), model)
model.force_backward = True
open('deploy.prototxt', 'w').write(str(model))
net = caffe.Classifier('/home/andrew/caffe/models/bvlc_reference_caffenet/deploy.prototxt', '/home/andrew/caffe/models/bvlc_reference_caffenet/caffenet_train_iter_500.caffemodel', caffe.TEST)
# a couple of utility functions for converting to and from Caffe's input image layout
def preprocess(net, img):
return np.float32(np.rollaxis(img, 2)[::-1]) - net.transformer.mean['data']
def deprocess(net, img):
return np.dstack((img + net.transformer.mean['data'])[::-1])
def objective_L2(dst):
dst.diff[:] = dst.data
def make_step(net, step_size=1.5, end='inception_4c/output',
jitter=32, clip=True, objective=objective_L2):
'''Basic gradient ascent step.'''
src = net.blobs['data'] # input image is stored in Net's 'data' blob
dst = net.blobs[end]
ox, oy = np.random.randint(-jitter, jitter+1, 2)
src.data[0] = np.roll(np.roll(src.data[0], ox, -1), oy, -2) # apply jitter shift
net.forward(end=end)
objective(dst) # specify the optimization objective
net.backward(start=end)
g = src.diff[0]
# apply normalized ascent step to the input image
src.data[:] += step_size/np.abs(g).mean() * g
src.data[0] = np.roll(np.roll(src.data[0], -ox, -1), -oy, -2) # unshift image
if clip:
bias = net.transformer.mean['data']
src.data[:] = np.clip(src.data, -bias, 255-bias)
def deepdream(net, base_img, iter_n=10, octave_n=4, octave_scale=1.4,
end='inception_4c/output', clip=True, **step_params):
# prepare base images for all octaves
octaves = [preprocess(net, base_img)]
for i in xrange(octave_n-1):
octaves.append(nd.zoom(octaves[-1], (1, 1.0/octave_scale,1.0/octave_scale), order=1))
src = net.blobs['data']
detail = np.zeros_like(octaves[-1]) # allocate image for network-produced details
for octave, octave_base in enumerate(octaves[::-1]):
h, w = octave_base.shape[-2:]
if octave > 0:
# upscale details from the previous octave
h1, w1 = detail.shape[-2:]
detail = nd.zoom(detail, (1, 1.0*h/h1,1.0*w/w1), order=1)
src.reshape(1,3,h,w) # resize the network's input image size
src.data[0] = octave_base+detail
for i in xrange(iter_n):
make_step(net, end=end, clip=clip, **step_params)
# visualization
vis = deprocess(net, src.data[0])
if not clip: # adjust image contrast if clipping is disabled
vis = vis*(255.0/np.percentile(vis, 99.98))
showarray(vis)
print octave, i, end, vis.shape
clear_output(wait=True)
# extract details produced on the current octave
detail = src.data[0]-octave_base
# returning the resulting image
return deprocess(net, src.data[0])
img = np.float32(PIL.Image.open('/home/andrew/caffe/examples/images/cat.jpg'))
showarray(img)
net.blobs.keys()
frame = img
frame_i = 0
h, w = frame.shape[:2]
s = 0.05 # scale coefficient
for i in xrange(100):
frame = deepdream(net, frame)
PIL.Image.fromarray(np.uint8(frame)).save("frames/%04d.jpg"%frame_i)
frame = nd.affine_transform(frame, [1-s,1-s,1], [h*s/2,w*s/2,0], order=1)
frame_i += 1
Image(filename='frames/0029.jpg')
Does anybody know what's happening? I am using my own data that I successfully trained a model with.

From the deepdream iPython notebook:
net = caffe.Classifier('tmp.prototxt', param_fn,
mean = np.float32([104.0, 116.0, 122.0]), # ImageNet mean, training set dependent
channel_swap = (2,1,0)) # the reference model has channels in BGR order instead of RGB
vs your:
net = caffe.Classifier('/home/andrew/caffe/models/bvlc_reference_caffenet/deploy.prototxt', '/home/andrew/caffe/models/bvlc_reference_caffenet/caffenet_train_iter_500.caffemodel', caffe.TEST)
You do not seem to include a mean when you create a caffe.Classifier.
See the definition of caffe.Classifier.
If you don't have a mean, you could probably just remove the mention of mean from preprocess/deprocess:
def preprocess(net, img):
return np.float32(np.rollaxis(img, 2)[::-1])
def deprocess(net, img):
return np.dstack((img)[::-1])