Hello, so i trained an object detection caffe custom model and downloaded it and i’m trying to use it in order to get the outputs using python however i ran into this error : “error: (-215:Assertion failed) pbBlob.raw_data_type() == caffe::FLOAT16 in function 'blobFromProto” a read some issues on github that need to add “store_blobs_in_old_format: true” to the solver file but the only solver file i found is with the folder jobs which it contains an already trained model
i’m using caffe20.03 from ngc
(i tried the code with a pretrained model from ModelZoo it works just fine)
this is the python code i’m running :
import numpy as np
import argparse
import cv2
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
help="path to input image")
ap.add_argument("-p", "--prototxt", required=True,
help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", required=True,
help="path to Caffe pre-trained model")
ap.add_argument("-c", "--confidence", type=float, default=0.2,
help="minimum probability to filter weak detections")
args = vars(ap.parse_args())
# initialize the list of class labels MobileNet SSD was trained to
# detect, then generate a set of bounding box colors for each class
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
"sofa", "train", "tvmonitor"]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))
# load our serialized model from disk
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])
# load the input image and construct an input blob for the image
# by resizing to a fixed 300x300 pixels and then normalizing it
# (note: normalization is done via the authors of the MobileNet SSD
# implementation)
image = cv2.imread(args["image"])
(h, w) = image.shape[:2]
blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 0.007843, (300, 300), 127.5)
# pass the blob through the network and obtain the detections and
# predictions
print("[INFO] computing object detections...")
net.setInput(blob)
detections = net.forward()
# loop over the detections
for i in np.arange(0, detections.shape[2]):
# extract the confidence (i.e., probability) associated with the
# prediction
confidence = detections[0, 0, i, 2]
# filter out weak detections by ensuring the `confidence` is
# greater than the minimum confidence
if confidence > args["confidence"]:
# extract the index of the class label from the `detections`,
# then compute the (x, y)-coordinates of the bounding box for
# the object
idx = int(detections[0, 0, i, 1])
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
# display the prediction
label = "{}: {:.2f}%".format(CLASSES[idx], confidence * 100)
print("[INFO] {}".format(label))
cv2.rectangle(image, (startX, startY), (endX, endY),
COLORS[idx], 2)
y = startY - 15 if startY - 15 > 15 else startY + 15
cv2.putText(image, label, (startX, y),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)
# show the output image
cv2.imshow("Output", image)
cv2.waitKey(0)
deploy.prototxt :
input: "data" input_shape { dim: 1 dim: 3 dim: 640 dim: 640 } layer { name: "deploy_transform" type: "Power" bottom: "data" top: "transformed_data" power_param { shift: -127.0 } } layer { name: "conv1/7x7_s2" type: "Convolution" bottom: "transformed_data" top: "conv1/7x7_s2" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 64 pad: 3 kernel_size: 7 stride: 2 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "conv1/relu_7x7" type: "ReLU" bottom: "conv1/7x7_s2" top: "conv1/7x7_s2" } layer { name: "pool1/3x3_s2" type: "Pooling" bottom: "conv1/7x7_s2" top: "pool1/3x3_s2" pooling_param { pool: MAX kernel_size: 3 stride: 2 } } layer { name: "pool1/norm1" type: "LRN" bottom: "pool1/3x3_s2" top: "pool1/norm1" lrn_param { local_size: 5 alpha: 9.99999974738e-05 beta: 0.75 } } layer { name: "conv2/3x3_reduce" type: "Convolution" bottom: "pool1/norm1" top: "conv2/3x3_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 64 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "conv2/relu_3x3_reduce" type: "ReLU" bottom: "conv2/3x3_reduce" top: "conv2/3x3_reduce" } layer { name: "conv2/3x3" type: "Convolution" bottom: "conv2/3x3_reduce" top: "conv2/3x3" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 192 pad: 1 kernel_size: 3 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "conv2/relu_3x3" type: "ReLU" bottom: "conv2/3x3" top: "conv2/3x3" } layer { name: "conv2/norm2" type: "LRN" bottom: "conv2/3x3" top: "conv2/norm2" lrn_param { local_size: 5 alpha: 9.99999974738e-05 beta: 0.75 } } layer { name: "pool2/3x3_s2" type: "Pooling" bottom: "conv2/norm2" top: "pool2/3x3_s2" pooling_param { pool: MAX kernel_size: 3 stride: 2 } } layer { name: "inception_3a/1x1" type: "Convolution" bottom: "pool2/3x3_s2" top: "inception_3a/1x1" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 64 kernel_size: 1 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_3a/relu_1x1" type: "ReLU" bottom: "inception_3a/1x1" top: "inception_3a/1x1" } layer { name: "inception_3a/3x3_reduce" type: "Convolution" bottom: "pool2/3x3_s2" top: "inception_3a/3x3_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 96 kernel_size: 1 weight_filler { type: "xavier" std: 0.0900000035763 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_3a/relu_3x3_reduce" type: "ReLU" bottom: "inception_3a/3x3_reduce" top: "inception_3a/3x3_reduce" } layer { name: "inception_3a/3x3" type: "Convolution" bottom: "inception_3a/3x3_reduce" top: "inception_3a/3x3" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 128 pad: 1 kernel_size: 3 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_3a/relu_3x3" type: "ReLU" bottom: "inception_3a/3x3" top: "inception_3a/3x3" } layer { name: "inception_3a/5x5_reduce" type: "Convolution" bottom: "pool2/3x3_s2" top: "inception_3a/5x5_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 16 kernel_size: 1 weight_filler { type: "xavier" std: 0.20000000298 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_3a/relu_5x5_reduce" type: "ReLU" bottom: "inception_3a/5x5_reduce" top: "inception_3a/5x5_reduce" } layer { name: "inception_3a/5x5" type: "Convolution" bottom: "inception_3a/5x5_reduce" top: "inception_3a/5x5" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 32 pad: 2 kernel_size: 5 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_3a/relu_5x5" type: "ReLU" bottom: "inception_3a/5x5" top: "inception_3a/5x5" } layer { name: "inception_3a/pool" type: "Pooling" bottom: "pool2/3x3_s2" top: "inception_3a/pool" pooling_param { pool: MAX kernel_size: 3 stride: 1 pad: 1 } } layer { name: "inception_3a/pool_proj" type: "Convolution" bottom: "inception_3a/pool" top: "inception_3a/pool_proj" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 32 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_3a/relu_pool_proj" type: "ReLU" bottom: "inception_3a/pool_proj" top: "inception_3a/pool_proj" } layer { name: "inception_3a/output" type: "Concat" bottom: "inception_3a/1x1" bottom: "inception_3a/3x3" bottom: "inception_3a/5x5" bottom: "inception_3a/pool_proj" top: "inception_3a/output" } layer { name: "inception_3b/1x1" type: "Convolution" bottom: "inception_3a/output" top: "inception_3b/1x1" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 128 kernel_size: 1 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_3b/relu_1x1" type: "ReLU" bottom: "inception_3b/1x1" top: "inception_3b/1x1" } layer { name: "inception_3b/3x3_reduce" type: "Convolution" bottom: "inception_3a/output" top: "inception_3b/3x3_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 128 kernel_size: 1 weight_filler { type: "xavier" std: 0.0900000035763 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_3b/relu_3x3_reduce" type: "ReLU" bottom: "inception_3b/3x3_reduce" top: "inception_3b/3x3_reduce" } layer { name: "inception_3b/3x3" type: "Convolution" bottom: "inception_3b/3x3_reduce" top: "inception_3b/3x3" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 192 pad: 1 kernel_size: 3 