|
Deep Learning Advanced Computer Vision (GANs, SSD, +More!)
4 f+ V$ `7 R6 r: ^7 D z/ c, I r- y8 i6 s# z# T8 i
8 ^% u( c: F* F! f" R9 x+ E: t2 O
深度学习:高级计算机视觉教程(英文外语教学); _8 K# g7 ^; B$ J' s3 l! F
├──1. Welcome
6 T5 X- r+ C# ~: E3 `6 h| ├──1. Introduction39.mp4 7.77M, ?4 H: t1 T% L
| ├──1. Introduction39.srt 5.05kb3 G8 o6 e0 d! h6 e6 R% f
| ├──2. Outline and Perspective.mp4 7.45M, L5 ~1 h M4 f; b; s: I3 g" ]$ ]
| ├──2. Outline and Perspective.srt 13.79kb
5 ?5 b3 |) W3 Y| ├──3. Where to get the code.mp4 46.05M
/ a3 V- B D# F( O& Z| ├──3. Where to get the code.srt 19.59kb3 p" R- v( J( U) K
| ├──3.1 Colab Notebooks.html 0.15kb
- y& e F% F" y$ j0 [| ├──3.2 Github Link.html 0.12kb
# S3 `( r# \* }/ c S| ├──4. How to Succeed in this Course.mp4 3.30M
4 h$ v! O7 v5 b1 V& d* ?) `| └──4. How to Succeed in this Course.srt 6.11kb6 w( R( q! J- S: J
├──10. GANs (Generative Adversarial Networks)
) A7 c' q. W1 a$ V7 B| ├──1. GAN Theory.mp4 91.06M
9 N9 @ k- Y+ W' h3 \: e| ├──1. GAN Theory.srt 31.94kb
% R& ~- h3 H4 M% e! m; |$ ~+ S5 U7 z| ├──2. GAN Colab Notebook.html 0.24kb
) {1 w' L6 |7 u2 N| ├──3. GAN Code.mp4 82.29M/ K+ k" D% V2 X& i0 P+ R7 t
| └──3. GAN Code.srt 23.34kb5 Y' h6 E! d0 v3 R, r, v4 h
├──11. Object Localization Project ( b' L' X5 h+ ], i+ ~% A: G
| ├──1. Localization Introduction and Outline.mp4 62.90M
- {+ c8 K7 D. h* [2 a/ B T8 M| ├──1. Localization Introduction and Outline.srt 28.09kb
+ v4 S6 D$ C( _( Y; j| ├──10. Localization Code (pt 4).mp4 13.32M) W3 f. k; R ^- b( k* ?$ p7 r
| ├──10. Localization Code (pt 4).srt 3.48kb
, Z2 v" L* D# [; H) t9 o7 e| ├──11. Localization Code Outline (pt 5).mp4 43.07M
, [. j$ K* Q2 d S| ├──11. Localization Code Outline (pt 5).srt 16.84kb
# ^* Q- j! k% e U3 R1 \| ├──12. Localization Code (pt 5).mp4 59.85M1 w) ?1 h2 Z) ~' h& _# W
| ├──12. Localization Code (pt 5).srt 16.40kb$ a6 E1 K0 Y( `, r5 v- }+ y' t
| ├──13. Localization Code Outline (pt 6).mp4 33.57M
7 u- b4 C k$ T- `9 T7 s| ├──13. Localization Code Outline (pt 6).srt 14.82kb
6 }9 u f* A9 g8 S' `# M% [| ├──14. Localization Code (pt 6).mp4 56.68M
! h$ I: V* |8 I, f4 J, u* \| ├──14. Localization Code (pt 6).srt 15.37kb
" x& \3 a+ @+ S1 i| ├──15. Localization Code Outline (pt 7).mp4 20.61M" N- t1 r1 ^! H% |4 m
