def classify_panda(model, image_shape):
rgb_panda_image = imread(panda_path)
if show_image:
bgr_panda_image = cv2.cvtColor(rgb_panda_image, cv2.COLOR_RGB2BGR)
cv2.imshow('panda_image', bgr_panda_image)
# preprocess input
cropped_rgb_panda_image = center_crop_and_resize(rgb_panda_image,
image_size=image_shape)
if show_image:
cropped_bgr_panda_image = cv2.cvtColor(
cropped_rgb_panda_image.astype('uint8'), cv2.COLOR_RGB2BGR)
cv2.imshow('cropped_panda_image', cropped_bgr_panda_image)
preprocessed_rgb_panda_image = preprocess_input(cropped_rgb_panda_image)
batch = np.expand_dims(preprocessed_rgb_panda_image, 0)
# make prediction and decode
predictions = model.predict(batch)
xprint(decode_predictions(predictions))
if show_image:
while cv2_window_open('panda_image') and cv2_window_open(
'cropped_panda_image'):
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cv2.destroyAllWindows()
def get_frame_batches(video, image_shape, desired_batch_size):
video_w = int(video.get(cv2.CAP_PROP_FRAME_WIDTH))
video_h = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))
frame_rate = video.get(cv2.CAP_PROP_FPS)
if (
video_w, video_h
) not in expected_video_resolutions or frame_rate not in expected_frame_rates:
xprint("Resolution: {}x{}".format(video_w, video_h))
xprint("Frame rate:", frame_rate)
raise Exception("Unexpected video property detected")
frame_idx = 0
batch = []
while True:
ret, bgr_frame = video.read()
if not ret:
break
else:
if show_image and frame_idx % frame_display_stride == 0:
image_scale = 0.5
new_width, new_height = bgr_frame.shape[
1] * image_scale, bgr_frame.shape[0] * image_scale
resized_bgr_frame = cv2.resize(
bgr_frame, (int(new_width), int(new_height)))
cv2.imshow('frame', resized_bgr_frame)
cropped_bgr_frame = center_crop_and_resize(
bgr_frame, image_size=image_shape, crop_padding=crop_padding)
if show_image:
cv2.imshow('cropped_frame', cropped_bgr_frame.astype('uint8'))
cropped_rgb_frame = cv2.cvtColor(cropped_bgr_frame.astype('uint8'),
cv2.COLOR_BGR2RGB)
batch.append(preprocess_input(cropped_rgb_frame))
if show_image:
if cv2.waitKey(1) & 0xFF == ord('q'):
raise Exception("q key pressed during video processing")
if not (cv2_window_open('frame')
and cv2_window_open('cropped_frame')):
raise Exception("Window closed during video processing")
if len(batch) == desired_batch_size:
yield np.asarray(batch)
batch = []
frame_idx += 1
if len(batch) > 0:
yield np.asarray(batch)
cv2.destroyAllWindows()
def test_webcams(model, image_shape):
for cam_idx in itertools.count():
cap = cv2.VideoCapture(cam_idx + cam_api_reference)
if not cap.isOpened():
break
ret, bgr_frame = cap.read()
xprint("Cam {} image shape: {}".format(cam_idx, bgr_frame.shape))
while True:
ret, bgr_frame = cap.read()
cv2.imshow('frame', bgr_frame)
# Use neural network
cam_batch_size = 1
verbose = False
# print("model.input_shape:", model.input_shape)
# input_size = model.input_shape[2]
cropped_bgr_frame = center_crop_and_resize(bgr_frame,
image_size=image_shape)
cv2.imshow('cropped_frame', cropped_bgr_frame.astype('uint8'))
xprint("cropped_bgr_frame.shape:", cropped_bgr_frame.shape)
cropped_rgb_frame = cv2.cvtColor(cropped_bgr_frame.astype('uint8'),
cv2.COLOR_BGR2RGB)
batch = preprocess_input(
cropped_rgb_frame.reshape((-1, ) + cropped_rgb_frame.shape))
prediction = model.predict(batch,
batch_size=cam_batch_size,
verbose=verbose)
if use_original_classifier:
for decoded_frame_prediction in decode_predictions(prediction):
xprint(decoded_frame_prediction)
else:
if not isinstance(prediction, list):
prediction = [prediction]
print()
for output_head in prediction:
for frame_output in output_head:
print(frame_output.shape, frame_output)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
if not (cv2_window_open('frame')
and cv2_window_open('cropped_frame')):
break
cap.release()
cv2.destroyAllWindows()
def save_examples(ds_info, ds, num_examples=10, folder=".", image_key=None):
"""Save images from an image classification dataset.
