Remove unnecessary files and clean up code

CITATION.cff

@@ -1,17 +0,0 @@
-cff-version: 1.2.0
-message: "If you find this repository useful in your research, please cite"
-authors:
-  - family-names: Kim
-    given-names: Saehoon
-  - family-names: Cho
-    given-names: Sanghun
-  - family-names: Kim
-    given-names: Chiheon
-  - family-names: Lee
-    given-names: Doyup
-  - family-names: Baek
-    given-names: Woonhyuk
-title: "minDALL-E on Conceptual Captions"
-version: 0.1
-date-released: 2021-12-14
-repository-code: https://github.com/kakaobrain/minDALL-E

LICENSE

@@ -1,2 +0,0 @@
-The `source codes` are licensed under [Apache 2.0](LICENSE.apache-2.0) License.
-The `stage2 pretrained weights` are licensed under [CC-BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) License.

LICENSE.apache-2.0

@@ -1,201 +0,0 @@
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [2021.11.13] [Kakao Brain]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.

LICENSE.cc-by-nc-sa-4.0

@@ -1,437 +0,0 @@
-Attribution-NonCommercial-ShareAlike 4.0 International
-
-=======================================================================
-
-Creative Commons Corporation ("Creative Commons") is not a law firm and
-does not provide legal services or legal advice. Distribution of
-Creative Commons public licenses does not create a lawyer-client or
-other relationship. Creative Commons makes its licenses and related
-information available on an "as-is" basis. Creative Commons gives no
-warranties regarding its licenses, any material licensed under their
-terms and conditions, or any related information. Creative Commons
-disclaims all liability for damages resulting from their use to the
-fullest extent possible.
-
-Using Creative Commons Public Licenses
-
-Creative Commons public licenses provide a standard set of terms and
-conditions that creators and other rights holders may use to share
-original works of authorship and other material subject to copyright
-and certain other rights specified in the public license below. The
-following considerations are for informational purposes only, are not
-exhaustive, and do not form part of our licenses.
-
-     Considerations for licensors: Our public licenses are
-     intended for use by those authorized to give the public
-     permission to use material in ways otherwise restricted by
-     copyright and certain other rights. Our licenses are
-     irrevocable. Licensors should read and understand the terms
-     and conditions of the license they choose before applying it.
-     Licensors should also secure all rights necessary before
-     applying our licenses so that the public can reuse the
-     material as expected. Licensors should clearly mark any
-     material not subject to the license. This includes other CC-
-     licensed material, or material used under an exception or
-     limitation to copyright. More considerations for licensors:
-    wiki.creativecommons.org/Considerations_for_licensors
-
-     Considerations for the public: By using one of our public
-     licenses, a licensor grants the public permission to use the
-     licensed material under specified terms and conditions. If
-     the licensor's permission is not necessary for any reason--for
-     example, because of any applicable exception or limitation to
-     copyright--then that use is not regulated by the license. Our
-     licenses grant only permissions under copyright and certain
-     other rights that a licensor has authority to grant. Use of
-     the licensed material may still be restricted for other
-     reasons, including because others have copyright or other
-     rights in the material. A licensor may make special requests,
-     such as asking that all changes be marked or described.
-     Although not required by our licenses, you are encouraged to
-     respect those requests where reasonable. More_considerations
-     for the public:
-    wiki.creativecommons.org/Considerations_for_licensees
-
-=======================================================================
-
-Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
-Public License
-
-By exercising the Licensed Rights (defined below), You accept and agree
-to be bound by the terms and conditions of this Creative Commons
-Attribution-NonCommercial-ShareAlike 4.0 International Public License
-("Public License"). To the extent this Public License may be
-interpreted as a contract, You are granted the Licensed Rights in
-consideration of Your acceptance of these terms and conditions, and the
-Licensor grants You such rights in consideration of benefits the
-Licensor receives from making the Licensed Material available under
-these terms and conditions.
-
-
-Section 1 -- Definitions.
-
-  a. Adapted Material means material subject to Copyright and Similar
-     Rights that is derived from or based upon the Licensed Material
-     and in which the Licensed Material is translated, altered,
-     arranged, transformed, or otherwise modified in a manner requiring
-     permission under the Copyright and Similar Rights held by the
-     Licensor. For purposes of this Public License, where the Licensed
-     Material is a musical work, performance, or sound recording,
-     Adapted Material is always produced where the Licensed Material is
-     synched in timed relation with a moving image.
-
-  b. Adapter's License means the license You apply to Your Copyright
-     and Similar Rights in Your contributions to Adapted Material in
-     accordance with the terms and conditions of this Public License.
-
-  c. BY-NC-SA Compatible License means a license listed at
-     creativecommons.org/compatiblelicenses, approved by Creative
-     Commons as essentially the equivalent of this Public License.
-
-  d. Copyright and Similar Rights means copyright and/or similar rights
-     closely related to copyright including, without limitation,
-     performance, broadcast, sound recording, and Sui Generis Database
-     Rights, without regard to how the rights are labeled or
-     categorized. For purposes of this Public License, the rights
-     specified in Section 2(b)(1)-(2) are not Copyright and Similar
-     Rights.
-
-  e. Effective Technological Measures means those measures that, in the
-     absence of proper authority, may not be circumvented under laws
-     fulfilling obligations under Article 11 of the WIPO Copyright
-     Treaty adopted on December 20, 1996, and/or similar international
-     agreements.
-
-  f. Exceptions and Limitations means fair use, fair dealing, and/or
-     any other exception or limitation to Copyright and Similar Rights
-     that applies to Your use of the Licensed Material.
-
-  g. License Elements means the license attributes listed in the name
-     of a Creative Commons Public License. The License Elements of this
-     Public License are Attribution, NonCommercial, and ShareAlike.
-
-  h. Licensed Material means the artistic or literary work, database,
-     or other material to which the Licensor applied this Public
-     License.
-
-  i. Licensed Rights means the rights granted to You subject to the
-     terms and conditions of this Public License, which are limited to
-     all Copyright and Similar Rights that apply to Your use of the
-     Licensed Material and that the Licensor has authority to license.
-
