Yolo-v3 tiny *.weights file contains less weights then expectedKeras model.to_json() error: 'rawunicodeescape' codec can't decode bytes in position 94-98: truncated uXXXXGetting predictions after training using darknetInvalidArgumentError with Keras and WGANsKeras and tensorflow concatenation and fitting errorOpenCV Yolo V3 tinyToo many parameters trying to rebuild VGG16layer mismatch in custom layer attention networkWhy replacing max pool by average pool using Keras APIs fails?Loss of CNN in Keras becomes nan at some point of training
How to take the beginning and end parts of a list with simpler syntax?
Does fossil fuels use since 1990 account for half of all the fossil fuels used in history?
My cat is a houdini
Submitting a new paper just after another was accepted by the same journal
Heating Margarine in Pan = loss of calories?
Simplification of numbers
Is there a way to encourage or even force airlines and booking engines to show options with overnight layovers?
Are 变 and 変 the same?
A continuous water "planet" ring around a star
Are differences between uniformly distributed numbers uniformly distributed?
An equality about sin function?
How do you deal with the emotions of not being the one to find the cause of a bug?
How much can I judge a company based on a phone screening?
How do I call a 6 digit Austrailian phone number with a US based mobile phone?
Are there really no countries that protect Freedom of Speech as the United States does?
Can renaming a method preserve encapsulation?
Running code generated in realtime in JavaScript with eval()
Boss asked a co-worker to assault me
Why is the Lucas test not recommended to differentiate higher alcohols?
If "more guns less crime", how do gun advocates explain that the EU has less crime than the US?
Translation of "I don't have anything to smile about"
Telephone number in spoken words
If I control a zombie (animated) does it get undead fortitude saves when it's reduced to 0 HP?
Help, I cannot decide when to start the story
Yolo-v3 tiny *.weights file contains less weights then expected
Keras model.to_json() error: 'rawunicodeescape' codec can't decode bytes in position 94-98: truncated uXXXXGetting predictions after training using darknetInvalidArgumentError with Keras and WGANsKeras and tensorflow concatenation and fitting errorOpenCV Yolo V3 tinyToo many parameters trying to rebuild VGG16layer mismatch in custom layer attention networkWhy replacing max pool by average pool using Keras APIs fails?Loss of CNN in Keras becomes nan at some point of training
.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty margin-bottom:0;
0
I build a Yolo V3 Tiny model in Tensorflow and I would like to load the weights provided by Yolo itself. I found here and reading the official Yolo code, that I can read yolov3-tiny.weights discarding the first 16 bytes and then reading the remaining bytes converting them in float32.
Now, yolov3-tiny.weights has 35.434.956 bytes, so (35.434.956-16)/4=8.858.735 float32 numbers and so I should have 8.858.735 weights.
Anyway the summary of my yolov3-tiny network is the following:
>>> model.summary()
Model: "model"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
Input (InputLayer) [(None, 416, 416, 3) 0
__________________________________________________________________________________________________
conv_1 (Conv2D) (None, 416, 416, 16) 448 Input[0][0]
__________________________________________________________________________________________________
norm_1 (BatchNormalizationV1) (None, 416, 416, 16) 64 conv_1[0][0]
__________________________________________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 208, 208, 16) 0 norm_1[0][0]
__________________________________________________________________________________________________
conv_2 (Conv2D) (None, 208, 208, 32) 4640 max_pooling2d[0][0]
__________________________________________________________________________________________________
norm_2 (BatchNormalizationV1) (None, 208, 208, 32) 128 conv_2[0][0]
__________________________________________________________________________________________________
max_pooling2d_1 (MaxPooling2D) (None, 104, 104, 32) 0 norm_2[0][0]
__________________________________________________________________________________________________
conv_3 (Conv2D) (None, 104, 104, 64) 18496 max_pooling2d_1[0][0]
__________________________________________________________________________________________________
norm_3 (BatchNormalizationV1) (None, 104, 104, 64) 256 conv_3[0][0]
__________________________________________________________________________________________________
max_pooling2d_2 (MaxPooling2D) (None, 52, 52, 64) 0 norm_3[0][0]
__________________________________________________________________________________________________
conv_4 (Conv2D) (None, 52, 52, 128) 73856 max_pooling2d_2[0][0]