| ├──15. Localization Code Outline (pt 7).srt 10.04kb
4 W" B. s! Y5 G, v1 {( k8 ]; m' ^/ [. o| ├──16. Localization Code (pt 7).mp4 77.18M9 q, X- t' X3 g6 d1 n( ?
| ├──16. Localization Code (pt 7).srt 24.21kb6 B6 @6 ? o1 u* i
| ├──2. Localization Code Outline (pt 1).mp4 41.29M
2 Q. a, W* X ~3 x a" E0 [& Z+ e" M| ├──2. Localization Code Outline (pt 1).srt 22.08kb8 V" z3 \' ?4 ^& q
| ├──3. Object Localization Colab Notebooks.html 0.77kb
8 \" }6 M0 l8 v& e5 j| ├──4. Localization Code (pt 1).mp4 53.81M
) u1 X" C; p1 d4 B| ├──4. Localization Code (pt 1).srt 18.45kb
* T4 n7 ?6 L; q) A! || ├──5. Localization Code Outline (pt 2).mp4 18.71M
+ C8 H' z3 a( M7 i, }+ K9 y+ P| ├──5. Localization Code Outline (pt 2).srt 9.74kb$ V5 ]+ D/ L O4 j
| ├──6. Localization Code (pt 2).mp4 58.60M
# s: @! Y( R: O| ├──6. Localization Code (pt 2).srt 21.76kb. {. ?, a$ @* J) i' K9 _* R
| ├──7. Localization Code Outline (pt 3).mp4 12.33M0 p- U; d! V+ z% S
| ├──7. Localization Code Outline (pt 3).srt 6.78kb
& G- j% V2 g) }, t| ├──8. Localization Code (pt 3).mp4 30.06M4 O+ M: z: K, d E5 k
| ├──8. Localization Code (pt 3).srt 8.13kb
+ y8 F2 V, {/ p; u| ├──9. Localization Code Outline (pt 4).mp4 13.66M
5 J* M0 ~6 |' e| └──9. Localization Code Outline (pt 4).srt 7.26kb
2 @/ p1 Q1 k8 e6 T$ E+ E) d├──12. Keras and Tensorflow 2 Basics Review 4 R! x3 Z& y. w! m7 f. O8 i
| ├──1. (Review) Tensorflow Basics.mp4 81.53M
( v! G$ {6 }) p& k| ├──1. (Review) Tensorflow Basics.srt 9.05kb
; H1 }5 }+ ]! u8 r| ├──2. (Review) Tensorflow Neural Network in Code.mp4 97.24M
0 L* P4 z# ^& G" m| ├──2. (Review) Tensorflow Neural Network in Code.srt 8.49kb
: }1 Y: H# B; X) X' N2 r3 y| ├──3. (Review) Keras Discussion.mp4 27.64M
, e4 N# T9 a& b0 R# X| ├──3. (Review) Keras Discussion.srt 14.56kb
- }# K4 n S* `| ├──4. (Review) Keras Neural Network in Code.mp4 66.16M5 d) I: r! b B4 {+ g
| ├──4. (Review) Keras Neural Network in Code.srt 11.48kb
/ H: O$ \2 D% V# W C+ i+ ?" x9 n| ├──5. (Review) Keras Functional API.mp4 38.64M
5 d" F+ u$ |' y& X @2 q' t+ X9 f, o1 w| ├──5. (Review) Keras Functional API.srt 8.43kb
# b9 r; C: a' O% M7 y& l| ├──6. (Review) How to easily convert Keras into Tensorflow 2.0 code.mp4 9.81M) G) ~8 v8 R5 r* o" Q8 f0 ?
| └──6. (Review) How to easily convert Keras into Tensorflow 2.0 code.srt 2.08kb5 H0 g$ ]/ w0 P4 H5 {( d8 c
├──13. Setting Up Your Environment (FAQ by Student Request)
- j( P: b' ?, o| ├──1. Windows-Focused Environment Setup 2018.mp4 186.32M
6 X1 y. C1 I: a9 m| ├──1. Windows-Focused Environment Setup 2018.srt 20.10kb$ J; T, T% a) ^2 g# A3 k0 r
| ├──2. How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow.mp4 43.82M
1 S+ X* ^! e3 h' a# B| └──2. How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow.srt 14.48kb% W* y' d) y `1 C5 D% ~