-  j. Licensor means the individual(s) or entity(ies) granting rights
-     under this Public License.
-
-  k. NonCommercial means not primarily intended for or directed towards
-     commercial advantage or monetary compensation. For purposes of
-     this Public License, the exchange of the Licensed Material for
-     other material subject to Copyright and Similar Rights by digital
-     file-sharing or similar means is NonCommercial provided there is
-     no payment of monetary compensation in connection with the
-     exchange.
-
-  l. Share means to provide material to the public by any means or
-     process that requires permission under the Licensed Rights, such
-     as reproduction, public display, public performance, distribution,
-     dissemination, communication, or importation, and to make material
-     available to the public including in ways that members of the
-     public may access the material from a place and at a time
-     individually chosen by them.
-
-  m. Sui Generis Database Rights means rights other than copyright
-     resulting from Directive 96/9/EC of the European Parliament and of
-     the Council of 11 March 1996 on the legal protection of databases,
-     as amended and/or succeeded, as well as other essentially
-     equivalent rights anywhere in the world.
-
-  n. You means the individual or entity exercising the Licensed Rights
-     under this Public License. Your has a corresponding meaning.
-
-
-Section 2 -- Scope.
-
-  a. License grant.
-
-       1. Subject to the terms and conditions of this Public License,
-          the Licensor hereby grants You a worldwide, royalty-free,
-          non-sublicensable, non-exclusive, irrevocable license to
-          exercise the Licensed Rights in the Licensed Material to:
-
-            a. reproduce and Share the Licensed Material, in whole or
-               in part, for NonCommercial purposes only; and
-
-            b. produce, reproduce, and Share Adapted Material for
-               NonCommercial purposes only.
-
-       2. Exceptions and Limitations. For the avoidance of doubt, where
-          Exceptions and Limitations apply to Your use, this Public
-          License does not apply, and You do not need to comply with
-          its terms and conditions.
-
-       3. Term. The term of this Public License is specified in Section
-          6(a).
-
-       4. Media and formats; technical modifications allowed. The
-          Licensor authorizes You to exercise the Licensed Rights in
-          all media and formats whether now known or hereafter created,
-          and to make technical modifications necessary to do so. The
-          Licensor waives and/or agrees not to assert any right or
-          authority to forbid You from making technical modifications
-          necessary to exercise the Licensed Rights, including
-          technical modifications necessary to circumvent Effective
-          Technological Measures. For purposes of this Public License,
-          simply making modifications authorized by this Section 2(a)
-          (4) never produces Adapted Material.
-
-       5. Downstream recipients.
-
-            a. Offer from the Licensor -- Licensed Material. Every
-               recipient of the Licensed Material automatically
-               receives an offer from the Licensor to exercise the
-               Licensed Rights under the terms and conditions of this
-               Public License.
-
-            b. Additional offer from the Licensor -- Adapted Material.
-               Every recipient of Adapted Material from You
-               automatically receives an offer from the Licensor to
-               exercise the Licensed Rights in the Adapted Material
-               under the conditions of the Adapter's License You apply.
-
-            c. No downstream restrictions. You may not offer or impose
-               any additional or different terms or conditions on, or
-               apply any Effective Technological Measures to, the
-               Licensed Material if doing so restricts exercise of the
-               Licensed Rights by any recipient of the Licensed
-               Material.
-
-       6. No endorsement. Nothing in this Public License constitutes or
-          may be construed as permission to assert or imply that You
-          are, or that Your use of the Licensed Material is, connected
-          with, or sponsored, endorsed, or granted official status by,
-          the Licensor or others designated to receive attribution as
-          provided in Section 3(a)(1)(A)(i).
-
-  b. Other rights.
-
-       1. Moral rights, such as the right of integrity, are not
-          licensed under this Public License, nor are publicity,
-          privacy, and/or other similar personality rights; however, to
-          the extent possible, the Licensor waives and/or agrees not to
-          assert any such rights held by the Licensor to the limited
-          extent necessary to allow You to exercise the Licensed
-          Rights, but not otherwise.
-
-       2. Patent and trademark rights are not licensed under this
-          Public License.
-
-       3. To the extent possible, the Licensor waives any right to
-          collect royalties from You for the exercise of the Licensed
-          Rights, whether directly or through a collecting society
-          under any voluntary or waivable statutory or compulsory
-          licensing scheme. In all other cases the Licensor expressly
-          reserves any right to collect such royalties, including when
-          the Licensed Material is used other than for NonCommercial
-          purposes.
-
-
-Section 3 -- License Conditions.
-
-Your exercise of the Licensed Rights is expressly made subject to the
-following conditions.
-
-  a. Attribution.
-
-       1. If You Share the Licensed Material (including in modified
-          form), You must:
-
-            a. retain the following if it is supplied by the Licensor
-               with the Licensed Material:
-
-                 i. identification of the creator(s) of the Licensed
-                    Material and any others designated to receive
-                    attribution, in any reasonable manner requested by
-                    the Licensor (including by pseudonym if
-                    designated);
-
-                ii. a copyright notice;
-
-               iii. a notice that refers to this Public License;
-
-                iv. a notice that refers to the disclaimer of
-                    warranties;
-
-                 v. a URI or hyperlink to the Licensed Material to the
-                    extent reasonably practicable;
-
-            b. indicate if You modified the Licensed Material and
-               retain an indication of any previous modifications; and
-
-            c. indicate the Licensed Material is licensed under this
-               Public License, and include the text of, or the URI or
-               hyperlink to, this Public License.
-
-       2. You may satisfy the conditions in Section 3(a)(1) in any
-          reasonable manner based on the medium, means, and context in
-          which You Share the Licensed Material. For example, it may be
-          reasonable to satisfy the conditions by providing a URI or
-          hyperlink to a resource that includes the required