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_3b/relu_3x3" type: "ReLU" bottom: "inception_3b/3x3" top: "inception_3b/3x3" } layer { name: "inception_3b/5x5_reduce" type: "Convolution" bottom: "inception_3a/output" top: "inception_3b/5x5_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 32 kernel_size: 1 weight_filler { type: "xavier" std: 0.20000000298 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_3b/relu_5x5_reduce" type: "ReLU" bottom: "inception_3b/5x5_reduce" top: "inception_3b/5x5_reduce" } layer { name: "inception_3b/5x5" type: "Convolution" bottom: "inception_3b/5x5_reduce" top: "inception_3b/5x5" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 96 pad: 2 kernel_size: 5 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_3b/relu_5x5" type: "ReLU" bottom: "inception_3b/5x5" top: "inception_3b/5x5" } layer { name: "inception_3b/pool" type: "Pooling" bottom: "inception_3a/output" top: "inception_3b/pool" pooling_param { pool: MAX kernel_size: 3 stride: 1 pad: 1 } } layer { name: "inception_3b/pool_proj" type: "Convolution" bottom: "inception_3b/pool" top: "inception_3b/pool_proj" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 64 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_3b/relu_pool_proj" type: "ReLU" bottom: "inception_3b/pool_proj" top: "inception_3b/pool_proj" } layer { name: "inception_3b/output" type: "Concat" bottom: "inception_3b/1x1" bottom: "inception_3b/3x3" bottom: "inception_3b/5x5" bottom: "inception_3b/pool_proj" top: "inception_3b/output" } layer { name: "pool3/3x3_s2" type: "Pooling" bottom: "inception_3b/output" top: "pool3/3x3_s2" pooling_param { pool: MAX kernel_size: 3 stride: 2 } } layer { name: "inception_4a/1x1" type: "Convolution" bottom: "pool3/3x3_s2" top: "inception_4a/1x1" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 192 kernel_size: 1 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4a/relu_1x1" type: "ReLU" bottom: "inception_4a/1x1" top: "inception_4a/1x1" } layer { name: "inception_4a/3x3_reduce" type: "Convolution" bottom: "pool3/3x3_s2" top: "inception_4a/3x3_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 96 kernel_size: 1 weight_filler { type: "xavier" std: 0.0900000035763 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4a/relu_3x3_reduce" type: "ReLU" bottom: "inception_4a/3x3_reduce" top: "inception_4a/3x3_reduce" } layer { name: "inception_4a/3x3" type: "Convolution" bottom: "inception_4a/3x3_reduce" top: "inception_4a/3x3" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 208 pad: 1 kernel_size: 3 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4a/relu_3x3" type: "ReLU" bottom: "inception_4a/3x3" top: "inception_4a/3x3" } layer { name: "inception_4a/5x5_reduce" type: "Convolution" bottom: "pool3/3x3_s2" top: "inception_4a/5x5_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 16 kernel_size: 1 weight_filler { type: "xavier" std: 0.20000000298 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4a/relu_5x5_reduce" type: "ReLU" bottom: "inception_4a/5x5_reduce" top: "inception_4a/5x5_reduce" } layer { name: "inception_4a/5x5" type: "Convolution" bottom: "inception_4a/5x5_reduce" top: "inception_4a/5x5" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 48 pad: 2 kernel_size: 5 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4a/relu_5x5" type: "ReLU" bottom: "inception_4a/5x5" top: "inception_4a/5x5" } layer { name: "inception_4a/pool" type: "Pooling" bottom: "pool3/3x3_s2" top: "inception_4a/pool" pooling_param { pool: MAX kernel_size: 3 stride: 1 pad: 1 } } layer { name: "inception_4a/pool_proj" type: "Convolution" bottom: "inception_4a/pool" top: "inception_4a/pool_proj" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 64 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4a/relu_pool_proj" type: "ReLU" bottom: "inception_4a/pool_proj" top: "inception_4a/pool_proj" } layer { name: "inception_4a/output" type: "Concat" bottom: "inception_4a/1x1" bottom: "inception_4a/3x3" bottom: "inception_4a/5x5" bottom: "inception_4a/pool_proj" top: "inception_4a/output" } layer { name: "inception_4b/1x1" type: "Convolution" bottom: "inception_4a/output" top: "inception_4b/1x1" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 160 kernel_size: 1 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4b/relu_1x1" type: "ReLU" bottom: "inception_4b/1x1" top: "inception_4b/1x1" } layer { name: "inception_4b/3x3_reduce" type: "Convolution" bottom: "inception_4a/output" top: "inception_4b/3x3_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 112 kernel_size: 1 weight_filler { type: "xavier" std: 0.0900000035763 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4b/relu_3x3_reduce" type: "ReLU" bottom: "inception_4b/3x3_reduce" top: "inception_4b/3x3_reduce" } layer { name: "inception_4b/3x3" type: "Convolution" bottom: "inception_4b/3x3_reduce" top: "inception_4b/3x3" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 224 pad: 1 kernel_size: 3 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4b/relu_3x3" type: "ReLU" bottom: "inception_4b/3x3" top: "inception_4b/3x3" } layer { name: "inception_4b/5x5_reduce" type: "Convolution" bottom: "inception_4a/output" top: "inception_4b/5x5_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 24 kernel_size: 1 weight_filler { type: "xavier" std: 0.20000000298 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4b/relu_5x5_reduce" type: "ReLU" bottom: "inception_4b/5x5_reduce" top: "inception_4b/5x5_reduce" } layer { name: "inception_4b/5x5" type: "Convolution" bottom: "inception_4b/5x5_reduce" top: "inception_4b/5x5" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 64 pad: 2 kernel_size: 5 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4b/relu_5x5" type: "ReLU" bottom: "inception_4b/5x5" top: "inception_4b/5x5" } layer { name: "inception_4b/pool" type: "Pooling" bottom: "inception_4a/output" top: "inception_4b/pool" pooling_param { pool: MAX kernel_size: 3 stride: 1 pad: 1 } } layer { name: "inception_4b/pool_proj" type: "Convolution" bottom: "inception_4b/pool" top: "inception_4b/pool_proj" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 64 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4b/relu_pool_proj" type: "ReLU" bottom: "inception_4b/pool_proj" top: "inception_4b/pool_proj" } layer { name: "inception_4b/output" type: "Concat" bottom: "inception_4b/1x1" bottom: "inception_4b/3x3" bottom: "inception_4b/5x5" bottom: "inception_4b/pool_proj" top: "inception_4b/output" } layer { name: "inception_4c/1x1" type: "Convolution" bottom: "inception_4b/output" top: "inception_4c/1x1" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 128 kernel_size: 1 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4c/relu_1x1" type: "ReLU" bottom: "inception_4c/1x1" top: "inception_4c/1x1" } layer { name: "inception_4c/3x3_reduce" type: "Convolution" bottom: "inception_4b/output" top: "inception_4c/3x3_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 128 kernel_size: 1 weight_filler { type: "xavier" std: 0.0900000035763 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4c/relu_3x3_reduce" type: "ReLU" bottom: "inception_4c/3x3_reduce" top: "inception_4c/3x3_reduce" } layer { name: "inception_4c/3x3" type: "Convolution" bottom: "inception_4c/3x3_reduce" top: "inception_4c/3x3" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 256 pad: 1 kernel_size: 3 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4c/relu_3x3" type: "ReLU" bottom: "inception_4c/3x3" top: "inception_4c/3x3" } layer { name: "inception_4c/5x5_reduce" type: "Convolution" bottom: "inception_4b/output" top: "inception_4c/5x5_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 24 kernel_size: 1 weight_filler { type: "xavier" std: 0.20000000298 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4c/relu_5x5_reduce" type: "ReLU" bottom: "inception_4c/5x5_reduce" top: "inception_4c/5x5_reduce" } layer { name: "inception_4c/5x5" type: "Convolution" bottom: "inception_4c/5x5_reduce" top: "inception_4c/5x5" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 64 pad: 2 kernel_size: 5 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4c/relu_5x5" type: "ReLU" bottom: "inception_4c/5x5" top: "inception_4c/5x5" } layer { name: "inception_4c/pool" type: "Pooling" bottom: "inception_4b/output" top: "inception_4c/pool" pooling_param { pool: MAX kernel_size: 3 stride: 1 pad: 1 } } layer { name: "inception_4c/pool_proj" type: "Convolution" bottom: "inception_4c/pool" top: "inception_4c/pool_proj" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 64 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4c/relu_pool_proj" type: "ReLU" bottom: "inception_4c/pool_proj" top: "inception_4c/pool_proj" } layer { name: "inception_4c/output" type: "Concat" bottom: "inception_4c/1x1" bottom: "inception_4c/3x3" bottom: "inception_4c/5x5" bottom: "inception_4c/pool_proj" top: "inception_4c/output" } layer { name: "inception_4d/1x1" type: "Convolution" bottom: "inception_4c/output" top: "inception_4d/1x1" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 112 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4d/relu_1x1" type: "ReLU" bottom: "inception_4d/1x1" top: "inception_4d/1x1" } layer { name: "inception_4d/3x3_reduce" type: "Convolution" bottom: "inception_4c/output" top: "inception_4d/3x3_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 144 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4d/relu_3x3_reduce" type: "ReLU" bottom: "inception_4d/3x3_reduce" top: "inception_4d/3x3_reduce" } layer { name: "inception_4d/3x3" type: "Convolution" bottom: "inception_4d/3x3_reduce" top: "inception_4d/3x3" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 288 pad: 1 kernel_size: 3 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4d/relu_3x3" type: "ReLU" bottom: "inception_4d/3x3" top: "inception_4d/3x3" } layer { name: "inception_4d/5x5_reduce" type: "Convolution" bottom: "inception_4c/output" top: "inception_4d/5x5_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 32 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4d/relu_5x5_reduce" type: "ReLU" bottom: "inception_4d/5x5_reduce" top: "inception_4d/5x5_reduce" } layer { name: "inception_4d/5x5" type: "Convolution" bottom: "inception_4d/5x5_reduce" top: "inception_4d/5x5" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 64 pad: 2 kernel_size: 5 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4d/relu_5x5" type: "ReLU" bottom: "inception_4d/5x5" top: "inception_4d/5x5" } layer { name: "inception_4d/pool" type: "Pooling" bottom: "inception_4c/output" top: "inception_4d/pool" pooling_param { pool: MAX kernel_size: 3 stride: 1 pad: 1 } } layer { name: "inception_4d/pool_proj" type: "Convolution" bottom: "inception_4d/pool" top: "inception_4d/pool_proj" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 64 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4d/relu_pool_proj" type: "ReLU" bottom: "inception_4d/pool_proj" top: "inception_4d/pool_proj" } layer { name: "inception_4d/output" type: "Concat" bottom: "inception_4d/1x1" bottom: "inception_4d/3x3" bottom: "inception_4d/5x5" bottom: "inception_4d/pool_proj" top: "inception_4d/output" } layer { name: "inception_4e/1x1" type: "Convolution" bottom: "inception_4d/output" top: "inception_4e/1x1" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 256 kernel_size: 1 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4e/relu_1x1" type: "ReLU" bottom: "inception_4e/1x1" top: "inception_4e/1x1" } layer { name: "inception_4e/3x3_reduce" type: "Convolution" bottom: "inception_4d/output" top: "inception_4e/3x3_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 160 kernel_size: 1 weight_filler { type: "xavier" std: 0.0900000035763 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4e/relu_3x3_reduce" type: "ReLU" bottom: "inception_4e/3x3_reduce" top: "inception_4e/3x3_reduce" } layer { name: "inception_4e/3x3" type: "Convolution" bottom: "inception_4e/3x3_reduce" top: "inception_4e/3x3" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 320 pad: 1 kernel_size: 3 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4e/relu_3x3" type: "ReLU" bottom: "inception_4e/3x3" top: "inception_4e/3x3" } layer { name: "inception_4e/5x5_reduce" type: "Convolution" bottom: "inception_4d/output" top: "inception_4e/5x5_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 32 kernel_size: 1 weight_filler { type: "xavier" std: 0.20000000298 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4e/relu_5x5_reduce" type: "ReLU" bottom: "inception_4e/5x5_reduce" top: "inception_4e/5x5_reduce" } layer { name: "inception_4e/5x5" type: "Convolution" bottom: "inception_4e/5x5_reduce" top: "inception_4e/5x5" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 128 pad: 2 kernel_size: 5 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4e/relu_5x5" type: "ReLU" bottom: "inception_4e/5x5" top: "inception_4e/5x5" } layer { name: "inception_4e/pool" type: "Pooling" bottom: "inception_4d/output" top: "inception_4e/pool" pooling_param { pool: MAX kernel_size: 3 stride: 1 pad: 1 } } layer { name: "inception_4e/pool_proj" type: "Convolution" bottom: "inception_4e/pool" top: "inception_4e/pool_proj" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 128 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_4e/relu_pool_proj" type: "ReLU" bottom: "inception_4e/pool_proj" top: "inception_4e/pool_proj" } layer { name: "inception_4e/output" type: "Concat" bottom: "inception_4e/1x1" bottom: "inception_4e/3x3" bottom: "inception_4e/5x5" bottom: "inception_4e/pool_proj" top: "inception_4e/output" } layer { name: "inception_5a/1x1" type: "Convolution" bottom: "inception_4e/output" top: "inception_5a/1x1" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 256 kernel_size: 1 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_5a/relu_1x1" type: "ReLU" bottom: "inception_5a/1x1" top: "inception_5a/1x1" } layer { name: "inception_5a/3x3_reduce" type: "Convolution" bottom: "inception_4e/output" top: "inception_5a/3x3_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 160 kernel_size: 1 weight_filler { type: "xavier" std: 0.0900000035763 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_5a/relu_3x3_reduce" type: "ReLU" bottom: "inception_5a/3x3_reduce" top: "inception_5a/3x3_reduce" } layer { name: "inception_5a/3x3" type: "Convolution" bottom: "inception_5a/3x3_reduce" top: "inception_5a/3x3" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 320 pad: 1 kernel_size: 3 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_5a/relu_3x3" type: "ReLU" bottom: "inception_5a/3x3" top: "inception_5a/3x3" } layer { name: "inception_5a/5x5_reduce" type: "Convolution" bottom: "inception_4e/output" top: "inception_5a/5x5_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 32 kernel_size: 1 weight_filler { type: "xavier" std: 0.20000000298 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_5a/relu_5x5_reduce" type: "ReLU" bottom: "inception_5a/5x5_reduce" top: "inception_5a/5x5_reduce" } layer { name: "inception_5a/5x5" type: "Convolution" bottom: "inception_5a/5x5_reduce" top: "inception_5a/5x5" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 128 pad: 2 kernel_size: 5 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_5a/relu_5x5" type: "ReLU" bottom: "inception_5a/5x5" top: "inception_5a/5x5" } layer { name: "inception_5a/pool" type: "Pooling" bottom: "inception_4e/output" top: "inception_5a/pool" pooling_param { pool: MAX kernel_size: 3 stride: 1 pad: 1 } } layer { name: "inception_5a/pool_proj" type: "Convolution" bottom: "inception_5a/pool" top: "inception_5a/pool_proj" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 128 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_5a/relu_pool_proj" type: "ReLU" bottom: "inception_5a/pool_proj" top: "inception_5a/pool_proj" } layer { name: "inception_5a/output" type: "Concat" bottom: "inception_5a/1x1" bottom: "inception_5a/3x3" bottom: "inception_5a/5x5" bottom: "inception_5a/pool_proj" top: "inception_5a/output" } layer { name: "inception_5b/1x1" type: "Convolution" bottom: "inception_5a/output" top: "inception_5b/1x1" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 384 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_5b/relu_1x1" type: "ReLU" bottom: "inception_5b/1x1" top: "inception_5b/1x1" } layer { name: "inception_5b/3x3_reduce" type: "Convolution" bottom: "inception_5a/output" top: "inception_5b/3x3_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 1.0 decay_mult: 0.0 } convolution_param { num_output: 192 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_5b/relu_3x3_reduce" type: "ReLU" bottom: "inception_5b/3x3_reduce" top: "inception_5b/3x3_reduce" } layer { name: "inception_5b/3x3" type: "Convolution" bottom: "inception_5b/3x3_reduce" top: "inception_5b/3x3" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 384 pad: 1 kernel_size: 3 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_5b/relu_3x3" type: "ReLU" bottom: "inception_5b/3x3" top: "inception_5b/3x3" } layer { name: "inception_5b/5x5_reduce" type: "Convolution" bottom: "inception_5a/output" top: "inception_5b/5x5_reduce" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 48 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_5b/relu_5x5_reduce" type: "ReLU" bottom: "inception_5b/5x5_reduce" top: "inception_5b/5x5_reduce" } layer { name: "inception_5b/5x5" type: "Convolution" bottom: "inception_5b/5x5_reduce" top: "inception_5b/5x5" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 128 pad: 2 kernel_size: 5 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_5b/relu_5x5" type: "ReLU" bottom: "inception_5b/5x5" top: "inception_5b/5x5" } layer { name: "inception_5b/pool" type: "Pooling" bottom: "inception_5a/output" top: "inception_5b/pool" pooling_param { pool: MAX kernel_size: 3 stride: 1 pad: 1 } } layer { name: "inception_5b/pool_proj" type: "Convolution" bottom: "inception_5b/pool" top: "inception_5b/pool_proj" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 128 kernel_size: 1 weight_filler { type: "xavier" std: 0.10000000149 } bias_filler { type: "constant" value: 0.20000000298 } } } layer { name: "inception_5b/relu_pool_proj" type: "ReLU" bottom: "inception_5b/pool_proj" top: "inception_5b/pool_proj" } layer { name: "inception_5b/output" type: "Concat" bottom: "inception_5b/1x1" bottom: "inception_5b/3x3" bottom: "inception_5b/5x5" bottom: "inception_5b/pool_proj" top: "inception_5b/output" } layer { name: "pool5/drop_s1" type: "Dropout" bottom: "inception_5b/output" top: "pool5/drop_s1" dropout_param { dropout_ratio: 0.40000000596 } } layer { name: "cvg/classifier" type: "Convolution" bottom: "pool5/drop_s1" top: "cvg/classifier" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 1 kernel_size: 1 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.0 } } } layer { name: "coverage/sig" type: "Sigmoid" bottom: "cvg/classifier" top: "coverage" } layer { name: "bbox/regressor" type: "Convolution" bottom: "pool5/drop_s1" top: "bboxes" param { lr_mult: 1.0 decay_mult: 1.0 } param { lr_mult: 2.0 decay_mult: 0.0 } convolution_param { num_output: 4 kernel_size: 1 weight_filler { type: "xavier" std: 0.0299999993294 } bias_filler { type: "constant" value: 0.0 } } } layer { name: "cluster" type: "Python" bottom: "coverage" bottom: "bboxes" top: "bbox-list" python_param { module: "caffe.layers.detectnet.clustering" layer: "ClusterDetections" param_str: "640, 640, 16, 0.6, 2, 0.02, 22, 1" } }
solver.prototxt:
test_iter: 28
test_interval: 10
base_lr: 9.99999974738e-05
display: 1
max_iter: 300
lr_policy: “step”
gamma: 0.10000000149
momentum: 0.899999976158
weight_decay: 9.99999997475e-07
stepsize: 99
snapshot: 10
snapshot_prefix: “snapshot”
solver_mode: GPU
net: “train_val.prototxt”
solver_type: ADAM