def predict(self):
print('---->predicting ', self.conf.test_epoch)
if self.conf.test_epoch > 0:
self.reload(self.conf.test_epoch)
else:
print("please set a reasonable test_epoch")
return
test_reader = H5DataLoader(
self.conf.data_dir+self.conf.test_data, False)
self.sess.run(tf.local_variables_initializer())
predictions = []
losses = []
accuracies = []
m_ious = []
count=0
while True:
inputs, annotations = test_reader.next_batch(self.conf.batch)
if inputs.shape[0] < self.conf.batch:
break
feed_dict = {self.inputs: inputs, self.annotations: annotations}
loss, accuracy, m_iou, _ = self.sess.run(
[self.loss_op, self.accuracy_op, self.m_iou, self.miou_op],
feed_dict=feed_dict)
print('values----->', loss, accuracy, m_iou)
losses.append(loss)
accuracies.append(accuracy)
m_ious.append(m_iou)
predictions.append(self.sess.run(
self.decoded_predictions, feed_dict=feed_dict))
print('----->saving predictions')
for index, prediction in enumerate(predictions):
for i in range(prediction.shape[0]):
imsave(prediction[i], self.conf.sample_dir +
str(index*prediction.shape[0]+i)+'.png')
return np.mean(losses),np.mean(accuracies),m_ious[-1]
def predict(self):
print('---->predicting ', self.conf.test_epoch)
if self.conf.test_epoch > 0:
self.reload(self.conf.test_epoch)
else:
print("please set a reasonable test_epoch")
return
# 读取数据
test_reader = H5DataLoader(self.conf.data_dir + self.conf.test_data,
False)
self.sess.run(tf.local_variables_initializer())
predictions = []
losses = []
accuracies = []
m_ious = []
while True:
inputs, annotations = test_reader.next_batch(self.conf.batch)
# 终止条件
if inputs.shape[0] < self.conf.batch:
break
feed_dict = {self.inputs: inputs, self.annotations: annotations}
loss, accuracy, m_iou, _ = self.sess.run(
[self.loss_op, self.accuracy_op, self.m_iou, self.miou_op],
feed_dict=feed_dict)
print('values----->', loss, accuracy, m_iou)
# 记录指标
losses.append(loss)
accuracies.append(accuracy)
m_ious.append(m_iou)
# 记录预测值
predictions.append(
self.sess.run(self.decoded_predictions, feed_dict=feed_dict))
print('----->saving predictions')
print(np.shape(predictions))
num = 0
for index, prediction in enumerate(predictions):
# 下面的程序用于输出一通道的预测值，测试时需要观察的
#print(prediction.shape)
#print(index)
#np.save("pred",np.array(prediction))
# 把一通道的预测值保存为三通道图片，这是自己写的函数
for i in range(prediction.shape[0]):
np.save(self.conf.sample_dir + "pred" + str(num) + ".npy",
prediction[i])
num += 1
imsave(
prediction[i], self.conf.sample_dir +
str(index * prediction.shape[0] + i) + '.png')
# 验证和测试的时候，指标都是返回的全体上的均值
return np.mean(losses), np.mean(accuracies), m_ious[-1]
def save_labelme_datav1(file_path,
image_path,
image_data,
annotations_list,
label_to_text=lambda x: str(x)):
wmli.imsave(image_path, image_data)
image = {"width": image_data.shape[1], "height": image_data.shape[0]}
save_labelme_data(file_path, image_path, image, annotations_list,
label_to_text)
def predict(self):
self.reload(self.conf.test_epoch)
test_reader = H5DataLoader(self.conf.data_dir + self.conf.test_data,
False)
self.sess.run(tf.local_variables_initializer())
predictions = []
net_predictions = []
losses = []
dices = []
accuracies = []
count = 0
while True:
inputs, annotations = test_reader.next_batch(self.conf.batchsize)
if inputs.shape[0] < self.conf.batch:
break
feed_dict = {
self.inputs: inputs,
self.annotations: annotations,
self.is_train: False
}
predictions.append(
self.sess.run(
self.predictions,
feed_dict=feed_dict)) # <-------decoded_predictions
net_predictions.append(