-          information.
-       3. If requested by the Licensor, You must remove any of the
-          information required by Section 3(a)(1)(A) to the extent
-          reasonably practicable.
-
-  b. ShareAlike.
-
-     In addition to the conditions in Section 3(a), if You Share
-     Adapted Material You produce, the following conditions also apply.
-
-       1. The Adapter's License You apply must be a Creative Commons
-          license with the same License Elements, this version or
-          later, or a BY-NC-SA Compatible License.
-
-       2. You must include the text of, or the URI or hyperlink to, the
-          Adapter's License You apply. You may satisfy this condition
-          in any reasonable manner based on the medium, means, and
-          context in which You Share Adapted Material.
-
-       3. You may not offer or impose any additional or different terms
-          or conditions on, or apply any Effective Technological
-          Measures to, Adapted Material that restrict exercise of the
-          rights granted under the Adapter's License You apply.
-
-
-Section 4 -- Sui Generis Database Rights.
-
-Where the Licensed Rights include Sui Generis Database Rights that
-apply to Your use of the Licensed Material:
-
-  a. for the avoidance of doubt, Section 2(a)(1) grants You the right
-     to extract, reuse, reproduce, and Share all or a substantial
-     portion of the contents of the database for NonCommercial purposes
-     only;
-
-  b. if You include all or a substantial portion of the database
-     contents in a database in which You have Sui Generis Database
-     Rights, then the database in which You have Sui Generis Database
-     Rights (but not its individual contents) is Adapted Material,
-     including for purposes of Section 3(b); and
-
-  c. You must comply with the conditions in Section 3(a) if You Share
-     all or a substantial portion of the contents of the database.
-
-For the avoidance of doubt, this Section 4 supplements and does not
-replace Your obligations under this Public License where the Licensed
-Rights include other Copyright and Similar Rights.
-
-
-Section 5 -- Disclaimer of Warranties and Limitation of Liability.
-
-  a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
-     EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
-     AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
-     ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
-     IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
-     WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
-     PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
-     ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
-     KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
-     ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
-
-  b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
-     TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
-     NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
-     INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
-     COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
-     USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
-     ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
-     DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
-     IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
-
-  c. The disclaimer of warranties and limitation of liability provided
-     above shall be interpreted in a manner that, to the extent
-     possible, most closely approximates an absolute disclaimer and
-     waiver of all liability.
-
-
-Section 6 -- Term and Termination.
-
-  a. This Public License applies for the term of the Copyright and
-     Similar Rights licensed here. However, if You fail to comply with
-     this Public License, then Your rights under this Public License
-     terminate automatically.
-
-  b. Where Your right to use the Licensed Material has terminated under
-     Section 6(a), it reinstates:
-
-       1. automatically as of the date the violation is cured, provided
-          it is cured within 30 days of Your discovery of the
-          violation; or
-
-       2. upon express reinstatement by the Licensor.
-
-     For the avoidance of doubt, this Section 6(b) does not affect any
-     right the Licensor may have to seek remedies for Your violations
-     of this Public License.
-
-  c. For the avoidance of doubt, the Licensor may also offer the
-     Licensed Material under separate terms or conditions or stop
-     distributing the Licensed Material at any time; however, doing so
-     will not terminate this Public License.
-
-  d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
-     License.
-
-
-Section 7 -- Other Terms and Conditions.
-
-  a. The Licensor shall not be bound by any additional or different
-     terms or conditions communicated by You unless expressly agreed.
-
-  b. Any arrangements, understandings, or agreements regarding the
-     Licensed Material not stated herein are separate from and
-     independent of the terms and conditions of this Public License.
-
-
-Section 8 -- Interpretation.
-
-  a. For the avoidance of doubt, this Public License does not, and
-     shall not be interpreted to, reduce, limit, restrict, or impose
-     conditions on any use of the Licensed Material that could lawfully
-     be made without permission under this Public License.
-
-  b. To the extent possible, if any provision of this Public License is
-     deemed unenforceable, it shall be automatically reformed to the
-     minimum extent necessary to make it enforceable. If the provision
-     cannot be reformed, it shall be severed from this Public License
-     without affecting the enforceability of the remaining terms and
-     conditions.
-
-  c. No term or condition of this Public License will be waived and no
-     failure to comply consented to unless expressly agreed to by the
-     Licensor.
-
-  d. Nothing in this Public License constitutes or may be interpreted
-     as a limitation upon, or waiver of, any privileges and immunities
-     that apply to the Licensor or You, including from the legal
-     processes of any jurisdiction or authority.
-
-=======================================================================
-
-Creative Commons is not a party to its public
-licenses. Notwithstanding, Creative Commons may elect to apply one of
-its public licenses to material it publishes and in those instances
-will be considered the “Licensor.” The text of the Creative Commons
-public licenses is dedicated to the public domain under the CC0 Public
-Domain Dedication. Except for the limited purpose of indicating that
-material is shared under a Creative Commons public license or as
-otherwise permitted by the Creative Commons policies published at
-creativecommons.org/policies, Creative Commons does not authorize the
-use of the trademark "Creative Commons" or any other trademark or logo
-of Creative Commons without its prior written consent including,
-without limitation, in connection with any unauthorized modifications
-to any of its public licenses or any other arrangements,
-understandings, or agreements concerning use of licensed material. For
-the avoidance of doubt, this paragraph does not form part of the
-public licenses.
-
-Creative Commons may be contacted at creativecommons.org.