__________________________________________________________________________________________________
norm_4 (BatchNormalizationV1) (None, 52, 52, 128) 512 conv_4[0][0]
__________________________________________________________________________________________________
max_pooling2d_3 (MaxPooling2D) (None, 26, 26, 128) 0 norm_4[0][0]
__________________________________________________________________________________________________
conv_5 (Conv2D) (None, 26, 26, 256) 295168 max_pooling2d_3[0][0]
__________________________________________________________________________________________________
norm_5 (BatchNormalizationV1) (None, 26, 26, 256) 1024 conv_5[0][0]
__________________________________________________________________________________________________
max_pooling2d_4 (MaxPooling2D) (None, 13, 13, 256) 0 norm_5[0][0]
__________________________________________________________________________________________________
conv_6 (Conv2D) (None, 13, 13, 512) 1180160 max_pooling2d_4[0][0]
__________________________________________________________________________________________________
norm_6 (BatchNormalizationV1) (None, 13, 13, 512) 2048 conv_6[0][0]
__________________________________________________________________________________________________
max_pooling2d_5 (MaxPooling2D) (None, 13, 13, 512) 0 norm_6[0][0]
__________________________________________________________________________________________________
conv_7 (Conv2D) (None, 13, 13, 1024) 4719616 max_pooling2d_5[0][0]
__________________________________________________________________________________________________
norm_7 (BatchNormalizationV1) (None, 13, 13, 1024) 4096 conv_7[0][0]
__________________________________________________________________________________________________
conv_8 (Conv2D) (None, 13, 13, 256) 262400 norm_7[0][0]
__________________________________________________________________________________________________
norm_8 (BatchNormalizationV1) (None, 13, 13, 256) 1024 conv_8[0][0]
__________________________________________________________________________________________________
conv_11 (Conv2D) (None, 13, 13, 128) 32896 norm_8[0][0]
__________________________________________________________________________________________________
norm_10 (BatchNormalizationV1) (None, 13, 13, 128) 512 conv_11[0][0]
__________________________________________________________________________________________________
lambda_1 (Lambda) (None, 26, 26, 128) 0 norm_10[0][0]
__________________________________________________________________________________________________
concatenate (Concatenate) (None, 26, 26, 384) 0 lambda_1[0][0]
norm_5[0][0]
__________________________________________________________________________________________________
conv_9 (Conv2D) (None, 13, 13, 512) 1180160 norm_8[0][0]
__________________________________________________________________________________________________
conv_12 (Conv2D) (None, 26, 26, 256) 884992 concatenate[0][0]
__________________________________________________________________________________________________
norm_9 (BatchNormalizationV1) (None, 13, 13, 512) 2048 conv_9[0][0]
__________________________________________________________________________________________________
norm_11 (BatchNormalizationV1) (None, 26, 26, 256) 1024 conv_12[0][0]
__________________________________________________________________________________________________
conv_10 (Conv2D) (None, 13, 13, 255) 130815 norm_9[0][0]
__________________________________________________________________________________________________
conv_13 (Conv2D) (None, 26, 26, 255) 65535 norm_11[0][0]
__________________________________________________________________________________________________
lambda (Lambda) (None, 507, 85) 0 conv_10[0][0]
__________________________________________________________________________________________________
lambda_2 (Lambda) (None, 2028, 85) 0 conv_13[0][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 2535, 85) 0 lambda[0][0]
lambda_2[0][0]
==================================================================================================
Total params: 8,861,918
Trainable params: 8,855,550
Non-trainable params: 6,368
__________________________________________________________________________________________________
and has 8.861.918 weights. There are (8.861.918-8.858.735)=3183 parameters more then those contained in yolov3-tiny.weights. Had I make any error building the network or am I missing something?
Thank you.
python tensorflow conv-neural-network yolo
asked Mar 27 at 10:20
aleio1aleio1
487 bronze badges
add a comment |
0
I build a Yolo V3 Tiny model in Tensorflow and I would like to load the weights provided by Yolo itself. I found here and reading the official Yolo code, that I can read yolov3-tiny.weights discarding the first 16 bytes and then reading the remaining bytes converting them in float32.