├──14. Extra Help With Python Coding for Beginners (FAQ by Student Request)
3 S* p- @; `9 {2 t" x| ├──1. How to Code by Yourself (part 1).mp4 24.53M
3 W! I, }( O) C+ Q| ├──1. How to Code by Yourself (part 1).srt 22.75kb7 x3 [$ U5 V: g$ K9 r Q$ \1 ]
| ├──2. How to Code by Yourself (part 2).mp4 8.64M4 I& J: c1 e! |) Q+ X
| ├──2. How to Code by Yourself (part 2).srt 13.22kb F# a d) G( r7 I, G3 U
| ├──3. Proof that using Jupyter Notebook is the same as not using it.mp4 78.26M3 I/ M7 I; R6 ~3 w6 ?4 }: X6 \
| ├──3. Proof that using Jupyter Notebook is the same as not using it.srt 14.12kb+ Y: I& o! R+ z& q, V" h
| ├──4. Python 2 vs Python 3.mp4 5.47M
0 H* [- c8 ` h8 U3 s| └──4. Python 2 vs Python 3.srt 6.05kb
. m& y/ E0 ?% D" \4 N) E0 F* v; z├──15. Effective Learning Strategies for Machine Learning (FAQ by Student Request)
b# V! @- d4 z+ x| ├──1. How to Succeed in this Course (Long Version).mp4 12.99M% R) H2 G2 m2 G
| ├──1. How to Succeed in this Course (Long Version).srt 14.66kb7 A3 c8 ~- v# {4 {1 T
| ├──2. Is this for Beginners or Experts Academic or Practical Fast or slow-paced.mp4 38.95M
8 q- D9 ]% C n| ├──2. Is this for Beginners or Experts Academic or Practical Fast or slow-paced.srt 31.79kb
4 v0 v. ]1 _) Z E| ├──3. Machine Learning and AI Prerequisite Roadmap (pt 1).mp4 29.32M. U) ~9 |- N7 e7 P
| ├──3. Machine Learning and AI Prerequisite Roadmap (pt 1).srt 16.03kb4 p; c( E4 K: g3 [1 H6 L% a2 o
| ├──4. Machine Learning and AI Prerequisite Roadmap (pt 2).mp4 37.62M' ?+ s# p# _* x' r+ @
| └──4. Machine Learning and AI Prerequisite Roadmap (pt 2).srt 23.04kb
3 R/ g( Y% }4 a1 D' |/ V; @├──16. Appendix FAQ Finale 7 c6 `4 y6 B" K- `* w2 q1 Q
| ├──1. What is the Appendix (1).srt 5.60kb
0 |! e+ [" j3 F( Y) W| ├──1. What is the Appendix.mp4 5.45M: c r" I2 g* I2 e: W4 K9 T( u0 I
| ├──1. What is the Appendix.srt 3.72kb
h5 C$ ?3 u7 y% e x( P# `| ├──2. BONUS Where to get discount coupons and FREE deep learning material.mp4 37.81M
* I ?3 W0 [1 d& `* s| └──2. BONUS Where to get discount coupons and FREE deep learning material.srt 12.44kb
c# X; `& @: W2 z8 d├──2. Machine Learning Basics Review
- o3 U8 m P0 T3 c. \4 [+ p/ W8 s- {| ├──1. What is Machine Learning.mp4 70.85M6 z/ z, p6 C% Y4 ^; l, A
| ├──1. What is Machine Learning.srt 29.35kb: U( i8 d* f5 m
| ├──10. Saving and Loading a Model.mp4 33.86M
% O' u3 h0 j4 @! V' b| ├──10. Saving and Loading a Model.srt 7.90kb* z S( T/ `2 d8 i J
| ├──11. Suggestion Box.mp4 16.11M
! A |' i' n" g' v7 c! x| ├──11. Suggestion Box.srt 7.15kb0 J3 \1 T( p3 a4 R1 x- |( V
| ├──2. Code Preparation (Classification Theory).mp4 65.13M5 x$ {- R" [' t' E1 u2 R
| ├──2. Code Preparation (Classification Theory).srt 32.25kb Z! v: H5 E. m' t) M