README.md

@@ -1,37 +1,9 @@
 ---
-title: MinDALL E
+title: Logo Generator
 emoji: 🔥
 colorFrom: red
 colorTo: yellow
 sdk: streamlit
 app_file: app.py
 pinned: false
----
-
-# Configuration
-
-`title`: _string_  
-Display title for the Space
-
-`emoji`: _string_  
-Space emoji (emoji-only character allowed)
-
-`colorFrom`: _string_  
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`colorTo`: _string_  
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`sdk`: _string_  
-Can be either `gradio` or `streamlit`
-
-`sdk_version` : _string_  
-Only applicable for `streamlit` SDK.  
-See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
-
-`app_file`: _string_  
-Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
-Path is relative to the root of the repository.
-
-`pinned`: _boolean_  
-Whether the Space stays on top of your list.
+---

app.py

@@ -1,3 +1,5 @@
+""" Code inspired by https://huggingface.co/spaces/flax-community/dalle-mini
+"""
 import base64
 import os
 import time
@@ -47,14 +49,14 @@ if "models_loaded" not in st.session_state:
     st.session_state["models_loaded"] = False
 
 
-st.header("minDALL-E")
+st.header("Logo generator")
 #st.subheader("Generate images from text")
-st.write("Generate images from text: Interactive demo for [minDALL-E](https://github.com/kakaobrain/minDALL-E)")
+st.write("Generate logos from text")
 
 if not st.session_state["models_loaded"]:
     load_models()
 
-prompt = st.text_input("What do you want to see?")
+prompt = st.text_input("Text prompt to generate logo for:")
 
 DEBUG = False
 # UI code taken from https://huggingface.co/spaces/flax-community/dalle-mini/blob/main/app/streamlit/app.py
@@ -91,6 +93,6 @@ if prompt != "":
         cols[(i % n_columns) * 2].image(img)
     container.markdown(f"**{prompt}**")
 
-    st.button("Again!", key="again_button")
+    st.button("Run again", key="again_button")
     
-    st.write(f"<b><i>UI credits: <a href='https://huggingface.co/spaces/flax-community/dalle-mini'>DALL-E mini Space</a></i></b>", unsafe_allow_html=True)
+

configs/dalle-1.3B.yaml

@@ -1,33 +0,0 @@
-stage1:
-  type: vqgan
-  embed_dim: 256
-  n_embed: 16384
-  hparams:
-    double_z: False
-    z_channels: 256
-    resolution: 256
-    in_channels: 3
-    out_ch: 3
-    ch: 128
-    ch_mult: [1, 1, 2, 2, 4]
-    num_res_blocks: 2
-    attn_resolutions: [16]
-    pdrop: 0.0
-
-stage2:
-  type: transformer1d
-  vocab_size_txt: 16384
-  vocab_size_img: 16384
-  hparams:
-    embed_dim: 1536
-    n_layers: 42
-    n_heads: 24
-    n_dense_layers: 42
-    ctx_len_img: 256
-    ctx_len_txt: 64
-    embd_pdrop: 0.0
-    resid_pdrop: 0.0
-    attn_pdrop: 0.0
-    mlp_bias: True
-    attn_bias: True
-    gelu_use_approx: False