Now, yolov3-tiny.weights has 35.434.956 bytes, so (35.434.956-16)/4=8.858.735 float32 numbers and so I should have 8.858.735 weights.
Anyway the summary of my yolov3-tiny network is the following:
>>> model.summary()
Model: "model"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
Input (InputLayer) [(None, 416, 416, 3) 0
__________________________________________________________________________________________________
conv_1 (Conv2D) (None, 416, 416, 16) 448 Input[0][0]
__________________________________________________________________________________________________
norm_1 (BatchNormalizationV1) (None, 416, 416, 16) 64 conv_1[0][0]
__________________________________________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 208, 208, 16) 0 norm_1[0][0]
__________________________________________________________________________________________________
conv_2 (Conv2D) (None, 208, 208, 32) 4640 max_pooling2d[0][0]
__________________________________________________________________________________________________
norm_2 (BatchNormalizationV1) (None, 208, 208, 32) 128 conv_2[0][0]
__________________________________________________________________________________________________
max_pooling2d_1 (MaxPooling2D) (None, 104, 104, 32) 0 norm_2[0][0]
__________________________________________________________________________________________________
conv_3 (Conv2D) (None, 104, 104, 64) 18496 max_pooling2d_1[0][0]
__________________________________________________________________________________________________
norm_3 (BatchNormalizationV1) (None, 104, 104, 64) 256 conv_3[0][0]
__________________________________________________________________________________________________
max_pooling2d_2 (MaxPooling2D) (None, 52, 52, 64) 0 norm_3[0][0]
__________________________________________________________________________________________________
conv_4 (Conv2D) (None, 52, 52, 128) 73856 max_pooling2d_2[0][0]
__________________________________________________________________________________________________
norm_4 (BatchNormalizationV1) (None, 52, 52, 128) 512 conv_4[0][0]
__________________________________________________________________________________________________
max_pooling2d_3 (MaxPooling2D) (None, 26, 26, 128) 0 norm_4[0][0]
__________________________________________________________________________________________________
conv_5 (Conv2D) (None, 26, 26, 256) 295168 max_pooling2d_3[0][0]
__________________________________________________________________________________________________
norm_5 (BatchNormalizationV1) (None, 26, 26, 256) 1024 conv_5[0][0]
__________________________________________________________________________________________________
max_pooling2d_4 (MaxPooling2D) (None, 13, 13, 256) 0 norm_5[0][0]
__________________________________________________________________________________________________
conv_6 (Conv2D) (None, 13, 13, 512) 1180160 max_pooling2d_4[0][0]
__________________________________________________________________________________________________
norm_6 (BatchNormalizationV1) (None, 13, 13, 512) 2048 conv_6[0][0]
__________________________________________________________________________________________________
max_pooling2d_5 (MaxPooling2D) (None, 13, 13, 512) 0 norm_6[0][0]
__________________________________________________________________________________________________
conv_7 (Conv2D) (None, 13, 13, 1024) 4719616 max_pooling2d_5[0][0]
__________________________________________________________________________________________________
norm_7 (BatchNormalizationV1) (None, 13, 13, 1024) 4096 conv_7[0][0]
__________________________________________________________________________________________________
conv_8 (Conv2D) (None, 13, 13, 256) 262400 norm_7[0][0]
__________________________________________________________________________________________________
norm_8 (BatchNormalizationV1) (None, 13, 13, 256) 1024 conv_8[0][0]
__________________________________________________________________________________________________
conv_11 (Conv2D) (None, 13, 13, 128) 32896 norm_8[0][0]
__________________________________________________________________________________________________
norm_10 (BatchNormalizationV1) (None, 13, 13, 128) 512 conv_11[0][0]
__________________________________________________________________________________________________
lambda_1 (Lambda) (None, 26, 26, 128) 0 norm_10[0][0]
__________________________________________________________________________________________________
concatenate (Concatenate) (None, 26, 26, 384) 0 lambda_1[0][0]
norm_5[0][0]
__________________________________________________________________________________________________
conv_9 (Conv2D) (None, 13, 13, 512) 1180160 norm_8[0][0]
__________________________________________________________________________________________________
conv_12 (Conv2D) (None, 26, 26, 256) 884992 concatenate[0][0]
__________________________________________________________________________________________________
norm_9 (BatchNormalizationV1) (None, 13, 13, 512) 2048 conv_9[0][0]
__________________________________________________________________________________________________
norm_11 (BatchNormalizationV1) (None, 26, 26, 256) 1024 conv_12[0][0]
__________________________________________________________________________________________________
conv_10 (Conv2D) (None, 13, 13, 255) 130815 norm_9[0][0]
__________________________________________________________________________________________________
conv_13 (Conv2D) (None, 26, 26, 255) 65535 norm_11[0][0]
__________________________________________________________________________________________________
lambda (Lambda) (None, 507, 85) 0 conv_10[0][0]
__________________________________________________________________________________________________
lambda_2 (Lambda) (None, 2028, 85) 0 conv_13[0][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 2535, 85) 0 lambda[0][0]
lambda_2[0][0]
==================================================================================================
Total params: 8,861,918
Trainable params: 8,855,550
Non-trainable params: 6,368
__________________________________________________________________________________________________
and has 8.861.918 weights. There are (8.861.918-8.858.735)=3183 parameters more then those contained in yolov3-tiny.weights. Had I make any error building the network or am I missing something?