self.sess.run(self.decoded_net_pred, feed_dict=feed_dict))
count += 1
if count == self.conf.test_num:
break
num = 0
for index, prediction in enumerate(net_predictions):
for i in range(prediction.shape[0]):
num += 1
imsave(
prediction[i], self.conf.sample_net_dir +
str(index * prediction.shape[0] + i) + '.png')
return np.mean(losses), np.mean(accuracies), np.mean(dices)
def predict(self):
print('---->predicting ', self.conf.test_epoch)
if self.conf.test_epoch > 0:
self.reload(self.conf.test_epoch)
else:
print("please set a reasonable test_epoch")
return
test_reader = H5DataLoader(
self.conf.data_dir+self.conf.test_data, False)
predictions = []
while True:
inputs, annotations = test_reader.next_batch(self.conf.batch)
if inputs.shape[0] < self.conf.batch:
break
feed_dict = {self.inputs: inputs, self.annotations: annotations}
predictions.append(self.sess.run(
self.decoded_predictions, feed_dict=feed_dict))
print('----->saving predictions')
for index, prediction in enumerate(predictions):
for i in range(prediction.shape[0]):
imsave(prediction[i], self.conf.sample_dir +
str(index*prediction.shape[0]+i)+'.png')
def _evaluate_denoise(sr_model : BaseSuperResolutionModel, validation_dir, scale_pred=False):
print("Validating %s model" % sr_model.model_name)
predict_path = "val_predict/"
if not os.path.exists(predict_path):
os.makedirs(predict_path)
validation_path_set5 = validation_dir + "set5/"
validation_path_set14 = validation_dir + "set14/"
validation_dirs = [validation_path_set5, validation_path_set14]
for val_dir in validation_dirs:
image_fns = [name for name in os.listdir(val_dir)]
nb_images = len(image_fns)
print("Validating %d images from path %s" % (nb_images, val_dir))
total_psnr = 0.0
for impath in os.listdir(val_dir):
t1 = time.time()
# Input image
y = img_utils.imread(val_dir + impath, mode='RGB')
width, height, _ = y.shape
if ((width // sr_model.scale_factor) % 4 != 0) or ((height // sr_model.scale_factor) % 4 != 0) \
or (width % 2 != 0) or (height % 2 != 0):
width = ((width // sr_model.scale_factor) // 4) * 4 * sr_model.scale_factor
height = ((height // sr_model.scale_factor) // 4) * 4 * sr_model.scale_factor
print("Model %s require the image size to be divisible by 4. New image size = (%d, %d)" % \
(sr_model.model_name, width, height))
y = img_utils.imresize(y, (width, height), interp='bicubic')
y = y.astype('float32')
y = np.expand_dims(y, axis=0)
x_temp = y.copy()
if sr_model.type_scale_type == "tanh":
x_temp = (x_temp - 127.5) / 127.5
y = (y - 127.5) / 127.5
else:
x_temp /= 255.
y /= 255.
img = img_utils.imresize(x_temp[0], (width // sr_model.scale_factor, height // sr_model.scale_factor),
interp='bicubic', mode='RGB')
if not sr_model.type_true_upscaling:
img = img_utils.imresize(img, (width, height), interp='bicubic')
x = np.expand_dims(img, axis=0)
if K.image_dim_ordering() == "th":
x = x.transpose((0, 3, 1, 2))
y = y.transpose((0, 3, 1, 2))
sr_model.model = sr_model.create_model(height, width, load_weights=True)
if sr_model.evaluation_func is None:
if sr_model.uses_learning_phase:
sr_model.evaluation_func = K.function([sr_model.model.layers[0].input, K.learning_phase()],
[sr_model.model.layers[-1].output])
else:
sr_model.evaluation_func = K.function([sr_model.model.layers[0].input],
[sr_model.model.layers[-1].output])
if sr_model.uses_learning_phase:
y_pred = sr_model.evaluation_func([x, 0])[0][0]
else:
y_pred = sr_model.evaluation_func([x])[0][0]
if scale_pred:
if sr_model.type_scale_type == "tanh":
y_pred = (y_pred + 1) * 127.5
else:
y_pred *= 255.