configs/transfer-imagenet-clscond-gen.yaml

@@ -1,49 +0,0 @@
-dataset:
-  dataset: imagenet
-  image_resolution: 256
-
-stage1:
-  type: vqgan
-  embed_dim: 256
-  n_embed: 16384
-  hparams:
-    double_z: False
-    z_channels: 256
-    resolution: 256
-    in_channels: 3
-    out_ch: 3
-    ch: 128
-    ch_mult: [1, 1, 2, 2, 4]
-    num_res_blocks: 2
-    attn_resolutions: [16]
-    pdrop: 0.0
-
-stage2:
-  type: igpt
-  use_cls_cond: True
-  vocab_size_img: 16384
-  hparams:
-    embed_dim: 1536
-    n_layers: 42
-    n_heads: 24
-    n_dense_layers: 42
-    ctx_len_img: 256
-    embd_pdrop: 0.0
-    resid_pdrop: 0.0
-    attn_pdrop: 0.0
-    mlp_bias: True
-    attn_bias: True
-    gelu_use_approx: False
-    n_classes: 1000
-
-optimizer:
-  opt_type: adamW
-  base_lr: 1e-4
-  weight_decay: 0.0
-  betas: [0.9, 0.95]
-  grad_clip_norm: 4.0
-
-experiment:
-  local_batch_size: 2
-  total_batch_size: 512
-  epochs: 8

configs/transfer-imagenet-uncond-gen.yaml

@@ -1,48 +0,0 @@
-dataset:
-  dataset: imagenet
-  image_resolution: 256
-
-stage1:
-  type: vqgan
-  embed_dim: 256
-  n_embed: 16384
-  hparams:
-    double_z: False
-    z_channels: 256
-    resolution: 256
-    in_channels: 3
-    out_ch: 3
-    ch: 128
-    ch_mult: [1, 1, 2, 2, 4]
-    num_res_blocks: 2
-    attn_resolutions: [16]
-    pdrop: 0.0
-
-stage2:
-  type: igpt
-  use_cls_cond: False
-  vocab_size_img: 16384
-  hparams:
-    embed_dim: 1536
-    n_layers: 42
-    n_heads: 24
-    n_dense_layers: 42
-    ctx_len_img: 256
-    embd_pdrop: 0.0
-    resid_pdrop: 0.0
-    attn_pdrop: 0.0
-    mlp_bias: True
-    attn_bias: True
-    gelu_use_approx: False
-
-optimizer:
-  opt_type: adamW
-  base_lr: 1e-4
-  weight_decay: 0.0
-  betas: [0.9, 0.95]
-  grad_clip_norm: 4.0
-
-experiment:
-  local_batch_size: 2
-  total_batch_size: 512
-  epochs: 8

dalle_last.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:227f1eb47f5be797bd6c38ff69fa881a669fe177d978f42e572833fb29e6371e
-size 5165951423

examples/sampling_ex.py

@@ -1,63 +0,0 @@
-# ------------------------------------------------------------------------------------
-# Minimal DALL-E
-# Copyright (c) 2021 KakaoBrain. All Rights Reserved.
-# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
-# ------------------------------------------------------------------------------------
-
-import os
-import sys
-import argparse
-import clip
-import numpy as np
-from PIL import Image
-
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from dalle.models import Dalle
-from dalle.utils.utils import set_seed, clip_score
-
-
-parser = argparse.ArgumentParser()
-parser.add_argument('-n', '--num_candidates', type=int, default=96)
-parser.add_argument('--prompt', type=str, default='A painting of a tree on the ocean')
-parser.add_argument('--softmax-temperature', type=float, default=1.0)
-parser.add_argument('--top-k', type=int, default=256)
-parser.add_argument('--top-p', type=float, default=None, help='0.0 <= top-p <= 1.0')
-parser.add_argument('--seed', type=int, default=0)
-
-args = parser.parse_args()
-
-# Setup
-assert args.top_k <= 256, "It is recommended that top_k is set lower than 256."
-
-set_seed(args.seed)
-device = 'cuda:0'
-model = Dalle.from_pretrained('minDALL-E/1.3B')  # This will automatically download the pretrained model.
-model.to(device=device)
-
-# Sampling
-images = model.sampling(prompt=args.prompt,
-                        top_k=args.top_k,
-                        top_p=args.top_p,
-                        softmax_temperature=args.softmax_temperature,
-                        num_candidates=args.num_candidates,
-                        device=device).cpu().numpy()
-images = np.transpose(images, (0, 2, 3, 1))
-
-# CLIP Re-ranking
-model_clip, preprocess_clip = clip.load("ViT-B/32", device=device)
-model_clip.to(device=device)
-rank = clip_score(prompt=args.prompt,
-                  images=images,
-                  model_clip=model_clip,
-                  preprocess_clip=preprocess_clip,
-                  device=device)
-
-# Save images
-images = images[rank]
-print(rank, images.shape)
-if not os.path.exists('./figures'):
-    os.makedirs('./figures')
-for i in range(min(16, args.num_candidates)):
-    im = Image.fromarray((images[i]*255).astype(np.uint8))
-    im.save(f'./figures/{args.prompt}_{i}.png')