Thank you.
python tensorflow conv-neural-network yolo
asked Mar 27 at 10:20
aleio1aleio1
487 bronze badges
add a comment |
0
0
0
1
I build a Yolo V3 Tiny model in Tensorflow and I would like to load the weights provided by Yolo itself. I found here and reading the official Yolo code, that I can read yolov3-tiny.weights discarding the first 16 bytes and then reading the remaining bytes converting them in float32.
Now, yolov3-tiny.weights has 35.434.956 bytes, so (35.434.956-16)/4=8.858.735 float32 numbers and so I should have 8.858.735 weights.
Anyway the summary of my yolov3-tiny network is the following:
>>> model.summary()
Model: "model"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
Input (InputLayer) [(None, 416, 416, 3) 0
__________________________________________________________________________________________________
conv_1 (Conv2D) (None, 416, 416, 16) 448 Input[0][0]
__________________________________________________________________________________________________
norm_1 (BatchNormalizationV1) (None, 416, 416, 16) 64 conv_1[0][0]
__________________________________________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 208, 208, 16) 0 norm_1[0][0]
__________________________________________________________________________________________________
conv_2 (Conv2D) (None, 208, 208, 32) 4640 max_pooling2d[0][0]
__________________________________________________________________________________________________
norm_2 (BatchNormalizationV1) (None, 208, 208, 32) 128 conv_2[0][0]
__________________________________________________________________________________________________
max_pooling2d_1 (MaxPooling2D) (None, 104, 104, 32) 0 norm_2[0][0]
__________________________________________________________________________________________________
conv_3 (Conv2D) (None, 104, 104, 64) 18496 max_pooling2d_1[0][0]
__________________________________________________________________________________________________
norm_3 (BatchNormalizationV1) (None, 104, 104, 64) 256 conv_3[0][0]
__________________________________________________________________________________________________
max_pooling2d_2 (MaxPooling2D) (None, 52, 52, 64) 0 norm_3[0][0]
__________________________________________________________________________________________________
conv_4 (Conv2D) (None, 52, 52, 128) 73856 max_pooling2d_2[0][0]
__________________________________________________________________________________________________
norm_4 (BatchNormalizationV1) (None, 52, 52, 128) 512 conv_4[0][0]
__________________________________________________________________________________________________
max_pooling2d_3 (MaxPooling2D) (None, 26, 26, 128) 0 norm_4[0][0]
__________________________________________________________________________________________________
conv_5 (Conv2D) (None, 26, 26, 256) 295168 max_pooling2d_3[0][0]
__________________________________________________________________________________________________
norm_5 (BatchNormalizationV1) (None, 26, 26, 256) 1024 conv_5[0][0]
__________________________________________________________________________________________________
max_pooling2d_4 (MaxPooling2D) (None, 13, 13, 256) 0 norm_5[0][0]
__________________________________________________________________________________________________
conv_6 (Conv2D) (None, 13, 13, 512) 1180160 max_pooling2d_4[0][0]
__________________________________________________________________________________________________
norm_6 (BatchNormalizationV1) (None, 13, 13, 512) 2048 conv_6[0][0]
__________________________________________________________________________________________________
max_pooling2d_5 (MaxPooling2D) (None, 13, 13, 512) 0 norm_6[0][0]