| ├──3. Beginner's Code Preamble.mp4 25.11M r8 r) n5 P9 s7 {1 |& g% V# M& K
| ├──3. Beginner's Code Preamble.srt 10.58kb8 i; h i6 v6 n8 V; e
| ├──3.1 Notebooks.html 0.15kb4 r' Q; ~/ q$ W- `5 M9 |1 \1 A
| ├──4. Classification Notebook.mp4 60.47M
* K, r) |$ X h/ m| ├──4. Classification Notebook.srt 14.66kb
, t) W* K; l$ Z6 F' o| ├──5. Code Preparation (Regression Theory).mp4 30.71M
) g8 j0 t# g7 o- f) _& L8 J5 K| ├──5. Code Preparation (Regression Theory).srt 13.73kb5 ^6 r0 S8 W3 t6 D% c
| ├──6. Regression Notebook.mp4 64.67M
& e- x" D5 [$ Q| ├──6. Regression Notebook.srt 19.38kb4 L) q; j8 w9 }
| ├──7. The Neuron.mp4 45.48M
# F q( z. _6 s. ^8 y+ }5 Q [0 E| ├──7. The Neuron.srt 19.58kb! v! E" S5 K; T. ?8 O" L
| ├──8. How does a model learn.mp4 51.84M
6 a- i/ V+ W" w6 M N9 l2 I| ├──8. How does a model learn.srt 22.05kb& f( g0 F- x# k! |2 @; U
| ├──9. Making Predictions.mp4 36.85M) u2 a R t7 c# g
| └──9. Making Predictions.srt 12.61kb* k( i0 q' _ `6 P' [/ B) k. F2 t
├──3. Artificial Neural Networks (ANN) Review
! m5 v+ \. `7 \7 A| ├──1. Artificial Neural Networks Section Introduction.mp4 29.85M
' E0 ~7 P; d% @- y- r v| ├──1. Artificial Neural Networks Section Introduction.srt 12.42kb
0 J# S/ e- O5 a' D# l: \8 Z1 H| ├──2. Forward Propagation.mp4 46.75M
+ |( u1 j! v* ?3 G% `' Y| ├──2. Forward Propagation.srt 12.41kb4 g( t& z; a" ]( o1 A/ C. M- W2 \
| ├──3. The Geometrical Picture.mp4 56.46M ]2 C0 G" x3 X, c) _0 I: E) M& O
| ├──3. The Geometrical Picture.srt 18.39kb
) Z4 V V8 `7 F0 ^+ L# {- o' y3 L| ├──4. Activation Functions.mp4 80.61M
) E, |( k) |) H; P7 d| ├──4. Activation Functions.srt 34.90kb
) R3 z* S& w" u. a) |6 j4 o; B1 h| ├──5. Multiclass Classification.mp4 41.41M, B4 b. [/ E8 K/ a8 d1 C
| ├──5. Multiclass Classification.srt 17.07kb
3 w: P& t" s3 K: p. s* K| ├──6. How to Represent Images.mp4 70.49M
$ V4 p3 I$ |/ M4 M& W1 e| ├──6. How to Represent Images.srt 24.87kb
8 [, ]! X0 J3 \/ Z. \+ j, C% J| ├──7. Code Preparation (ANN).mp4 50.97M
' h' v; [/ [" ]| ├──7. Code Preparation (ANN).srt 25.25kb% ^7 I n& e; n8 T
| ├──8. ANN for Image Classification.mp4 47.71M4 S* g& D' t# V
| ├──8. ANN for Image Classification.srt 15.36kb8 z8 ?" I9 C u0 b1 Y" |
| ├──9. ANN for Regression.mp4 69.23M
( G6 x1 ?4 s" \6 I; V+ f- F| └──9. ANN for Regression.srt 20.53kb
; B# \- K1 K% E% D# ~├──4. Convolutional Neural Networks (CNN) Review 8 V- O; z% s' i4 I- o2 |
| ├──1. What is Convolution (part 1).mp4 79.83M
% x: ?9 `: [3 \4 H4 w# S| ├──1. What is Convolution (part 1).srt 32.04kb
. c, g" D* u) x: L( m| ├──10. Batch Normalization.mp4 21.13M
' o3 b7 \0 N' `- k7 U| ├──10. Batch Normalization.srt 10.19kb
. _+ v/ F+ I) ^- J| ├──11. Improving CIFAR-10 Results.mp4 72.94M
7 j. [4 h& K$ K: V) B0 g' @% L| ├──11. Improving CIFAR-10 Results.srt 20.90kb+ w+ c; o& N$ _" E! o O$ |