examples/sampling_interactive_demo.ipynb

@@ -1,298 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "cdf36725-ec00-4027-95d6-374340c2264e",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "100%|█████████████████████████████████████| 4.72G/4.72G [02:04<00:00, 40.7MiB/s]\n",
-      "extracting: ./1.3B/tokenizer/bpe-16k-vocab.json (size:0MB): 100%|██████████| 7/7 [00:59<00:00,  8.51s/it]\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "/root/.cache/minDALL-E/1.3B/tokenizer successfully restored..\n",
-      "/root/.cache/minDALL-E/1.3B/stage1_last.ckpt successfully restored..\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "  0%|                                               | 0.00/338M [00:00<?, ?iB/s]"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "/root/.cache/minDALL-E/1.3B/stage2_last.ckpt succesfully restored..\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "100%|███████████████████████████████████████| 338M/338M [00:09<00:00, 38.5MiB/s]\n"
-     ]
-    }
-   ],
-   "source": [
-    "import os\n",
-    "import sys\n",
-    "import math\n",
-    "import argparse\n",
-    "import clip\n",
-    "import numpy as np\n",
-    "%matplotlib inline\n",
-    "import matplotlib.pyplot as plt\n",
-    "from PIL import Image\n",
-    "\n",
-    "sys.path.append(os.path.dirname(os.getcwd()))\n",
-    "\n",
-    "from dalle.models import Dalle\n",
-    "from dalle.utils.utils import set_seed, clip_score\n",
-    "\n",
-    "device = 'cuda:0'\n",
-    "model = Dalle.from_pretrained(\"minDALL-E/1.3B\")\n",
-    "model_clip, preprocess_clip = clip.load(\"ViT-B/32\", device=device)\n",
-    "\n",
-    "model_clip.to(device=device)\n",
-    "model.to(device=device)\n",
-    "\n",
-    "def sampling(prompt, top_k, softmax_temperature, seed, num_candidates=96, num_samples_for_display=36):\n",
-    "    # Setup\n",
-    "    n_row = int(math.sqrt(num_samples_for_display))\n",
-    "    n_col = int(math.sqrt(num_samples_for_display))\n",
-    "    set_seed(seed)\n",
-    "    \n",
-    "    # Sampling\n",
-    "    images = model.sampling(prompt=prompt,\n",
-    "                            top_k=top_k,\n",
-    "                            top_p=None,\n",
-    "                            softmax_temperature=softmax_temperature,\n",
-    "                            num_candidates=num_candidates,\n",
-    "                            device=device).cpu().numpy()\n",
-    "    images = np.transpose(images, (0, 2, 3, 1))\n",
-    "\n",
-    "    # CLIP Re-ranking\n",
-    "    rank = clip_score(prompt=prompt, images=images, model_clip=model_clip, preprocess_clip=preprocess_clip, device=device)\n",
-    "    images = images[rank]\n",
-    "    \n",
-    "    images = images[:num_samples_for_display]\n",
-    "    fig = plt.figure(figsize=(8*n_row, 8*n_col))\n",
-    "\n",
-    "    for i in range(num_samples_for_display):\n",
-    "        ax = fig.add_subplot(n_row, n_col, i+1)\n",
-    "        ax.imshow(images[i])\n",
-    "        ax.set_axis_off()\n",
-    "\n",
-    "    plt.tight_layout()\n",
-    "    plt.show()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "619add15-073e-40f4-9a97-06b89d647c81",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ee477531ea0e4b86b20d997f8cb83767",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "IntSlider(value=0, description='RND SEED: ', max=1024)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d63edc4725ef4f4e8a6f03f7693a481d",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "FloatSlider(value=1.0, description='SOFTMAX TEMPERATURE:', max=5.0, step=0.2)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5bb9170e9e8b4686a661799d8aff3901",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "IntSlider(value=256, description='TOP-K:', max=512, step=16)"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6b97b49debfc4f7ab002748e9fd89864",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Text(value='A painting of a monkey with sunglasses in the frame', description='String:', placeholder='Text pro…"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a520b10d8c0b4dd0bb6db56dc37b4422",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Button(description='Generate!', style=ButtonStyle())"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5a98437abf964636a467677dc4f816bb",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Output()"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "90d05006d50e4d88b8fb7c36095b12e7",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Output()"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "import ipywidgets as widgets\n",
-    "from IPython.display import display\n",
-    "from IPython.display import clear_output\n",
-    "\n",
-    "output = widgets.Output()\n",
-    "plot_output = widgets.Output()\n",
-    "\n",
-    "def btn_eventhandler(obj):\n",
-    "    output.clear_output()\n",
-    "    plot_output.clear_output()\n",
-    "    \n",
-    "    with output:\n",
-    "        print(f'SEED: {slider_seed.value}')\n",
-    "        print(f'Softmax Temperature: {slider_temp.value}')\n",
-    "        print(f'Top-K: {slider_topk.value}')\n",
-    "        print(f'Text prompt: {wd_text.value}')\n",
-    "        \n",
-    "    with plot_output:\n",
-    "        sampling(prompt=wd_text.value, top_k=slider_topk.value, softmax_temperature=slider_temp.value, seed=slider_seed.value)\n",
-    "    \n",
-    "slider_seed = widgets.IntSlider(\n",
-    "    min=0,\n",
-    "    max=1024,\n",
-    "    step=1,\n",
-    "    description='RND SEED: ',\n",
-    "    value=0\n",
-    ")\n",
-    "slider_topk = widgets.IntSlider(\n",
-    "    min=0,\n",
-    "    max=512,\n",
-    "    step=16,\n",
-    "    description='TOP-K:',\n",
-    "    value=256\n",
-    ")\n",
-    "slider_temp = widgets.FloatSlider(\n",
-    "    min=0.0,\n",
-    "    max=5.0,\n",
-    "    step=0.2,\n",
-    "    description='SOFTMAX TEMPERATURE:',\n",
-    "    value=1.0\n",
-    ")\n",
-    "wd_text = widgets.Text(\n",
-    "    value='A painting of a monkey with sunglasses in the frame',\n",
-    "    placeholder='Text prompt',\n",
-    "    description='String:',\n",
-    "    disabled=False\n",
-    ")\n",
-    "\n",
-    "display(slider_seed)\n",
-    "display(slider_temp)\n",
-    "display(slider_topk)\n",
-    "display(wd_text)\n",
-    "\n",
-    "btn = widgets.Button(description='Generate!')\n",
-    "display(btn)\n",
-    "btn.on_click(btn_eventhandler)\n",
-    "\n",
-    "display(output)\n",
-    "display(plot_output)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "20571236-3b9a-426e-ab29-96b643c8cbe1",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