__________________________________________________________________________________________________
conv_7 (Conv2D) (None, 13, 13, 1024) 4719616 max_pooling2d_5[0][0]
__________________________________________________________________________________________________
norm_7 (BatchNormalizationV1) (None, 13, 13, 1024) 4096 conv_7[0][0]
__________________________________________________________________________________________________
conv_8 (Conv2D) (None, 13, 13, 256) 262400 norm_7[0][0]
__________________________________________________________________________________________________
norm_8 (BatchNormalizationV1) (None, 13, 13, 256) 1024 conv_8[0][0]
__________________________________________________________________________________________________
conv_11 (Conv2D) (None, 13, 13, 128) 32896 norm_8[0][0]
__________________________________________________________________________________________________
norm_10 (BatchNormalizationV1) (None, 13, 13, 128) 512 conv_11[0][0]
__________________________________________________________________________________________________
lambda_1 (Lambda) (None, 26, 26, 128) 0 norm_10[0][0]
__________________________________________________________________________________________________
concatenate (Concatenate) (None, 26, 26, 384) 0 lambda_1[0][0]
norm_5[0][0]
__________________________________________________________________________________________________
conv_9 (Conv2D) (None, 13, 13, 512) 1180160 norm_8[0][0]
__________________________________________________________________________________________________
conv_12 (Conv2D) (None, 26, 26, 256) 884992 concatenate[0][0]
__________________________________________________________________________________________________
norm_9 (BatchNormalizationV1) (None, 13, 13, 512) 2048 conv_9[0][0]
__________________________________________________________________________________________________
norm_11 (BatchNormalizationV1) (None, 26, 26, 256) 1024 conv_12[0][0]
__________________________________________________________________________________________________
conv_10 (Conv2D) (None, 13, 13, 255) 130815 norm_9[0][0]
__________________________________________________________________________________________________
conv_13 (Conv2D) (None, 26, 26, 255) 65535 norm_11[0][0]
__________________________________________________________________________________________________
lambda (Lambda) (None, 507, 85) 0 conv_10[0][0]
__________________________________________________________________________________________________
lambda_2 (Lambda) (None, 2028, 85) 0 conv_13[0][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 2535, 85) 0 lambda[0][0]
lambda_2[0][0]
==================================================================================================
Total params: 8,861,918
Trainable params: 8,855,550
Non-trainable params: 6,368
__________________________________________________________________________________________________
and has 8.861.918 weights. There are (8.861.918-8.858.735)=3183 parameters more then those contained in yolov3-tiny.weights. Had I make any error building the network or am I missing something?
Thank you.
python tensorflow conv-neural-network yolo
asked Mar 27 at 10:20
aleio1aleio1
487 bronze badges
I build a Yolo V3 Tiny model in Tensorflow and I would like to load the weights provided by Yolo itself. I found here and reading the official Yolo code, that I can read yolov3-tiny.weights discarding the first 16 bytes and then reading the remaining bytes converting them in float32.
Now, yolov3-tiny.weights has 35.434.956 bytes, so (35.434.956-16)/4=8.858.735 float32 numbers and so I should have 8.858.735 weights.