| ├──2. What is Convolution (part 2).mp4 22.30M
1 m3 Z, M8 I2 `5 k# f| ├──2. What is Convolution (part 2).srt 10.70kb
2 a) N) ^, j; Y# E7 `| ├──3. What is Convolution (part 3).mp4 27.63M
$ M: b5 o( F! P| ├──3. What is Convolution (part 3).srt 12.55kb
2 K4 |, G' s, t" O1 k| ├──4. Convolution on Color Images.mp4 69.43M" x; N9 F+ D* p$ a u
| ├──4. Convolution on Color Images.srt 32.45kb
* t( r1 V9 z0 T, l| ├──5. CNN Architecture.mp4 80.68M
1 R/ Y) l# F$ M$ D6 |: {| ├──5. CNN Architecture.srt 44.47kb
! C! m8 o2 S5 o2 j6 z: Y! K| ├──6. CNN Code Preparation.mp4 76.91M
* X. I4 }! B* ?8 }( u5 ]; m| ├──6. CNN Code Preparation.srt 30.67kb ~' y7 d" a! _7 R7 }
| ├──7. CNN for Fashion MNIST.mp4 42.80M
3 g. C1 \7 x" d1 w| ├──7. CNN for Fashion MNIST.srt 12.58kb2 T, _# A" C4 R4 ]- l
| ├──8. CNN for CIFAR-10.mp4 29.69M
5 _; m4 x: R! J6 w$ X| ├──8. CNN for CIFAR-10.srt 8.65kb
$ _& d O* Q7 G8 G3 `| ├──9. Data Augmentation.mp4 34.99M
: w+ s# N h6 ?4 a: t; }| └──9. Data Augmentation.srt 17.75kb
6 Z2 Z; m6 `% F" v├──5. VGG and Transfer Learning . h1 h$ c1 l$ P5 s! { {" f
| ├──1. VGG Section Intro.mp4 2.69M
- I0 D+ U1 d. x! g) k* d/ L| ├──1. VGG Section Intro.srt 5.84kb, K9 }- g3 S# U5 C
| ├──2. What's so special about VGG.mp4 12.19M
) |/ \' P0 B! @; c# W2 H3 D| ├──2. What's so special about VGG.srt 14.29kb
$ R+ s( |+ w$ j( \* s. W| ├──3. Transfer Learning.mp4 38.12M
: E' C$ X# b( q( v| ├──3. Transfer Learning.srt 16.40kb1 }) |0 _" \- W S' o1 \
| ├──4. Relationship to Greedy Layer-Wise Pretraining.mp4 3.88M. h$ @: U6 m; m$ K3 D6 w
| ├──4. Relationship to Greedy Layer-Wise Pretraining.srt 4.16kb
) x2 {) P5 t! R6 V3 T; [) Q7 x9 F| ├──5. Getting the data.mp4 1.77M
7 J) M( [' d+ u! T" B. p| ├──5. Getting the data.srt 4.40kb
) z/ v; C$ j9 t \! P9 J; u$ m| ├──6. Code pt 1.mp4 11.51M* A+ O% m5 j) e+ b5 g
| ├──6. Code pt 1.srt 19.43kb
( u, T$ m$ ^8 v. t5 M& q3 Y| ├──7. Code pt 2.mp4 8.56M
$ K* X; s) r4 n2 i a/ O| ├──7. Code pt 2.srt 7.48kb
$ D. Z! t# H/ {* U, Z' ?" y| ├──8. Code pt 3.mp4 4.22M0 S f: Q; Q$ ?' e( u
| ├──8. Code pt 3.srt 6.80kb
( G0 }9 u( L4 f$ Q @( C7 I$ a( [! [| ├──9. VGG Section Summary.mp4 3.15M
* s) \6 S. ^' Y6 D$ {: t' V| └──9. VGG Section Summary.srt 3.28kb
3 V+ |+ l! K# Q; s( e$ N6 k% x├──6. ResNet (and Inception) 0 d: |% d4 R% y" Q3 k
| ├──1. ResNet Section Intro.mp4 2.82M! L8 B' z* e; n7 u2 I2 m
| ├──1. ResNet Section Intro.srt 5.89kb; ^* k5 h+ {/ w9 t% I }! N/ z0 B
| ├──10. Building ResNet - Putting it all together.mp4 5.91M, J/ V, ?8 v# i$ y: i x
| ├──10. Building ResNet - Putting it all together.srt 7.91kb
, D# Q; G( k8 C/ N8 ^& N| ├──11. Exercise Apply ResNet.mp4 2.07M, o4 v6 W9 L s$ @
| ├──11. Exercise Apply ResNet.srt 2.43kb7 r1 d+ @+ l3 r7 t% k