if sr_model.type_scale_type == 'tanh':
y = (y + 1) / 2
psnr_val = psnr(y[0], np.clip(y_pred, 0, 255) / 255)
total_psnr += psnr_val
t2 = time.time()
print("Validated image : %s, Time required : %0.2f, PSNR value : %0.4f" % (impath, t2 - t1, psnr_val))
generated_path = predict_path + "%s_%s_generated.png" % (sr_model.model_name, os.path.splitext(impath)[0])
if K.image_dim_ordering() == "th":
y_pred = y_pred.transpose((1, 2, 0))
y_pred = np.clip(y_pred, 0, 255).astype('uint8')
img_utils.imsave(generated_path, y_pred)
print("Average PRNS value of validation images = %00.4f \n" % (total_psnr / nb_images))
def evaluate(self,
validation_dir,
scale_factor,
target_size=256,
small_train_images=False):
"""
Evaluates the model on the Set5 Validation images
"""
if self.model == None:
self.create_model(load_weights=True,
small_train_images=small_train_images)
if self.evaluation_func is None:
self.evaluation_func = K.function([self.model.layers[0].input],
[self.model.layers[-1].output])
predict_path = "val_predict/"
if not os.path.exists(predict_path):
os.makedirs(predict_path)
image_fns = [name for name in os.listdir(validation_dir)]
nb_images = len(image_fns)
print("Validating %d images" % (nb_images))
total_psnr = 0.0
for impath in os.listdir(validation_dir):
t1 = time.time()
# Input image
y = img_utils.imread(validation_dir + impath, mode='RGB')
width, height, _ = y.shape
if self.model_name in self.denoise_models:
# Denoise models require precise width and height, divisible by 4
if ((width // scale_factor) % 4 != 0) or (
(height // scale_factor) % 4 != 0):
width = ((width // scale_factor) // 4) * 4 * scale_factor
height = ((height // scale_factor) // 4) * 4 * scale_factor
print("Model %s require the image size to be divisible by 4. New image size = (%d, %d)" % \
(self.model_name, width, height))
y = img_utils.imresize(y, (width, height),
interp='bicubic')
y = y.astype('float32') / 255.
y = np.expand_dims(y, axis=0)
x_width = width if not small_train_images else width // scale_factor
x_height = height if not small_train_images else height // scale_factor
x_temp = y.copy()
img = img_utils.gaussian_filter(x_temp[0], sigma=0.01)
img = img_utils.imresize(
img, (x_width // scale_factor, x_height // scale_factor),
interp='bicubic')
if not small_train_images:
img = img_utils.imresize(img, (x_width, x_height),
interp='bicubic')
x = np.expand_dims(img, axis=0)
if K.image_dim_ordering() == "th":
x = x.transpose((0, 3, 1, 2))
y = y.transpose((0, 3, 1, 2))
y_pred = self.evaluation_func([x])[0][0]
psnr_val = psnr(y[0], np.clip(y_pred, 0, 255) / 255)
total_psnr += psnr_val
t2 = time.time()
print(
"Validated image : %s, Time required : %0.2f, PSNR value : %0.4f"
% (impath, t2 - t1, psnr_val))
generated_path = predict_path + "%s_generated.png" % (
os.path.splitext(impath)[0])
if K.image_dim_ordering() == "th":
y_pred = y_pred.transpose((1, 2, 0))
y_pred = np.clip(y_pred, 0, 255).astype('uint8')
img_utils.imsave(generated_path, y_pred)
print("Average PRNS value of validation images = %00.4f" %
(total_psnr / nb_images))
help="path to test data dir")
parser.add_argument("--save_dir",
default="/2_data/wj/mldata/coco/coco_results",
type=str,
help="path to save data dir")
return parser
if __name__ == "__main__":
args = default_argument_parser().parse_args()
save_path = args.save_dir
dataset = PascalVOCData()
# data_path0 = get_data_dir2("annotationed_data/verify_p03_1020_1_proc_m")
data_path = args.test_dir
if not dataset.read_data(data_path):
exit(0)
wmlu.create_empty_dir(save_path, remove_if_exists=True, yes_to_all=True)
for data in dataset.get_items():
full_path, shape, category_ids, category_names, boxes, binary_masks, area, is_crowd, num_annotations_skipped = data
print(f"Process {full_path}")
img = wmli.imread(full_path)
base_name = wmlu.base_name(full_path) + "_a.jpg"
save_file_path = os.path.join(save_path, base_name)
img = odv.draw_bboxes(img,
classes=category_names,
bboxes=boxes,
show_text=True,
text_color=(255., 0., 0.))