Anyway the summary of my yolov3-tiny network is the following:
>>> model.summary()
Model: "model"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
Input (InputLayer) [(None, 416, 416, 3) 0
__________________________________________________________________________________________________
conv_1 (Conv2D) (None, 416, 416, 16) 448 Input[0][0]
__________________________________________________________________________________________________
norm_1 (BatchNormalizationV1) (None, 416, 416, 16) 64 conv_1[0][0]
__________________________________________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 208, 208, 16) 0 norm_1[0][0]
__________________________________________________________________________________________________
conv_2 (Conv2D) (None, 208, 208, 32) 4640 max_pooling2d[0][0]
__________________________________________________________________________________________________
norm_2 (BatchNormalizationV1) (None, 208, 208, 32) 128 conv_2[0][0]
__________________________________________________________________________________________________
max_pooling2d_1 (MaxPooling2D) (None, 104, 104, 32) 0 norm_2[0][0]
__________________________________________________________________________________________________
conv_3 (Conv2D) (None, 104, 104, 64) 18496 max_pooling2d_1[0][0]
__________________________________________________________________________________________________
norm_3 (BatchNormalizationV1) (None, 104, 104, 64) 256 conv_3[0][0]
__________________________________________________________________________________________________
max_pooling2d_2 (MaxPooling2D) (None, 52, 52, 64) 0 norm_3[0][0]
__________________________________________________________________________________________________
conv_4 (Conv2D) (None, 52, 52, 128) 73856 max_pooling2d_2[0][0]
__________________________________________________________________________________________________
norm_4 (BatchNormalizationV1) (None, 52, 52, 128) 512 conv_4[0][0]
__________________________________________________________________________________________________
max_pooling2d_3 (MaxPooling2D) (None, 26, 26, 128) 0 norm_4[0][0]
__________________________________________________________________________________________________
conv_5 (Conv2D) (None, 26, 26, 256) 295168 max_pooling2d_3[0][0]
__________________________________________________________________________________________________
norm_5 (BatchNormalizationV1) (None, 26, 26, 256) 1024 conv_5[0][0]
__________________________________________________________________________________________________
max_pooling2d_4 (MaxPooling2D) (None, 13, 13, 256) 0 norm_5[0][0]
__________________________________________________________________________________________________
conv_6 (Conv2D) (None, 13, 13, 512) 1180160 max_pooling2d_4[0][0]
__________________________________________________________________________________________________
norm_6 (BatchNormalizationV1) (None, 13, 13, 512) 2048 conv_6[0][0]
__________________________________________________________________________________________________
max_pooling2d_5 (MaxPooling2D) (None, 13, 13, 512) 0 norm_6[0][0]
__________________________________________________________________________________________________
conv_7 (Conv2D) (None, 13, 13, 1024) 4719616 max_pooling2d_5[0][0]
__________________________________________________________________________________________________
norm_7 (BatchNormalizationV1) (None, 13, 13, 1024) 4096 conv_7[0][0]
__________________________________________________________________________________________________
conv_8 (Conv2D) (None, 13, 13, 256) 262400 norm_7[0][0]
__________________________________________________________________________________________________
norm_8 (BatchNormalizationV1) (None, 13, 13, 256) 1024 conv_8[0][0]
__________________________________________________________________________________________________
conv_11 (Conv2D) (None, 13, 13, 128) 32896 norm_8[0][0]
__________________________________________________________________________________________________
norm_10 (BatchNormalizationV1) (None, 13, 13, 128) 512 conv_11[0][0]
__________________________________________________________________________________________________
lambda_1 (Lambda) (None, 26, 26, 128) 0 norm_10[0][0]
__________________________________________________________________________________________________
concatenate (Concatenate) (None, 26, 26, 384) 0 lambda_1[0][0]
norm_5[0][0]
__________________________________________________________________________________________________
conv_9 (Conv2D) (None, 13, 13, 512) 1180160 norm_8[0][0]
__________________________________________________________________________________________________
conv_12 (Conv2D) (None, 26, 26, 256) 884992 concatenate[0][0]
__________________________________________________________________________________________________
norm_9 (BatchNormalizationV1) (None, 13, 13, 512) 2048 conv_9[0][0]
__________________________________________________________________________________________________
norm_11 (BatchNormalizationV1) (None, 26, 26, 256) 1024 conv_12[0][0]
__________________________________________________________________________________________________
conv_10 (Conv2D) (None, 13, 13, 255) 130815 norm_9[0][0]
__________________________________________________________________________________________________
conv_13 (Conv2D) (None, 26, 26, 255) 65535 norm_11[0][0]
__________________________________________________________________________________________________
lambda (Lambda) (None, 507, 85) 0 conv_10[0][0]
__________________________________________________________________________________________________
lambda_2 (Lambda) (None, 2028, 85) 0 conv_13[0][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 2535, 85) 0 lambda[0][0]
lambda_2[0][0]
==================================================================================================
Total params: 8,861,918
Trainable params: 8,855,550
Non-trainable params: 6,368
__________________________________________________________________________________________________
and has 8.861.918 weights. There are (8.861.918-8.858.735)=3183 parameters more then those contained in yolov3-tiny.weights. Had I make any error building the network or am I missing something?