| ├──12. Applying ResNet.mp4 3.59M- ?5 M* t" Y( p+ O+ T6 M
| ├──12. Applying ResNet.srt 4.84kb# n1 ]( d2 `5 i' H5 V! I) ?. b
| ├──13. 1x1 Convolutions.mp4 3.11M0 d+ G; `; d, l% u. R
| ├──13. 1x1 Convolutions.srt 7.75kb
* B( c' p3 u' Y) V" A| ├──14. Optional Inception.mp4 5.39M0 ~: X5 { Z6 `) Q( A. V. v
| ├──14. Optional Inception.srt 13.62kb" ^( \" c6 l8 H: Q9 D& W4 a+ N) h
| ├──15. Different sized images using the same network.mp4 7.41M; O. G" V8 L! o7 G; f: p; c
| ├──15. Different sized images using the same network.srt 8.69kb
: S' }0 U- U7 ?: T, }5 V- o, L| ├──16. ResNet Section Summary.mp4 4.19M
$ M9 N* X3 _" A| ├──16. ResNet Section Summary.srt 4.53kb
7 [$ B, J" V2 k2 q& i9 }| ├──2. ResNet Architecture.mp4 10.39M3 R' }3 }0 p1 p" J6 [
| ├──2. ResNet Architecture.srt 25.67kb
- w( u; S2 h: L5 Y; a7 U| ├──3. Building ResNet - Strategy.mp4 2.66M
- S' n/ D1 v/ D: P| ├──3. Building ResNet - Strategy.srt 4.68kb6 Y7 i. i$ v8 i# W: u$ \
| ├──4. Uh-oh! What Happens if the Implementation Changes.mp4 25.34M0 M: e7 h0 \ [( N
| ├──4. Uh-oh! What Happens if the Implementation Changes.srt 11.24kb8 P0 y' f0 L Z( I2 p
| ├──5. Building ResNet - Conv Block Details.mp4 6.18M' W9 w5 l, [: I- n+ Y3 @
| ├──5. Building ResNet - Conv Block Details.srt 7.04kb
* b% B4 W( ?3 E. B4 B1 u+ g| ├──6. Building ResNet - Conv Block Code.mp4 8.97M/ Z- m$ R* [' R# u" Y5 }- q
| ├──6. Building ResNet - Conv Block Code.srt 12.24kb/ a, z' `! f* S
| ├──7. Building ResNet - Identity Block Details.mp4 2.38M7 w; L7 H1 b# [9 C5 E5 y2 _! J
| ├──7. Building ResNet - Identity Block Details.srt 2.69kb( u7 t8 w9 y o
| ├──8. Building ResNet - First Few Layers.mp4 4.03M1 ]1 v4 M. q5 }! T @
| ├──8. Building ResNet - First Few Layers.srt 4.74kb: r; f: `! [8 a4 ]0 W
| ├──9. Building ResNet - First Few Layers (Code).mp4 10.31M9 Y" ^. ~! j% w$ L, e2 D9 ]3 b
| └──9. Building ResNet - First Few Layers (Code).srt 7.49kb$ U3 u4 s& f/ d4 b* B6 Y2 g% Z
├──7. Object Detection (SSD RetinaNet) : Q. l; b: l# B
| ├──1. SSD Section Intro.mp4 5.69M
! l3 ?0 \$ A0 h, Y+ G- L: I| ├──1. SSD Section Intro.srt 9.83kb
3 j# Q, _( T' r$ y5 [+ B2 K| ├──10. RetinaNet with Custom Dataset (pt 2).mp4 60.52M
* L6 j: s6 }1 U' w* c0 W! E8 [| ├──10. RetinaNet with Custom Dataset (pt 2).srt 19.31kb2 R- x* F% r @1 T
| ├──11. RetinaNet with Custom Dataset (pt 3).mp4 61.81M
! [" d! q8 a- N3 q/ ~# @6 ^% H s| ├──11. RetinaNet with Custom Dataset (pt 3).srt 12.66kb% V$ k- y; N3 r, F. W
| ├──12. Optional Intersection over Union & Non-max Suppression.mp4 4.59M
- Q% c- U6 M6 A8 N' i| ├──12. Optional Intersection over Union & Non-max Suppression.srt 9.73kb
0 {. f, o' x# x" _) p- s4 }+ K" y! h: t| ├──13. SSD Section Summary.mp4 2.83M
, ?! S! J+ u, B7 O! T. g7 G! ^( i6 J| ├──13. SSD Section Summary.srt 5.50kb