wmli.imsave(save_file_path, img)
def evaluate(self, validation_dir, scale_factor, target_size=256, small_train_images=False):
"""
Evaluates the model on the Set5 Validation images
"""
if self.model == None: self.create_model(load_weights=True, small_train_images=small_train_images)
if self.evaluation_func is None:
self.evaluation_func = K.function([self.model.layers[0].input],
[self.model.layers[-1].output])
predict_path = "val_predict/"
if not os.path.exists(predict_path):
os.makedirs(predict_path)
image_fns = [name for name in os.listdir(validation_dir)]
nb_images = len(image_fns)
print("Validating %d images" % (nb_images))
total_psnr = 0.0
for impath in os.listdir(validation_dir):
t1 = time.time()
# Input image
y = img_utils.imread(validation_dir + impath, mode='RGB')
width, height, _ = y.shape
if self.model_name in self.denoise_models:
# Denoise models require precise width and height, divisible by 4
if ((width // scale_factor) % 4 != 0) or ((height // scale_factor) % 4 != 0):
width = ((width // scale_factor) // 4) * 4 * scale_factor
height = ((height // scale_factor) // 4) * 4 * scale_factor
print("Model %s require the image size to be divisible by 4. New image size = (%d, %d)" % \
(self.model_name, width, height))
y = img_utils.imresize(y, (width, height), interp='bicubic')
y = y.astype('float32') / 255.
y = np.expand_dims(y, axis=0)
x_width = width if not small_train_images else width // scale_factor
x_height = height if not small_train_images else height // scale_factor
x_temp = y.copy()
img = img_utils.gaussian_filter(x_temp[0], sigma=0.01)
img = img_utils.imresize(img, (x_width // scale_factor, x_height // scale_factor), interp='bicubic')
if not small_train_images:
img = img_utils.imresize(img, (x_width, x_height), interp='bicubic')
x = np.expand_dims(img, axis=0)
if K.image_dim_ordering() == "th":
x = x.transpose((0, 3, 1, 2))
y = y.transpose((0, 3, 1, 2))
y_pred = self.evaluation_func([x])[0][0]
psnr_val = psnr(y[0], np.clip(y_pred, 0, 255) / 255)
total_psnr += psnr_val
t2 = time.time()
print("Validated image : %s, Time required : %0.2f, PSNR value : %0.4f" % (impath, t2 - t1, psnr_val))
generated_path = predict_path + "%s_generated.png" % (os.path.splitext(impath)[0])
if K.image_dim_ordering() == "th":
y_pred = y_pred.transpose((1, 2, 0))
y_pred = np.clip(y_pred, 0, 255).astype('uint8')
img_utils.imsave(generated_path, y_pred)
print("Average PRNS value of validation images = %00.4f" % (total_psnr / nb_images))
def predict(self):
print('---->predicting ', self.conf.test_epoch)
if self.conf.test_epoch > 0:
self.reload(self.conf.test_epoch)
else:
print("please set a reasonable test_epoch")
return
test_reader = H5DataLoader(self.conf.data_dir + self.conf.test_data,
False)
self.sess.run(tf.local_variables_initializer())
predictions = []
net_predictions = []
outputs = []
probabilitys = []
losses = []
accuracies = []
m_ious = []
rate_list = []
befores = []
afters = []
maps = []
start_maps = []
count = 0
while True:
inputs, annotations = test_reader.next_batch(self.conf.batchsize)
if inputs.shape[0] < self.conf.batch:
break
feed_dict = {
self.inputs: inputs,
self.annotations: annotations,
self.is_train: False
}
loss, accuracy, m_iou, _ = self.sess.run(