examples/transfer_learning_ex.py

@@ -1,172 +0,0 @@
-# ------------------------------------------------------------------------------------
-# Minimal DALL-E
-# Copyright (c) 2021 KakaoBrain. All Rights Reserved.
-# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
-# ------------------------------------------------------------------------------------
-
-import os
-import sys
-import argparse
-from typing import Optional
-from datetime import datetime
-
-import torch
-from torch.utils.data import DataLoader
-import torchvision
-import torchvision.transforms as transforms
-import pytorch_lightning as pl
-from pytorch_lightning.callbacks import ModelCheckpoint, Callback
-from pytorch_lightning.loggers import TensorBoardLogger
-from pytorch_lightning.utilities.distributed import rank_zero_only
-
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from dalle.models import ImageGPT
-
-
-parser = argparse.ArgumentParser()
-
-parser.add_argument('-d', '--config-downstream', type=str, default=None, required=True)
-parser.add_argument('-u', '--path-upstream', type=str, default=None, required=True)
-parser.add_argument('-r', '--result-path', type=str, default=None, required=True)
-parser.add_argument('--imagenet-path', type=str, default=None, required=True)
-
-parser.add_argument('--n-gpus', type=int, default=1)
-parser.add_argument('--seed', type=int, default=0)
-
-
-args = parser.parse_args()
-
-
-class ImageLogger(Callback):
-    def __init__(self):
-        super().__init__()
-
-    @rank_zero_only
-    def log_img(self, pl_module, batch, current_epoch, split="train"):
-        with torch.no_grad():
-            images, labels = batch
-            recons = pl_module.stage1(images)
-            images = images.cpu()
-            recons = recons.cpu()
-
-            grid_org = (torchvision.utils.make_grid(images, nrow=8) + 1.0) / 2.0
-            grid_rec = (torchvision.utils.make_grid(recons, nrow=8) + 1.0) / 2.0
-            grid_rec = torch.clip(grid_rec, min=0, max=1)
-
-            pl_module.logger.experiment.add_image(f"images_org/{split}", grid_org, global_step=current_epoch)
-            pl_module.logger.experiment.add_image(f"images_rec/{split}", grid_rec, global_step=current_epoch)
-
-    def on_train_batch_end(self, trainer, pl_module, outputs, batch, batch_idx, dataloader_idx):
-        if batch_idx == 0 and trainer.current_epoch < 5:
-            self.log_img(pl_module, batch, current_epoch=trainer.current_epoch, split="train")
-
-    def on_validation_batch_end(self, trainer, pl_module, outputs, batch, batch_idx, dataloader_idx):
-        if batch_idx == 0 and trainer.current_epoch < 5:
-            self.log_img(pl_module, batch, current_epoch=trainer.current_epoch, split="test")
-
-
-class ImageNetDataModule(pl.LightningDataModule):
-    def __init__(self,
-                 data_dir: Optional[str] = None,
-                 image_resolution: int = 256,
-                 train_batch_size: int = 2,
-                 valid_batch_size: int = 32,
-                 num_workers: int = 8):
-        super().__init__()
-
-        self.data_dir = data_dir
-        self.image_resolution = image_resolution
-        self.train_batch_size = train_batch_size
-        self.valid_batch_size = valid_batch_size
-        self.num_workers = num_workers
-
-        self.train_transform = transforms.Compose(
-            [transforms.Resize(image_resolution),
-             transforms.RandomCrop(image_resolution),
-             transforms.ToTensor(),
-             transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])]
-        )
-        self.valid_transform = transforms.Compose(
-            [transforms.Resize(image_resolution),
-             transforms.CenterCrop(image_resolution),
-             transforms.ToTensor(),
-             transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])]
-        )
-
-    def setup(self, stage=None):
-        self.trainset = torchvision.datasets.ImageNet(root=self.data_dir, split='train', transform=self.train_transform)
-        self.validset = torchvision.datasets.ImageNet(root=self.data_dir, split='val', transform=self.valid_transform)
-
-    def train_dataloader(self):
-        return DataLoader(self.trainset,
-                          batch_size=self.train_batch_size,
-                          num_workers=self.num_workers,