+ l) r% @& Z- c5 O; b' v| ├──2. Object Localization.mp4 5.69M
' h1 r/ t( L2 h J| ├──2. Object Localization.srt 12.50kb
. o4 U7 w1 ]$ S5 Q8 A7 e| ├──3. What is Object Detection.mp4 4.79M
: C6 I: S5 Q. D2 m9 p2 W| ├──3. What is Object Detection.srt 5.68kb2 j6 Q" P7 n% r0 n N
| ├──4. How would you find an object in an image.mp4 7.85M
. r* z1 P% H7 k) C9 k| ├──4. How would you find an object in an image.srt 16.34kb
! N- r% m$ j2 Y0 J S| ├──5. The Problem of Scale.mp4 4.16M
. {2 J. n% g* V| ├──5. The Problem of Scale.srt 7.14kb
. }& N0 M2 w. W| ├──6. The Problem of Shape.mp4 3.59M
, _) A6 h. m/ {' o- i| ├──6. The Problem of Shape.srt 7.26kb: }# b* L9 a7 v- A$ e1 H) L+ m
| ├──7. 2020 Update - More Fun and Excitement.mp4 34.59M5 L* ^: m4 Y- w& b/ w
| ├──7. 2020 Update - More Fun and Excitement.srt 12.97kb9 I1 j0 D/ X; {2 [/ `! n
| ├──8. Using Pretrained RetinaNet.mp4 88.23M. J% ^9 }$ ~' g9 Q7 {% Y2 H3 u
| ├──8. Using Pretrained RetinaNet.srt 23.15kb
8 p7 A% i: M9 Q1 w5 }| ├──8.1 Notebooks.html 0.15kb w B6 V T; o, E2 q- O
| ├──9. RetinaNet with Custom Dataset (pt 1).mp4 26.60M
& R3 q. W$ g4 K) D% D9 d3 j5 X/ o| └──9. RetinaNet with Custom Dataset (pt 1).srt 9.50kb
2 M7 ^, |+ B' K0 Y. @. B4 g├──8. Neural Style Transfer * I6 p* x0 ?: Q$ R7 u! ^, p
| ├──1. Style Transfer Section Intro.mp4 2.91M
- Q" ?4 ~% T4 L. \. D' O| ├──1. Style Transfer Section Intro.srt 5.95kb
7 V' U# S! C8 C5 D- C0 Y5 \0 e8 R || ├──2. Style Transfer Theory.mp4 19.94M
; G2 l$ Z( V* T1 R; ~* \. ]/ f| ├──2. Style Transfer Theory.srt 22.38kb
7 ^* f; F( Y* f% e# G| ├──3. Optimizing the Loss.mp4 7.24M8 y$ l2 F; B8 _5 [+ L2 X
| ├──3. Optimizing the Loss.srt 16.07kb7 X/ |$ f- B1 |( q9 F
| ├──4. Code pt 1.mp4 9.46M2 g7 e0 t' Q7 v. u
| ├──4. Code pt 1.srt 14.97kb6 Q% v/ p, J* I Y4 H& p
| ├──5. Code pt 2.mp4 15.71M
3 x) A O2 p3 d. _- _4 N| ├──5. Code pt 2.srt 14.26kb
5 U9 h# t. F) f| ├──6. Code pt 3.mp4 5.74M) h6 w5 t& b+ a9 V1 v+ ~
| ├──6. Code pt 3.srt 6.90kb
" ~% T+ ]( d4 i6 s| ├──7. Style Transfer Section Summary.mp4 2.50M" E6 r, y8 i8 O4 m
| └──7. Style Transfer Section Summary.srt 4.60kb
! O; ]$ Z8 c; H3 M( [/ ^└──9. Class Activation Maps 3 M/ E; H% p5 \' E2 G
| ├──1. Class Activation Maps (Theory).mp4 53.42M
; j$ C+ a j3 U| ├──1. Class Activation Maps (Theory).srt 13.88kb
* X" D' z3 f, s/ P, ~5 a( I4 \| ├──2. Class Activation Maps (Code).mp4 104.76M$ y3 O+ X4 A! ~/ p( \" Z
| └──2. Class Activation Maps (Code).srt 15.57kb
g5 A% H% {) i, Z! f( w- l. \) D8 ?, Q% ~9 C' @3 D
& L6 H% Q4 w5 x. ~, y0 ?4 |8 Q! `
7 I* U7 N; k+ y/ I. x* w) h& H, B. I
资源下载地址和密码(百度云盘): [/hide] 百度网盘信息回帖可见
% t' ]9 @" B8 j, k B/ m2 V+ q1 h) U' r9 I3 f
7 R) X( s/ S }4 L& n e7 `4 N( S$ g1 n
) T) E# D. w" ^本资源由Java自学网收集整理【www.javazx.com】 |
|