Thank you.
python tensorflow conv-neural-network yolo
python tensorflow conv-neural-network yolo
asked Mar 27 at 10:20
aleio1aleio1
487 bronze badges
asked Mar 27 at 10:20
aleio1aleio1
487 bronze badges
edited Mar 28 at 8:40
aleio1
asked Mar 27 at 10:20
aleio1aleio1
487 bronze badges
asked Mar 27 at 10:20
aleio1aleio1
487 bronze badges
asked Mar 27 at 10:20
aleio1aleio1
487 bronze badges
487 bronze badges
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
0
For every conv layer with batch-normalization, you mistake using bias(b). In yolo, conv layer followed by batchnorm don't have bias. For example, for conv_1 layer, the correct para number should be 3*3*3*16=432, while in your model, it's 432+16=448.
edited May 23 at 13:29
Dinesh Shingadiya
9191 gold badge4 silver badges21 bronze badges
answered May 23 at 11:41
lordkTklordkTk
1
add a comment |
Your Answer
StackExchange.ifUsing("editor", function ()
StackExchange.using("externalEditor", function ()
StackExchange.using("snippets", function ()
StackExchange.snippets.init();
);
);
, "code-snippets");
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "1"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);
else
createEditor();
);
function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);
);
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f55374814%2fyolo-v3-tiny-weights-file-contains-less-weights-then-expected%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
0
For every conv layer with batch-normalization, you mistake using bias(b). In yolo, conv layer followed by batchnorm don't have bias. For example, for conv_1 layer, the correct para number should be 3*3*3*16=432, while in your model, it's 432+16=448.
edited May 23 at 13:29
Dinesh Shingadiya
9191 gold badge4 silver badges21 bronze badges
answered May 23 at 11:41
lordkTklordkTk
1
add a comment |
0
For every conv layer with batch-normalization, you mistake using bias(b). In yolo, conv layer followed by batchnorm don't have bias. For example, for conv_1 layer, the correct para number should be 3*3*3*16=432, while in your model, it's 432+16=448.
edited May 23 at 13:29
Dinesh Shingadiya
9191 gold badge4 silver badges21 bronze badges
answered May 23 at 11:41
lordkTklordkTk
1
add a comment |
0
0
0
For every conv layer with batch-normalization, you mistake using bias(b). In yolo, conv layer followed by batchnorm don't have bias. For example, for conv_1 layer, the correct para number should be 3*3*3*16=432, while in your model, it's 432+16=448.
edited May 23 at 13:29
Dinesh Shingadiya
9191 gold badge4 silver badges21 bronze badges
answered May 23 at 11:41
lordkTklordkTk
1
For every conv layer with batch-normalization, you mistake using bias(b). In yolo, conv layer followed by batchnorm don't have bias. For example, for conv_1 layer, the correct para number should be 3*3*3*16=432, while in your model, it's 432+16=448.
edited May 23 at 13:29
Dinesh Shingadiya
9191 gold badge4 silver badges21 bronze badges
answered May 23 at 11:41
lordkTklordkTk
1
edited May 23 at 13:29
Dinesh Shingadiya
9191 gold badge4 silver badges21 bronze badges
edited May 23 at 13:29
Dinesh Shingadiya
9191 gold badge4 silver badges21 bronze badges
edited May 23 at 13:29
Dinesh Shingadiya
9191 gold badge4 silver badges21 bronze badges
9191 gold badge4 silver badges21 bronze badges
answered May 23 at 11:41
lordkTklordkTk
1
answered May 23 at 11:41
lordkTklordkTk
1
answered May 23 at 11:41
lordkTklordkTk
1
1
add a comment |
add a comment |
Got a question that you can’t ask on public Stack Overflow? Learn more about sharing private information with Stack Overflow for Teams.
Got a question that you can’t ask on public Stack Overflow? Learn more about sharing private information with Stack Overflow for Teams.
draft saved
draft discarded
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f55374814%2fyolo-v3-tiny-weights-file-contains-less-weights-then-expected%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