-                          pin_memory=True)
-
-    def valid_dataloader(self):
-        return DataLoader(self.validset,
-                          batch_size=self.valid_batch_size,
-                          num_workers=self.num_workers,
-                          pin_memory=True)
-
-
-def setup_callbacks(config):
-    # Setup callbacks
-    now = datetime.now().strftime('%d%m%Y_%H%M%S')
-    result_path = os.path.join(args.result_path,
-                               os.path.basename(args.config_downstream).split('.')[0],
-                               now)
-    ckpt_path = os.path.join(result_path, 'ckpt')
-    log_path = os.path.join(result_path, 'log')
-
-    checkpoint_callback = ModelCheckpoint(
-        dirpath=ckpt_path,
-        filename="imagenet-clscond-gen-{epoch:02d}" if config.stage2.use_cls_cond else
-                 "imagenet-uncond-gen-{epoch:02d}",
-        every_n_epochs=config.experiment.save_ckpt_freq,
-        save_weights_only=True,
-        save_last=True
-    )
-    logger = TensorBoardLogger(log_path, name="iGPT")
-    logger_img = ImageLogger()
-    return checkpoint_callback, logger, logger_img
-
-
-if __name__ == '__main__':
-    pl.seed_everything(args.seed)
-
-    # Build iGPT
-    model, config = ImageGPT.from_pretrained(args.path_upstream, args.config_downstream)
-
-    # Setup callbacks
-    ckpt_callback, logger, logger_img = setup_callbacks(config)
-
-    # Build data modules
-    dataset = ImageNetDataModule(data_dir=args.imagenet_path,
-                                 image_resolution=config.dataset.image_resolution,
-                                 train_batch_size=config.experiment.local_batch_size,
-                                 valid_batch_size=config.experiment.valid_batch_size,
-                                 num_workers=16)
-    dataset.setup()
-    train_dataloader = dataset.train_dataloader()
-    valid_dataloader = dataset.valid_dataloader()
-    print(f"len(train_dataset) = {len(dataset.trainset)}")
-    print(f"len(valid_dataset) = {len(dataset.validset)}")
-
-    # Calculate how many batches are accumulated
-    assert config.experiment.total_batch_size % (config.experiment.local_batch_size * args.n_gpus) == 0
-    grad_accm_steps = config.experiment.total_batch_size // (config.experiment.local_batch_size * args.n_gpus)
-    config.optimizer.max_steps = len(dataset.trainset) // config.experiment.total_batch_size * config.experiment.epochs
-
-    # Build trainer
-    trainer = pl.Trainer(max_epochs=config.experiment.epochs,
-                         accumulate_grad_batches=grad_accm_steps,
-                         gradient_clip_val=config.optimizer.grad_clip_norm,
-                         precision=16 if config.experiment.use_amp else 32,
-                         callbacks=[ckpt_callback, logger_img],
-                         accelerator="gpu",
-                         devices=args.n_gpus,
-                         strategy="ddp",
-                         logger=logger)
-    trainer.fit(model, train_dataloader, valid_dataloader)

last.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8c8e53ac2ae57e72d2df9bcecd6b758e9ec4ae0eb96a0154719feb1d7ef4708c
-size 980089751

server.py

@@ -10,11 +10,10 @@ from fastapi import FastAPI
 import numpy as np
 from PIL import Image
 
-#import clip
 from dalle.models import Dalle
 import logging
 import streamlit as st
-from dalle.utils.utils import clip_score, download
+
 
 print("Loading models...")
 app = FastAPI()
@@ -29,13 +28,9 @@ logging.info("End downloading")
 device = "cuda" if torch.cuda.is_available() else "cpu"
 model = Dalle.from_pretrained("minDALL-E/1.3B")
 
-# NEW METHOD
 model.load_state_dict(torch.load(full_dict_path, map_location=torch.device('cpu')))
 model.to(device=device)
 
-# model_clip, preprocess_clip = clip.load("ViT-B/32", device=device)
-# model_clip.to(device=device)
-
 print("Models loaded !")
 
 
@@ -62,11 +57,6 @@ def sample(prompt):
     logging.info("sampling succeeded")
     images = np.transpose(images, (0, 2, 3, 1))
 
-    # CLIP Re-ranking
-    # rank = clip_score(
-    #     prompt=prompt, images=images, model_clip=model_clip, preprocess_clip=preprocess_clip, device=device
-    # )
-    # images = images[rank]
     
     pil_images = []
     for i in range(len(images)):