[self.loss_op, self.accuracy_op, self.m_iou, self.miou_op],
feed_dict=feed_dict)
print('values----->', loss, accuracy, m_iou)
losses.append(loss)
accuracies.append(accuracy)
m_ious.append(m_iou)
predictions.append(
self.sess.run(self.decoded_predictions, feed_dict=feed_dict))
net_predictions.append(
self.sess.run(self.decoded_net_pred, feed_dict=feed_dict))
outputs.append(self.sess.run(self.outputs, feed_dict=feed_dict))
count += 1
if count == self.conf.test_num:
break
print('----->saving outputs')
print(np.shape(probabilitys))
np.save(self.conf.sample_dir + "outputs" + ".npy", np.array(outputs))
print('----->saving predictions')
print(np.shape(predictions))
num = 0
for index, prediction in enumerate(predictions):
for i in range(prediction.shape[0]):
np.save(self.conf.sample_dir + "pred" + str(num) + ".npy",
prediction[i])
num += 1
imsave(
prediction[i], self.conf.sample_dir +
str(index * prediction.shape[0] + i) + '.png')
print('----->saving net_predictions')
print(np.shape(net_predictions))
num = 0
for index, prediction in enumerate(net_predictions):
for i in range(prediction.shape[0]):
np.save(self.conf.sample_dir + "netpred" + str(num) + ".npy",
prediction[i])
num += 1
imsave(
prediction[i], self.conf.sample_dir +
str(index * prediction.shape[0] + i) + 'net.png')
return np.mean(losses), np.mean(accuracies), m_ious[-1]
def evaluate(self, validation_dir, small_train_images=False):
print("Validating %s model" % self.model_name)
predict_path = "val_predict/"
if not os.path.exists(predict_path):
os.makedirs(predict_path)
validation_path_set5 = validation_dir + "set5/"
validation_path_set14 = validation_dir + "set14/"
validation_dirs = [validation_path_set5, validation_path_set14]
for val_dir in validation_dirs:
image_fns = [name for name in os.listdir(val_dir)]
nb_images = len(image_fns)
print("Validating %d images from path %s" % (nb_images, val_dir))
total_psnr = 0.0
for impath in os.listdir(val_dir):
t1 = time.time()
# Input image
y = img_utils.imread(val_dir + impath, mode='RGB')
width, height, _ = y.shape
y = y.astype('float32') / 255.
y = np.expand_dims(y, axis=0)
x_temp = y.copy()
img = img_utils.imresize(
x_temp[0],
(width // self.scale_factor, height // self.scale_factor),
interp='bicubic')
if not small_train_images:
img = img_utils.imresize(img, (width, height),
interp='bicubic')
x = np.expand_dims(img, axis=0)
if K.image_dim_ordering() == "th":
x = x.transpose((0, 3, 1, 2))
y = y.transpose((0, 3, 1, 2))
self.model = self.create_model(height,
width,
load_weights=True)
self.evaluation_func = K.function(
[self.model.layers[0].input],
[self.model.layers[-1].output])
y_pred = self.evaluation_func([x])[0][0]
psnr_val = psnr(y[0], np.clip(y_pred, 0, 255) / 255)
total_psnr += psnr_val
t2 = time.time()
print(
"Validated image : %s, Time required : %0.2f, PSNR value : %0.4f"
% (impath, t2 - t1, psnr_val))
generated_path = predict_path + "%s_%s_generated.png" % (
self.model_name, os.path.splitext(impath)[0])
if K.image_dim_ordering() == "th":
y_pred = y_pred.transpose((1, 2, 0))
y_pred = np.clip(y_pred, 0, 255).astype('uint8')
img_utils.imsave(generated_path, y_pred)
print("Average PRNS value of validation images = %00.4f \n" %
(total_psnr / nb_images))