Only works with datasets that have 1 image feature and optionally 1 label
feature (both inferred from `ds_info`). Note the dataset should be unbatched.
Usage:
```python
ds, ds_info = tfds.load('cifar10', split='train', with_info=True)
fig = save_examples(ds_info, ds)
```
Args:
ds_info: The dataset info object to which extract the label and features
info. Available either through `tfds.load('mnist', with_info=True)` or
`tfds.builder('mnist').info`
ds: `tf.data.Dataset`. The tf.data.Dataset object to visualize. Examples
should not be batched.
num_examples: `int`. Number of examples to save
folder: `str`. Where to save images
image_key: `string`, name of the feature that contains the image. If not
set, the system will try to auto-detect it.
Returns:
"""
if not image_key:
# Infer the image and label keys
image_keys = [
k for k, feature in ds_info.features.items()
if isinstance(feature, features_lib.Image)
]
if not image_keys:
raise ValueError(
"Visualisation not supported for dataset `{}`. Was not able to "
"auto-infer image.".format(ds_info.name))
if len(image_keys) > 1:
raise ValueError(
"Multiple image features detected in the dataset. Using the first one. You can "
"use `image_key` argument to override. Images detected: %s" %
(",".join(image_keys)))
image_key = image_keys[0]
label_keys = [
k for k, feature in ds_info.features.items()
if isinstance(feature, features_lib.ClassLabel)
]
label_key = label_keys[0] if len(label_keys) == 1 else None
if not label_key:
logging.info("Was not able to auto-infer label.")
examples = list(dataset_utils.as_numpy(ds.take(num_examples)))
for i, ex in enumerate(examples):
if not isinstance(ex, dict):
raise ValueError(
"tfds.show_examples requires examples as `dict`, with the same "
"structure as `ds_info.features`. It is currently not compatible "
"with `as_supervised=True`. Received: {}".format(type(ex)))
# Plot the image
image = ex[image_key]
if len(image.shape) != 3:
raise ValueError(
"Image dimension should be 3. tfds.show_examples does not support "
"batched examples or video.")
_, _, c = image.shape
if c == 1:
image = image.reshape(image.shape[:2])
image = center_crop_and_resize(image, 224).astype(np.uint8)
im = Image.fromarray(image)
if label_key:
label = ex[label_key]
label_str = ds_info.features[label_key].int2str(label).replace(
"/", "_")
else:
label_str = ""
im.save(f"{folder}/image_{label_str}_{i}.jpeg")
import os
import numpy as np
import efficientnet.tfkeras as efn
from tensorflow.keras.applications.imagenet_utils import decode_predictions, preprocess_input
from efficientnet.preprocessing import center_crop_and_resize
from skimage.io import imread
model = efn.EfficientNetB0(weights='imagenet')
with open('./label.txt', 'r') as f:
text_labels = [''.join(l.split("'")[1]) for l in f]
image_list = os.listdir('./samples')
for image_name in image_list:
image_path = os.path.join('./samples', image_name)
print(image_path)
image = imread(image_path)
image_size = model.input_shape[1]
x = center_crop_and_resize(image, image_size=image_size)
x = preprocess_input(x, mode='torch')
inputs = np.expand_dims(x, 0)
expected = model.predict(inputs)
result = decode_predictions(expected, top=1)
print('With prob = %.2f, it contains %s' % (
result[0][0][2] * 100, result[0][0][1]))